{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T18:36:35Z","timestamp":1786214195319,"version":"3.56.0"},"reference-count":423,"publisher":"Emerald","issue":"2-3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,2,21]]},"abstract":"<jats:p>The present paper surveys neural approaches to conversational AI that have been developed in the last few years. We group conversational systems into three categories: (1) question answering agents, (2) task-oriented dialogue agents, and (3) chatbots. For each category, we present a review of state-of-the-art neural approaches, draw the connection between them and traditional approaches, and discuss the progress that has been made and challenges still being faced, using specific systems and models as case studies.<\/jats:p>","DOI":"10.1561\/1500000074","type":"journal-article","created":{"date-parts":[[2019,2,21]],"date-time":"2019-02-21T10:01:23Z","timestamp":1550743283000},"page":"127-298","source":"Crossref","is-referenced-by-count":173,"title":["Neural Approaches to Conversational AI"],"prefix":"10.1108","volume":"13","author":[{"given":"Jianfeng","family":"Gao","sequence":"first","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michel","family":"Galley","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihong","family":"Li","sequence":"additional","affiliation":[{"name":"Google Brain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","published-online":{"date-parts":[[2019,2,21]]},"reference":[{"key":"2026040314515463800_ref001","article-title":"\u201cOverview of the TREC 2015 LiveQA Track\u201d","author":"Agichtein","year":"2015","journal-title":"TREC"},{"key":"2026040314515463800_ref002","first-page":"622","article-title":"\u201cAssessing Dialog System User Simulation Evaluation Measures Using Human Judges\u201d","volume-title":"Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Ai","year":"2008"},{"key":"2026040314515463800_ref003","doi-asserted-by":"crossref","first-page":"124","DOI":"10.18653\/v1\/2007.sigdial-1.23","article-title":"\u201cComparing Spoken Dialog Corpora Collected with Recruited Subjects versus Real Users\u201d","volume-title":"Proceedings of the 8th SIGdial Workshop on Discourse and Dialogue","author":"Ai","year":"2007"},{"key":"2026040314515463800_ref004","article-title":"\u201cConversational Contextual Cues: The Case of Personalization and History for Response Ranking\u201d","author":"Al-Rfou","year":"2016","journal-title":"CoRR"},{"key":"2026040314515463800_ref005","first-page":"880","article-title":"\u201cA Re-examination of Machine Learning Approaches for Sentence-Level MT Evaluation\u201d","volume-title":"Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics","author":"Albrecht","year":"2007"},{"issue":"4","key":"2026040314515463800_ref006","first-page":"27","article-title":"\u201cToward Conversational Human-Computer Interaction\u201d","volume":"22","author":"Allen","year":"2001","journal-title":"AI Magazine"},{"key":"2026040314515463800_ref007","first-page":"502","article-title":"\u201cA Simple Domain-Independent Probabilistic Approach to Generation\u201d","volume-title":"Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Angeli","year":"2010"},{"key":"2026040314515463800_ref008","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1007\/978-3-540-76298-0_52","volume-title":"The Semantic Web","author":"Auer","year":"2007"},{"key":"2026040314515463800_ref009","article-title":"\u201cNeural machine translation by jointly learning to align and translate\u201d","volume-title":"Proceedings of ICLR","author":"Bahdanau","year":"2015"},{"key":"2026040314515463800_ref010","first-page":"65","article-title":"\u201cMETEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments\u201d","volume-title":"ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"2026040314515463800_ref011","doi-asserted-by":"crossref","first-page":"967","DOI":"10.3115\/v1\/P14-1091","article-title":"\u201cKnowledge-based question answering as machine translation\u201d","volume-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Bao","year":"2014"},{"key":"2026040314515463800_ref012","first-page":"2476","article-title":"\u201cTowards Zero-Shot Frame Semantic Parsing for Domain Scaling\u201d","volume-title":"Proceedings of the 18th Annual Conference of the International Speech Communication Association (INTERSPEECH)","author":"Bapna","year":"2017"},{"key":"2026040314515463800_ref013","doi-asserted-by":"crossref","first-page":"2","DOI":"10.18653\/v1\/W15-4602","article-title":"\u201cHuman-Machine Dialogue as a Stochastic Game\u201d","volume-title":"Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Barlier","year":"2015"},{"key":"2026040314515463800_ref014","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"\u201cInfinite-Horizon Policy-Gradient Estimation\u201d","volume":"15","author":"Baxter","year":"2001","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2026040314515463800_ref015","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1613\/jair.807","article-title":"\u201cExperiments with Infinite-Horizon, Policy-Gradient Estimation\u201d","volume":"15","author":"Baxter","year":"2001","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2026040314515463800_ref016","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/3-540-48315-2_4","volume-title":"International and Interdisciplinary Conference on Modeling and Using Context","author":"Bell","year":"1999"},{"key":"2026040314515463800_ref017","first-page":"1471","article-title":"\u201cUnifying Count-Based Exploration and Intrinsic Motivation\u201d","author":"Bellemare","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"2026040314515463800_ref018","first-page":"1533","article-title":"\u201cSemantic parsing on Freebase from question-answer pairs\u201d","volume-title":"Proceedings of the 2013 Other on Empirical Methods in Natural Language Processing","author":"Berant","year":"2013"},{"key":"2026040314515463800_ref019","volume-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1996"},{"key":"2026040314515463800_ref020","article-title":"\u201csoc2seq: Social Embedding meets Conversation Model\u201d","volume-title":"CoRR","author":"Bhatia","year":"2017"},{"key":"2026040314515463800_ref021","volume-title":"Natural Language Processing with Python","author":"Bird","year":"2009"},{"key":"2026040314515463800_ref022","first-page":"2","article-title":"\u201cSpoken Dialog Challenge 2010: Comparison of Live and Control Test Results\u201d","volume-title":"Proceedings of the 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Black","year":"2011"},{"key":"2026040314515463800_ref023","first-page":"225","article-title":"\u201cModels for Multiparty Engagement in Open-World Dialog\u201d","volume-title":"Proceedings of the 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Bohus","year":"2009"},{"key":"2026040314515463800_ref024","first-page":"98","article-title":"\u201cMultiparty Turn Taking in Situated Dialog: Study, Lessons, and Directions\u201d","volume-title":"Proceedings of the 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Bohus","year":"2011"},{"issue":"3","key":"2026040314515463800_ref025","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.csl.2008.10.001","article-title":"\u201cThe RavenClaw Dialog Management Framework: Architecture and Systems\u201d","volume":"23","author":"Bohus","year":"2009","journal-title":"Computer Speech & Language"},{"key":"2026040314515463800_ref026","first-page":"637","article-title":"\u201cDirections Robot: In-the-wild Experiences and Lessons Learned\u201d","volume-title":"Proceedings of the International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)","author":"Bohus","year":"2014"},{"key":"2026040314515463800_ref027","first-page":"1247","article-title":"\u201cFreebase: a collaboratively created graph database for structuring human knowledge\u201d","volume-title":"Proceedings of the 2008 ACM SIGMOD International Other on Management of Data","author":"Bollacker","year":"2008"},{"key":"2026040314515463800_ref028","article-title":"\u201cLearning End-to-End Goal-Oriented Dialog\u201d","volume-title":"Proceedings of the International Other on Learning Representations (ICLR)","author":"Bordes","year":"2017"},{"key":"2026040314515463800_ref029","first-page":"2787","article-title":"\u201cTranslating embeddings for modeling multi-relational data\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Bordes","year":"2013"},{"key":"2026040314515463800_ref030","first-page":"115","article-title":"\u201cDIPPER: Description and Formalisation of an Information-State Update Dialogue System Architecture\u201d","volume-title":"Proceedings of the 4th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Bos","year":"2003"},{"key":"2026040314515463800_ref031","first-page":"576","article-title":"\u201cComparison of an End-to-End Trainable Dialogue System with a Modular Statistical Dialogue System\u201d","volume-title":"Proceedings of the 19th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Braunschweiler","year":"2018"},{"key":"2026040314515463800_ref032","first-page":"86","article-title":"\u201cSub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning\u201d","volume-title":"Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL)","author":"Budzianowski","year":"2017"},{"key":"2026040314515463800_ref033","first-page":"1","article-title":"\u201cFindings of the 2009 Workshop on Statistical Machine Translation\u201d","volume-title":"Proceedings of the Fourth Workshop on Statistical Machine Translation","author":"Callison-Burch","year":"2009"},{"key":"2026040314515463800_ref034","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/978-1-4615-5529-2_5","volume-title":"Learning to Learn","author":"Caruana","year":"1998"},{"key":"2026040314515463800_ref035","first-page":"714","article-title":"\u201cFeudal Reinforcement Learning for Dialogue Management in Large Domains\u201d","volume-title":"Proceedings of the 2018 Other of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Casanueva","year":"2018"},{"key":"2026040314515463800_ref036","first-page":"555","article-title":"\u201cThe Best Lexical Metric for Phrase-based Statistical MT System Optimization\u201d","volume-title":"Human Language Technologies: The 2010 Annual Other of the North American Chapter of the Association for Computational Linguistics","author":"Cer","year":"2010"},{"key":"2026040314515463800_ref037","first-page":"1025","article-title":"\u201cUser Simulation in Dialogue Systems Using Inverse Reinforcement Learning\u201d","volume-title":"Proceedings of the 12th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Chandramohan","year":"2011"},{"key":"2026040314515463800_ref038","first-page":"2249","article-title":"\u201cAn Empirical Evaluation of Thompson Sampling\u201d","author":"Chapelle","year":"2012","journal-title":"Advances in Neural Information Processing Systems 24 (NIPS)"},{"key":"2026040314515463800_ref039","unstructured":"Chen\n              D.\n            \n            \n              Bolton\n              J.\n            \n            \n              Manning\n              C. D.\n            \n          . (2016a). \u201cA thorough examination of the CNN\/Daily Mail reading comprehension task\u201d. arXiv preprint. 1606.02858."},{"key":"2026040314515463800_ref040","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P17-1171","article-title":"\u201cReading Wikipedia to answer open-domain questions\u201d","volume-title":"arXIV","author":"Chen","year":"2017"},{"key":"2026040314515463800_ref041","doi-asserted-by":"crossref","DOI":"10.1145\/3166054.3166058","article-title":"\u201cA Survey on Dialogue Systems: Recent Advances and New Frontiers\u201d","volume-title":"arXiv preprint","author":"Chen","year":"2017"},{"key":"2026040314515463800_ref042","first-page":"4984","article-title":"\u201cQ-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes\u201d","volume":"30","author":"Chen","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026040314515463800_ref043","first-page":"1257","article-title":"\u201cStructured Dialogue Policy with Graph Neural Networks\u201d","volume-title":"Proceedings of the 27th International Other on Computational Linguistics (COLING)","author":"Chen","year":"2018"},{"key":"2026040314515463800_ref044","first-page":"2454","article-title":"\u201cAgent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning\u201d","volume-title":"Proceedings of the 2017 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Chen","year":"2017"},{"key":"2026040314515463800_ref045","first-page":"8","article-title":"\u201cDeep Learning for Dialogue Systems\u201d","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Tutorial Abstracts)","author":"Chen","year":"2017"},{"key":"2026040314515463800_ref046","first-page":"6","article-title":"\u201cOpen-Domain Neural Dialogue Systems\u201d","volume-title":"Proceedings of the Eighth International Joint Other on Natural Language Processing (Tutorial Abstracts)","author":"Chen","year":"2017"},{"key":"2026040314515463800_ref047","first-page":"3245","article-title":"\u201cEnd-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding\u201d","volume-title":"Proceedings of the 17th Annual Meeting of the International Speech Communication Association","author":"Chen","year":"2016"},{"key":"2026040314515463800_ref048","doi-asserted-by":"crossref","first-page":"103","DOI":"10.3115\/v1\/W14-4012","article-title":"\u201cOn the Properties of Neural Machine Translation: Encoder\u2013Decoder Approaches\u201d","volume-title":"Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation","author":"Cho","year":"2014"},{"key":"2026040314515463800_ref049","first-page":"1724","article-title":"\u201cLearning Phrase Representations using RNN Encoder\u2013Decoder for Statistical Machine Translation\u201d","volume-title":"Proceedings of the 2014 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Cho","year":"2014"},{"key":"2026040314515463800_ref050","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D18-1241","article-title":"\u201cQuAC: Question Answering in Context\u201d","volume-title":"arXiv preprint","author":"Choi","year":"2018"},{"key":"2026040314515463800_ref051","article-title":"\u201cThink you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge\u201d","volume-title":"arXiv preprint","author":"Clark","year":"2018"},{"key":"2026040314515463800_ref052","volume-title":"Artificial Paranoia: A Computer Simulation of Paranoid Processes","author":"Colby","year":"1975"},{"key":"2026040314515463800_ref053","first-page":"1277","article-title":"\u201cTools for Research and Education in Speech Science\u201d","volume-title":"Proceedings of International Other of Phonetic Sciences","author":"Cole","year":"1999"},{"key":"2026040314515463800_ref054","first-page":"28","article-title":"\u201cCoding Dialogs with the DAMSL Annotation Scheme\u201d","volume-title":"Proceedings of AAAI Fall Symposium on Communicative Action in Humans and Machines","author":"Core","year":"1997"},{"key":"2026040314515463800_ref055","first-page":"148","article-title":"\u201cA Machine Learning Approach to the Automatic Evaluation of Machine Translation\u201d","volume-title":"Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics","author":"Corston-Oliver","year":"2001"},{"key":"2026040314515463800_ref056","article-title":"\u201cTextWorld: A Learning Environment for Text-based Games\u201d","volume-title":"arXiv","author":"C\u00f4t\u00e9","year":"2018"},{"key":"2026040314515463800_ref057","first-page":"47","article-title":"\u201cTask Completion Platform: A Self-service Multi-domain Goal Oriented Dialogue Platform\u201d","volume-title":"Proceedings of the 2016 Other of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL): Demonstrations Session","author":"Crook","year":"2016"},{"issue":"2","key":"2026040314515463800_ref058","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.csl.2009.07.001","article-title":"\u201cEvaluation of a Hierarchical Reinforcement Learning Spoken Dialogue System\u201d","volume":"24","author":"Cuay\u00e1huitl","year":"2010","journal-title":"Computer Speech and Language"},{"key":"2026040314515463800_ref059","article-title":"\u201cDeep Reinforcement Learning for Multi-Domain Dialogue Systems\u201d","volume-title":"arXiv preprint","author":"Cuay\u00e1huitl","year":"2016"},{"key":"2026040314515463800_ref060","article-title":"\u201cBoosting the Actor with Dual Critic\u201d","volume-title":"Proceedings of the Sixth International Other on Learning Representations (ICLR)","author":"Dai","year":"2018"},{"key":"2026040314515463800_ref061","first-page":"1133","article-title":"\u201cSBEEED: Convergent Reinforcement Learning with Nonlinear Function Approximation\u201d","volume-title":"Proceedings of the Thirty-Fifth International Other on Machine Learning (ICML-18)","author":"Dai","year":"2018"},{"key":"2026040314515463800_ref062","first-page":"63","article-title":"\u201cOverview of the TREC 2007 Question Answering Track\u201d","volume":"7","author":"Dang","year":"2007","journal-title":"TREC"},{"key":"2026040314515463800_ref063","first-page":"5717","article-title":"\u201cUnifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning\u201d","volume-title":"Advances in Neural Information Processing Systems 30 (NIPS)","author":"Dann","year":"2017"},{"key":"2026040314515463800_ref064","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.121","article-title":"\u201cVisual Dialog\u201d","volume-title":"CVPR","author":"Das","year":"2017"},{"key":"2026040314515463800_ref065","article-title":"\u201cGo for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning\u201d","volume-title":"arXiv preprint","author":"Das","year":"2017"},{"key":"2026040314515463800_ref066","first-page":"1301","article-title":"\u201cUncertainty Management for On-Line Optimisation of a POMDP-Based Large-Scale Spoken Dialogue System\u201d","volume-title":"Proceedings of the 12th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Daubigney","year":"2011"},{"issue":"8","key":"2026040314515463800_ref067","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1109\/JSTSP.2012.2229257","article-title":"\u201cA Comprehensive Reinforcement Learning Framework for Dialogue Management Optimization\u201d","volume":"6","author":"Daubigney","year":"2012","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"2026040314515463800_ref068","first-page":"271","article-title":"\u201cFeudal Reinforcement Learning\u201d","volume-title":"Advances in Neural Information Processing Systems 5 (NIPS)","author":"Dayan","year":"1993"},{"key":"2026040314515463800_ref069","first-page":"1061","article-title":"\u201cSimSensei Kiosk: A Virtual Human Interviewer for Healthcare Decision Support\u201d","volume-title":"Proceedings of the International Other on Autonomous Agents and Multi-Agent Systems (AAMAS)","author":"DeVault","year":"2014"},{"key":"2026040314515463800_ref070","article-title":"\u201cBERT: Pre-training of deep bidirectional transformers for language understanding\u201d","volume-title":"arXiv preprint","author":"Devlin","year":"2018"},{"key":"2026040314515463800_ref071","first-page":"484","article-title":"\u201cTowards End-to-End Reinforcement Learning of Dialogue Agents for Information Access\u201d","volume-title":"ACL","author":"Dhingra","year":"2017"},{"key":"2026040314515463800_ref072","article-title":"\u201cGated-attention readers for text comprehension\u201d","volume-title":"arXiv preprint","author":"Dhingra","year":"2016"},{"key":"2026040314515463800_ref073","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","article-title":"\u201cHierarchical Reinforcement Learning with the MAXQ Value Function Decomposition\u201d","volume":"13","author":"Dietterich","year":"2000","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2026040314515463800_ref074","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.18653\/v1\/P17-1106","article-title":"\u201cVisualizing and Understanding Neural Machine Translation\u201d","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Ding","year":"2017"},{"key":"2026040314515463800_ref075","article-title":"\u201cEvaluating prerequisite qualities for learning end-to-end dialog systems\u201d","volume-title":"ICLR","author":"Dodge","year":"2016"},{"key":"2026040314515463800_ref076","article-title":"\u201cSearchQA: A new Q&A dataset augmented with context from a search engine\u201d","volume-title":"arXiv preprint","author":"Dunn","year":"2017"},{"key":"2026040314515463800_ref077","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/ASRU.1997.658991","article-title":"\u201cUser Modeling for Spoken Dialogue System Evaluation\u201d","volume-title":"Proceedings of the 1997 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","author":"Eckert","year":"1997"},{"key":"2026040314515463800_ref078","first-page":"1151","article-title":"\u201cA Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems\u201d","volume-title":"Proceedings of the 17th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"El Asri","year":"2016"},{"key":"2026040314515463800_ref079","first-page":"95","article-title":"\u201cReward Function Learning for Dialogue Management\u201d","volume-title":"Proceedings of the Sixth Starting AI Researchers\u2019 Symposium (STAIRS)","author":"El Asri","year":"2012"},{"key":"2026040314515463800_ref080","first-page":"201","article-title":"\u201cReinforcement Learning with Gaussian Processes\u201d","volume-title":"Proceedings of the 22nd International Other on Machine Learning (ICML)","author":"Engel","year":"2005"},{"key":"2026040314515463800_ref081","first-page":"37","article-title":"\u201cKey-Value Retrieval Networks for Task-Oriented Dialogue\u201d","volume-title":"Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL)","author":"Eric","year":"2017"},{"key":"2026040314515463800_ref082","first-page":"503","article-title":"\u201cTree-Based Batch Mode Reinforcement Learning\u201d","volume":"6","author":"Ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"2026040314515463800_ref083","first-page":"1473","article-title":"\u201cFrom captions to visual concepts and back\u201d","volume-title":"Proceedings of the IEEE Other on Computer Vision and Pattern Recognition","author":"Fang","year":"2015"},{"key":"2026040314515463800_ref084","doi-asserted-by":"crossref","first-page":"101","DOI":"10.18653\/v1\/W16-3613","article-title":"\u201cPolicy Networks with Two-stage Training for Dialogue Systems\u201d","volume-title":"Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Fatemi","year":"2016"},{"key":"2026040314515463800_ref085","article-title":"\u201cAvoiding Echo-Responses in a Retrieval-Based Conversation System\u201d","volume-title":"CoRR","author":"Fedorenko","year":"2017"},{"key":"2026040314515463800_ref086","article-title":"\u201cTowards Empathetic Human-Robot Interactions\u201d","volume-title":"CoRR","author":"Fung","year":"2016"},{"key":"2026040314515463800_ref087","first-page":"A45","article-title":"\u201cdeltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets\u201d","volume-title":"ACL-IJCNLP","author":"Galley","year":"2015"},{"key":"2026040314515463800_ref088","article-title":"\u201cAn Introduction to Deep Learning for Natural Language Processing\u201d","volume-title":"International Summer School on Deep Learning","author":"Ge","year":"2017"},{"key":"2026040314515463800_ref089","first-page":"1371","article-title":"\u201cNeural Approaches to Conversational AI\u201d","volume-title":"The 41st International ACM SIGIR Other on Research & Development in Information Retrieval","author":"Gao","year":"2018"},{"key":"2026040314515463800_ref090","doi-asserted-by":"crossref","first-page":"2","DOI":"10.18653\/v1\/P18-5002","article-title":"\u201cNeural Approaches to Conversational AI\u201d","volume-title":"Proceedings of ACL 2018, Tutorial Abstracts","author":"Gao","year":"2018"},{"key":"2026040314515463800_ref091","doi-asserted-by":"crossref","first-page":"699","DOI":"10.3115\/v1\/P14-1066","article-title":"\u201cLearning continuous phrase representations for translation modeling\u201d","volume-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Gao","year":"2014"},{"key":"2026040314515463800_ref092","first-page":"2","article-title":"\u201cModeling interestingness with deep neural networks\u201d","volume-title":"Proceedings of the 2014 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Gao","year":"2014"},{"key":"2026040314515463800_ref093","first-page":"397","article-title":"\u201cIncorporating vector space similarity in random walk inference over knowledge bases\u201d","volume-title":"Proceedings of the 2014 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Gardner","year":"2014"},{"key":"2026040314515463800_ref094","first-page":"8367","article-title":"\u201cOn-line Policy Optimisation of Bayesian Spoken Dialogue Systems via Human Interaction\u201d","volume-title":"Proceedings of the IEEE International Other on Acoustics, Speech and Signal Processing (ICASSP)","author":"Ga\u0161i\u0107","year":"2013"},{"key":"2026040314515463800_ref095","first-page":"140","article-title":"\u201cIncremental On-line Adaptation of POMDP-based Dialogue Managers to Extended Domains\u201d","volume-title":"Proceedings of the 15th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Ga\u0161i\u0107","year":"2014"},{"key":"2026040314515463800_ref096","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1109\/ASRU.2015.7404871","article-title":"\u201cPolicy Committee for Adaptation in Multi-domain Spoken Dialogue Systems\u201d","volume-title":"Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","author":"Ga\u0161i\u0107","year":"2015"},{"issue":"1","key":"2026040314515463800_ref097","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/TASL.2013.2282190","article-title":"\u201cGaussian Processes for POMDP-based Dialogue Manager Optimization\u201d","volume":"22","author":"Ga\u0161i\u0107","year":"2014","journal-title":"IEEE Transactions on Audio, Speech & Language Processing"},{"key":"2026040314515463800_ref098","first-page":"1065","article-title":"\u201cUser Simulation for Spoken Dialogue Systems: Learning and Evaluation\u201d","volume-title":"Proceedings of the 9th International Other on Spoken Language Processing (INTERSPEECH)","author":"Georgila","year":"2006"},{"key":"2026040314515463800_ref099","first-page":"5110","article-title":"\u201cA Knowledge-Grounded Neural Conversation Model\u201d","volume-title":"Proceedings of ACL","author":"Ghazvininejad","year":"2018"},{"key":"2026040314515463800_ref100","first-page":"195","article-title":"\u201cA Smorgasbord of Features for Automatic MT Evaluation\u201d","volume-title":"Proceedings of the Third Workshop on Statistical Machine Translation","author":"Gim\u00e9nez","year":"2008"},{"key":"2026040314515463800_ref101","volume-title":"MIT Press","author":"Goodfellow","year":"2016"},{"key":"2026040314515463800_ref102","first-page":"2672","article-title":"\u201cGenerative adversarial nets\u201d","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Goodfellow","year":"2014"},{"key":"2026040314515463800_ref103","first-page":"172","article-title":"\u201cTesting for Significance of Increased Correlation with Human Judgment\u201d","volume-title":"Proceedings of the 2014 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Graham","year":"2014"},{"key":"2026040314515463800_ref104","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/N15-1124","article-title":"\u201cAccurate Evaluation of Segment-level Machine Translation Metrics\u201d","volume-title":"NAACL-HLT","author":"Graham","year":"2015"},{"key":"2026040314515463800_ref105","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"\u201cFramewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures\u201d","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Networks"},{"key":"2026040314515463800_ref106","doi-asserted-by":"crossref","first-page":"1631","DOI":"10.18653\/v1\/P16-1154","article-title":"\u201cIncorporating Copying Mechanism in Sequence-to-Sequence Learning\u201d","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Gu","year":"2016"},{"key":"2026040314515463800_ref107","article-title":"\u201cQ-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic\u201d","volume-title":"Proceedings of the 5th International Other on Learning Representations (ICLR)","author":"Gu","year":"2017"},{"key":"2026040314515463800_ref108","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D15-1038","article-title":"\u201cTraversing knowledge graphs in vector space\u201d","volume-title":"arXiv preprint","author":"Guu","year":"2015"},{"key":"2026040314515463800_ref109","first-page":"715","article-title":"\u201cMulti-Domain Joint Semantic Frame Parsing using Bi-directional RNN-LSTM\u201d","volume-title":"Proceedings of the 17th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Hakkani-T\u00fcr","year":"2016"},{"key":"2026040314515463800_ref110","first-page":"330","article-title":"\u201cA Discriminative Classification-Based Approach to Information State Updates for a Multi-Domain Dialog System\u201d","volume-title":"Proceedings of the 13th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Hakkani-T\u00fcr","year":"2012"},{"key":"2026040314515463800_ref111","first-page":"2273","article-title":"\u201cSubjective Evaluation of Spoken Dialogue Systems using SERVQUAL Method\u201d","volume-title":"Proceedings of the 8th International Other on Spoken Language Processing (INTERSPEECH)","author":"Hartikainen","year":"2004"},{"key":"2026040314515463800_ref112","first-page":"29","article-title":"\u201cDeep Recurrent Q-Learning for Partially Observable MDPs\u201d","volume-title":"Proceedings of the AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents","author":"Hausknecht","year":"2015"},{"key":"2026040314515463800_ref113","first-page":"1621","article-title":"\u201cDeep Reinforcement Learning with a Natural Language Action Space\u201d","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"He","year":"2016"},{"key":"2026040314515463800_ref114","first-page":"199","article-title":"\u201cGenerating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning\u201d","volume-title":"ACL","author":"He","year":"2017"},{"key":"2026040314515463800_ref115","article-title":"\u201cDuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications\u201d","volume-title":"arXiv preprint","author":"He","year":"2017"},{"issue":"4","key":"2026040314515463800_ref116","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1162\/coli.2008.07-028-R2-05-82","article-title":"\u201cHybrid Reinforcement\/Supervised Learning of Dialogue Policies from Fixed Data Sets\u201d","volume":"34","author":"Henderson","year":"2008","journal-title":"Computational Linguistics"},{"key":"2026040314515463800_ref117","article-title":"\u201cMachine Learning for Dialog State Tracking: A Review\u201d","volume-title":"Proceedings of The First International Workshop on Machine Learning in Spoken Language Processing","author":"Henderson","year":"2015"},{"key":"2026040314515463800_ref118","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1109\/SLT.2014.7078595","article-title":"\u201cThe 3rd Dialog State Tracking Challenge\u201d","volume-title":"Proceedings of the 2014 IEEE Spoken Language Technology Workshop (SLT)","author":"Henderson","year":"2014"},{"key":"2026040314515463800_ref119","first-page":"263","article-title":"\u201cThe Second Dialog State Tracking Challenge\u201d","volume-title":"Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Henderson","year":"2014"},{"key":"2026040314515463800_ref120","first-page":"467","article-title":"\u201cDeep Neural Network Approach for the Dialog State Tracking Challenge\u201d","volume-title":"Proceedings of the 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Henderson","year":"2013"},{"key":"2026040314515463800_ref121","first-page":"1693","article-title":"\u201cTeaching machines to read and comprehend\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Hermann","year":"2015"},{"key":"2026040314515463800_ref122","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P16-1145","article-title":"\u201cWikiReading: A novel large-scale language understanding task over Wikipedia\u201d","volume-title":"arXiv preprint","author":"Hewlett","year":"2016"},{"key":"2026040314515463800_ref123","article-title":"\u201cThe Goldilocks principle: Reading children\u2019s books with explicit memory representations\u201d","volume-title":"arXiv preprint","author":"Hill","year":"2015"},{"key":"2026040314515463800_ref124","first-page":"5","article-title":"\u201cKeeping the neural networks simple by minimizing the description length of the weights\u201d","volume-title":"Proceedings of the Sixth Annual Other on Computational Learning Theory","author":"Hinton","year":"1993"},{"issue":"6","key":"2026040314515463800_ref125","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"\u201cDeep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups\u201d","volume":"29","author":"Hinton","year":"2012","journal-title":"IEEE Signal Processing Magazine"},{"key":"2026040314515463800_ref126","article-title":"\u201cUntersuchungen zu dynamischen neuronalen Netzen\u201d","volume-title":"Diploma other, Institut f\u00fcr Informatik, Lehrstuhl Prof. Brauer, Technische Universit\u00e4t M\u00fcnchen","author":"Hochreiter","year":"1991"},{"issue":"8","key":"2026040314515463800_ref127","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"\u201cLong short-term memory\u201d","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"issue":"1","key":"2026040314515463800_ref128","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/1500000051","article-title":"\u201cOnline Evaluation for Information Retrieval\u201d","volume":"10","author":"Hofmann","year":"2016","journal-title":"Foundations and Trends in Information Retrieval"},{"key":"2026040314515463800_ref129","first-page":"1638","article-title":"\u201cLearning to Write with Cooperative Discriminators\u201d","volume-title":"ACL","author":"Holtzman","year":"2018"},{"key":"2026040314515463800_ref130","article-title":"\u201cEnd-to-end Conversation Modeling Track in DSTC6\u201d","volume-title":"CoRR","author":"Hori","year":"2017"},{"key":"2026040314515463800_ref131","article-title":"\u201cContext Sensitive Spoken Language Understanding using Role Dependent LSTM Layers\u201d","volume-title":"Technical Other TR2015-134","author":"Hori","year":"2015"},{"key":"2026040314515463800_ref132","article-title":"\u201cThe Sixth Dialog State Tracking Challenge\u201d","author":"Hori","year":"2017"},{"key":"2026040314515463800_ref133","first-page":"159","article-title":"\u201cPrinciples of Mixed-Initiative User Interfaces\u201d","volume-title":"Proceedings of the Other on Human Factors in Computing Systems (CHI)","author":"Horvitz","year":"1999"},{"key":"2026040314515463800_ref134","first-page":"1109","article-title":"\u201cVIME: Variational Information Maximizing Exploration\u201d","volume-title":"Advances in Neural Information Processing Systems 29 (NIPS)","author":"Houthooft","year":"2016"},{"key":"2026040314515463800_ref135","article-title":"\u201cMnemonic reader for machine comprehension\u201d","volume-title":"arXiv preprint","author":"Hu","year":"2017"},{"key":"2026040314515463800_ref136","article-title":"\u201cFusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension\u201d","volume-title":"arXiv preprint","author":"Huang","year":"2017"},{"key":"2026040314515463800_ref137","article-title":"\u201cHierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation\u201d","volume-title":"CoRR","author":"Huang","year":"2018"},{"key":"2026040314515463800_ref138","first-page":"2333","article-title":"\u201cLearning deep structured semantic models for web search using clickthrough data\u201d","volume-title":"Proceedings of the 22nd ACM International Other on Information & Knowledge Management","author":"Huang","year":"2013"},{"key":"2026040314515463800_ref139","author":"Huang","year":"2001"},{"key":"2026040314515463800_ref140","first-page":"277:1","article-title":"\u201cEmotional Dialogue Generation using Image-Grounded Language Models\u201d","volume-title":"CHI","author":"Huber","year":"2018"},{"key":"2026040314515463800_ref141","first-page":"393","article-title":"\u201cNeural Utterance Ranking Model for Conversational Dialogue Systems\u201d","volume-title":"SIGDIAL","author":"Inaba","year":"2016"},{"key":"2026040314515463800_ref142","doi-asserted-by":"crossref","first-page":"1821","DOI":"10.18653\/v1\/P17-1167","article-title":"\u201cSearch-based neural structured learning for sequential question answering\u201d","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Iyyer","year":"2017"},{"key":"2026040314515463800_ref143","first-page":"2329","article-title":"\u201cFilter, rank, and transfer the knowledge: Learning to chat\u201d","author":"Jafarpour","year":"2010","journal-title":"Advances in Ranking"},{"key":"2026040314515463800_ref144","first-page":"1563","article-title":"\u201cNear-optimal Regret Bounds for Reinforcement Learning\u201d","volume":"11","author":"Jaksch","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"2026040314515463800_ref145","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D17-1215","article-title":"\u201cAdversarial examples for evaluating reading comprehension systems\u201d","volume-title":"arXiv preprint","author":"Jia","year":"2017"},{"key":"2026040314515463800_ref146","first-page":"1704","article-title":"\u201cContextual Decision Processes with Low Bellman Rank are PAC-Learnable\u201d","volume-title":"Proceedings of the 34th International Other on Machine Learning (ICML)","author":"Jiang","year":"2017"},{"key":"2026040314515463800_ref147","first-page":"652","article-title":"\u201cDoubly Robust Off-policy Evaluation for Reinforcement Learning\u201d","volume-title":"Proceedings of the 33rd International Other on Machine Learning (ICML)","author":"Jiang","year":"2016"},{"key":"2026040314515463800_ref148","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P17-1147","article-title":"\u201cTriviaQA: A large scale distantly supervised challenge dataset for reading comprehension\u201d","volume-title":"arXiv preprint","author":"Joshi","year":"2017"},{"key":"2026040314515463800_ref149","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1016\/j.csl.2009.03.002","article-title":"\u201cData-driven User Simulation for Automated Evaluation of Spoken Dialog Systems\u201d","volume":"23","author":"Jung","year":"2009","journal-title":"Computer Speech and Language"},{"key":"2026040314515463800_ref150","author":"Jurafsky","year":"2009"},{"key":"2026040314515463800_ref151","author":"Jurafsky","year":"2018"},{"key":"2026040314515463800_ref152","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"\u201cReinforcement Learning: A Survey\u201d","volume":"4","author":"Kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2026040314515463800_ref153","first-page":"1531","article-title":"\u201cA Natural Policy Gradient\u201d","volume-title":"Advances in Neural Information Processing Systems 13 (NIPS)","author":"Kakade","year":"2001"},{"key":"2026040314515463800_ref154","first-page":"1700","article-title":"\u201cRecurrent Continuous Translation Models\u201d","volume-title":"Proceedings of the 2013 Other on Empirical Methods in Natural Language Processing","author":"Kalchbrenner","year":"2013"},{"key":"2026040314515463800_ref155","article-title":"\u201cAdversarial Evaluation of Dialogue Models\u201d","volume-title":"NIPS Workshop on Adversarial Training","author":"Kannan","year":"2016"},{"key":"2026040314515463800_ref156","doi-asserted-by":"crossref","first-page":"284","DOI":"10.18653\/v1\/P18-1027","article-title":"\u201cSharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context\u201d","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Khandelwal","year":"2018"},{"key":"2026040314515463800_ref157","first-page":"435","article-title":"\u201cThe Fourth Dialog State Tracking Challenge\u201d","volume-title":"Proceedings of the 7th International Workshop on Spoken Dialogue Systems (IWSDS)","author":"Kim","year":"2016"},{"key":"2026040314515463800_ref158","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1109\/SLT.2016.7846311","article-title":"\u201cThe Fifth Dialog State Tracking Challenge\u201d","volume-title":"Proceedings of the 2016 IEEE Spoken Language Technology Workshop (SLT-16)","author":"Kim","year":"2016"},{"key":"2026040314515463800_ref159","article-title":"\u201cThe NarrativeQA Reading Comprehension Challenge\u201d","volume-title":"arXiv preprint","author":"Ko\u010disky","year":"2017"},{"key":"2026040314515463800_ref160","first-page":"388","article-title":"\u201cStatistical Significance Tests for Machine Translation Evaluation\u201d","volume-title":"Proceedings of EMNLP 2004","author":"Koehn","year":"2004"},{"key":"2026040314515463800_ref161","first-page":"48","article-title":"\u201cStatistical Phrase-based Translation\u201d","volume-title":"Proceedings of the 2003 Other of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1. NAACL \u201903","author":"Koehn","year":"2003"},{"key":"2026040314515463800_ref162","first-page":"336","article-title":"\u201cSentence Generation as a Planning Problem\u201d","volume-title":"Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL-07)","author":"Koller","year":"2007"},{"key":"2026040314515463800_ref163","first-page":"9","article-title":"\u201cMulti-Domain Spoken Dialogue System with Extensibility and Robustness against Speech Recognition Errors\u201d","volume-title":"Proceedings of the SIGDIAL 2006 Workshop","author":"Komatani","year":"2006"},{"key":"2026040314515463800_ref164","first-page":"1008","article-title":"\u201cActor-Critic Algorithms\u201d","volume-title":"Advances in Neural Information Processing Systems 12 (NIPS)","author":"Konda","year":"1999"},{"key":"2026040314515463800_ref165","first-page":"1406","article-title":"\u201cA Statistical NLG Framework for Aggregated Planning and Realization\u201d","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Kondadadi","year":"2013"},{"key":"2026040314515463800_ref166","first-page":"986","article-title":"\u201cA Case Study on the Importance of Belief State Representation for Dialogue Policy Management\u201d","volume-title":"Proceedings of the 19th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Kotti","year":"2018"},{"key":"2026040314515463800_ref167","article-title":"\u201cA Learning Approach to Improving Sentence-Level MT Evaluation\u201d","volume-title":"Proceedings of the 10th International Other on Theoretical and Methodological Issues in Machine Translation","author":"Kulesza","year":"2004"},{"key":"2026040314515463800_ref168","first-page":"1378","article-title":"\u201cAsk me anything: Dynamic memory networks for natural language processing\u201d","volume-title":"International Other on Machine Learning","author":"Kumar","year":"2016"},{"key":"2026040314515463800_ref169","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D17-1082","article-title":"\u201cRACE: Large-scale reading comprehension dataset from examinations\u201d","volume-title":"arXiv other arXiv:1704.04683","author":"Lai","year":"2017"},{"key":"2026040314515463800_ref170","first-page":"704","article-title":"\u201cGeneration that Exploits Corpus-Based Statistical Knowledge\u201d","volume-title":"Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Other on Computational Linguistics (COLING-ACL)","author":"Langkilde","year":"1998"},{"issue":"1","key":"2026040314515463800_ref171","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s10994-010-5205-8","article-title":"\u201cRelational retrieval using a combination of path-constrained random walks\u201d","volume":"81","author":"Lao","year":"2010","journal-title":"Machine Learning"},{"key":"2026040314515463800_ref172","first-page":"529","article-title":"\u201cRandom walk inference and learning in a large scale knowledge base\u201d","volume-title":"Proceedings of the Other on Empirical Methods in Natural Language Processing","author":"Lao","year":"2011"},{"issue":"3\u20134","key":"2026040314515463800_ref173","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1017\/S1351324900002539","article-title":"\u201cInformation State and Dialogue Management in the TRINDI Dialogue Move Engine Toolkit\u201d","volume":"6","author":"Larsson","year":"2000","journal-title":"Natural Language Engineering"},{"key":"2026040314515463800_ref174","first-page":"515","article-title":"\u201cSequential Short-Text Classification with Recurrent and Convolutional Neural Networks\u201d","volume-title":"Proceedings of the 2016 Other of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Lee","year":"2016"},{"key":"2026040314515463800_ref175","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v33i01.33016642","article-title":"\u201cZero-Shot Adaptive Transfer for Conversational Language Understanding\u201d","volume-title":"Proceedings of the Thirty-Third AAAI Other on Artificial Intelligence (AAAI-19)","author":"Lee","year":"2019"},{"key":"2026040314515463800_ref176","first-page":"1437","article-title":"\u201cSequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures\u201d","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Lei","year":"2018"},{"issue":"2","key":"2026040314515463800_ref177","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.csl.2010.04.005","article-title":"\u201cLearning What to Say and How to Say It: Joint Optimisation of Spoken Dialogue Management and Natural Language Generation\u201d","volume":"25","author":"Lemon","year":"2011","journal-title":"Computer Speech & Language"},{"issue":"1","key":"2026040314515463800_ref178","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/89.817450","article-title":"\u201cA Stochastic Model of Human-Machine Interaction for Learning Dialog Strategies\u201d","volume":"8","author":"Levin","year":"2000","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"2026040314515463800_ref179","first-page":"2443","article-title":"\u201cDeal or No Deal? End-to-End Learning of Negotiation Dialogues\u201d","volume-title":"Proceedings of the 2017 Other on Empirical Methods in Natural Language Processing (EMNLP-17)","author":"Lewis","year":"2017"},{"key":"2026040314515463800_ref180","first-page":"110","article-title":"\u201cA diversity-promoting objective function for neural conversation models\u201d","volume-title":"NAACL-HLT","author":"Li","year":"2016"},{"key":"2026040314515463800_ref181","first-page":"994","article-title":"\u201cA Persona-Based Neural Conversation Model\u201d","volume-title":"ACL","author":"Li","year":"2016"},{"key":"2026040314515463800_ref182","article-title":"\u201cDialogue learning with human-in-the-loop\u201d","volume-title":"ICLR","author":"Li","year":"2017"},{"key":"2026040314515463800_ref183","article-title":"\u201cLearning Through Dialogue Interactions by Asking Questions\u201d","volume-title":"ICLR","author":"Li","year":"2017"},{"key":"2026040314515463800_ref184","first-page":"1192","article-title":"\u201cDeep Reinforcement Learning for Dialogue Generation\u201d","volume-title":"EMNLP","author":"Li","year":"2016"},{"key":"2026040314515463800_ref185","first-page":"2157","article-title":"\u201cAdversarial Learning for Neural Dialogue Generation\u201d","volume-title":"Proceedings of the 2017 Other on Empirical Methods in Natural Language Processing","author":"Li","year":"2017"},{"key":"2026040314515463800_ref186","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1109\/SLT.2014.7078593","article-title":"\u201cTemporal Supervised Learning for Inferring a Dialog Policy from Example Conversations\u201d","volume-title":"Proceedings of the 2014 IEEE Spoken Language Technology Workshop (SLT)","author":"Li","year":"2014"},{"key":"2026040314515463800_ref187","first-page":"2475","article-title":"\u201cReinforcement Learning for Spoken Dialog Management using Least-Squares Policy Iteration and Fast Feature Selection\u201d","volume-title":"Proceedings of the 10th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Li","year":"2009"},{"key":"2026040314515463800_ref188","first-page":"733","article-title":"\u201cEnd-to-End Task-Completion Neural Dialogue Systems\u201d","volume-title":"Proceedings of the 8th International Joint Other on Natural Language Processing (IJCNLP)","author":"Li","year":"2017"},{"key":"2026040314515463800_ref189","article-title":"\u201cInvestigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems\u201d","volume-title":"CoRR","author":"Li","year":"2017"},{"key":"2026040314515463800_ref190","article-title":"\u201cRecurrent Reinforcement Learning: A Hybrid Approach\u201d","volume-title":"arXiv","author":"Li","year":"2015"},{"key":"2026040314515463800_ref191","article-title":"\u201cA User Simulator for Task-Completion Dialogues\u201d","volume-title":"CoRR","author":"Li","year":"2016"},{"key":"2026040314515463800_ref192","article-title":"\u201cMicrosoft Dialogue Challenge: Building End-to-End Task-Completion Dialogue Systems\u201d","volume-title":"arXiv other","author":"Li","year":"2018"},{"key":"2026040314515463800_ref193","article-title":"\u201cDeep Reinforcement Learning\u201d","volume-title":"arXiv","author":"Li","year":"2018"},{"key":"2026040314515463800_ref194","article-title":"\u201cNeural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision\u201d","volume-title":"arXiv other","author":"Liang","year":"2016"},{"key":"2026040314515463800_ref195","first-page":"74","article-title":"\u201cROUGE: A package for automatic evaluation of summaries\u201d","volume-title":"ACL Workshop","author":"Lin","year":"2004"},{"issue":"3\u20134","key":"2026040314515463800_ref196","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1023\/A:1022628806385","article-title":"\u201cSelf-Improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching\u201d","volume":"8","author":"Lin","year":"1992","journal-title":"Machine Learning"},{"key":"2026040314515463800_ref197","first-page":"5237","article-title":"\u201cBBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems\u201d","volume-title":"AAAI","author":"Lipton","year":"2018"},{"key":"2026040314515463800_ref198","first-page":"740","article-title":"\u201cBLANC: Learning Evaluation Metrics for MT\u201d","volume-title":"Proceedings of the Other on Human Language Technology and Empirical Methods in Natural Language Processing, HLT \u201905","author":"Lita","year":"2005"},{"issue":"163\u2013200","key":"2026040314515463800_ref199","article-title":"\u201cA Plan Recognition Model for Subdialogues in Conversations\u201d","volume":"11","author":"Litman","year":"1987","journal-title":"Cognitive Science"},{"key":"2026040314515463800_ref200","first-page":"685","article-title":"\u201cAttention-based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling\u201d","volume-title":"Proceedings of the 17th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Liu","year":"2016"},{"key":"2026040314515463800_ref201","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1109\/ASRU.2017.8268975","article-title":"\u201cIterative Policy Learning in End-to-end Trainable Task-oriented Neural Dialog Models\u201d","volume-title":"Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","author":"Liu","year":"2017"},{"key":"2026040314515463800_ref202","doi-asserted-by":"crossref","first-page":"350","DOI":"10.18653\/v1\/W18-5041","article-title":"\u201cAdversarial Learning of Task-Oriented Neural Dialog Models\u201d","volume-title":"Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL)","author":"Liu","year":"2018"},{"key":"2026040314515463800_ref203","first-page":"2060","article-title":"\u201cDialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems\u201d","volume-title":"Proceedings of the 2018 Other of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Liu","year":"2018"},{"key":"2026040314515463800_ref204","first-page":"2122","article-title":"\u201cHow NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation\u201d","volume-title":"EMNLP","author":"Liu","year":"2016"},{"key":"2026040314515463800_ref205","article-title":"\u201cAction-dependent Control Variates for Policy Optimization via Stein\u2019s Identity\u201d","volume-title":"Proceedings of the 6th International Other on Learning Representations (ICLR)","author":"Liu","year":"2018"},{"key":"2026040314515463800_ref206","first-page":"5361","article-title":"\u201cBreaking the Curse of Horizon: Infinite-horizon Off-policy Estimation\u201d","volume-title":"Advances in Neural Information Processing Systems 31 (NIPS-18)","author":"Liu","year":"2018"},{"key":"2026040314515463800_ref207","article-title":"\u201cPhase Conductor on Multi-layered Attentions for Machine Comprehension\u201d","volume-title":"arXiv other","author":"Liu","year":"2017"},{"key":"2026040314515463800_ref208","first-page":"1694","article-title":"\u201cStochastic answer networks for machine reading comprehension\u201d","volume-title":"ACL","author":"Liu","year":"2018"},{"key":"2026040314515463800_ref209","first-page":"1116","article-title":"\u201cTowards an Automatic Turing Test: Learning to Evaluate Dialogue Responses\u201d","volume-title":"ACL","author":"Lowe","year":"2017"},{"key":"2026040314515463800_ref210","first-page":"285","article-title":"\u201cThe Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems\u201d","volume-title":"SIGDIAL","author":"Lowe","year":"2015"},{"key":"2026040314515463800_ref211","first-page":"1368","article-title":"\u201cA Deep Architecture for Matching Short Texts\u201d","volume-title":"Advances in Neural Information Processing Systems 27","author":"Lu","year":"2014"},{"key":"2026040314515463800_ref212","first-page":"605","article-title":"\u201cMulti-Task Learning for Speaker-Role Adaptation in Neural Conversation Models\u201d","volume-title":"IJCNLP","author":"Luan","year":"2017"},{"key":"2026040314515463800_ref213","first-page":"1412","article-title":"\u201cEffective Approaches to Attention-based Neural Machine Translation\u201d","volume-title":"Proceedings of the 2015 Other on Empirical Methods in Natural Language Processing","author":"Luong","year":"2015"},{"key":"2026040314515463800_ref214","first-page":"1468","article-title":"\u201cMem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems\u201d","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Madotto","year":"2018"},{"issue":"4","key":"2026040314515463800_ref215","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1162\/COLI_a_00199","article-title":"\u201cStochastic Language Generation in Dialogue using Factored Language Models\u201d","volume":"40","author":"Mairesse","year":"2014","journal-title":"Computational Linguistics"},{"key":"2026040314515463800_ref216","doi-asserted-by":"crossref","first-page":"55","DOI":"10.3115\/v1\/P14-5010","article-title":"\u201cThe Stanford CoreNLP Natural Language Processing Toolkit\u201d","volume-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Manning","year":"2014"},{"key":"2026040314515463800_ref217","article-title":"\u201cDeep Captioning with Multimodal Recurrent Neural Networks (m-RNN)\u201d","volume-title":"ICLR","author":"Mao","year":"2015"},{"key":"2026040314515463800_ref218","first-page":"6297","article-title":"\u201cLearned in Translation: Contextualized Word Vectors\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"McCann","year":"2017"},{"key":"2026040314515463800_ref219","article-title":"\u201cThe Natural Language Decathlon: Multitask Learning as Question Answering\u201d","volume-title":"arXiv other arXiv:1806.08730","author":"McCann","year":"2018"},{"issue":"1","key":"2026040314515463800_ref220","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1145\/505282.505285","article-title":"\u201cSpoken Dialogue Technology: Enabling the Conversational User Interface\u201d","volume":"34","author":"McTear","year":"2002","journal-title":"ACM Computing Surveys"},{"key":"2026040314515463800_ref221","first-page":"3252","article-title":"\u201cCoherent Dialogue with Attention-based Language Models\u201d","volume-title":"AAAI","author":"Mei","year":"2017"},{"key":"2026040314515463800_ref222","first-page":"51","article-title":"\u201ccontext2vec: Learning generic context embedding with bidirectional lstm\u201d","volume-title":"Proceedings of The 20th SIGNLL Other on Computational Natural Language Learning","author":"Melamud","year":"2016"},{"issue":"3","key":"2026040314515463800_ref223","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1109\/TASLP.2014.2383614","article-title":"\u201cUsing Recurrent Neural Networks for Slot Filling in Spoken Language Understanding\u201d","volume":"23","author":"Mesnil","year":"2015","journal-title":"IEEE\/ACM Transactions on Audio, Speech & Language Processing"},{"key":"2026040314515463800_ref224","first-page":"3771","article-title":"\u201cInvestigation of Recurrent-Neural-network Architectures and Learning Methods for Spoken Language Understanding\u201d","volume-title":"Proceedings of the 14th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Mesnil","year":"2013"},{"key":"2026040314515463800_ref225","first-page":"3111","article-title":"\u201cDistributed representations of words and phrases and their compositionality\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Mikolov","year":"2013"},{"key":"2026040314515463800_ref226","volume-title":"MIT Press","author":"Minsky","year":"1969"},{"key":"2026040314515463800_ref227","volume-title":"McGraw-Hill","author":"Mitchell","year":"1997"},{"key":"2026040314515463800_ref228","first-page":"1928","article-title":"\u201cAsynchronous Methods for Deep Reinforcement Learning\u201d","volume-title":"Proceedings of the 33rd International Other on Machine Learning (ICML)","author":"Mnih","year":"2016"},{"key":"2026040314515463800_ref229","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"\u201cHuman-level Control through Deep Reinforcement Learning\u201d","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"2026040314515463800_ref230","first-page":"4024","article-title":"\u201cThe Winograd Schema Challenge: Evaluating Progress in Commonsense Reasoning\u201d","volume-title":"Proceedings of the Twenty-Ninth AAAI Other on Artificial Intelligence. AAAI\u201915","author":"Morgenstern","year":"2015"},{"key":"2026040314515463800_ref231","first-page":"462","article-title":"\u201cImage-Grounded Conversations: Multimodal Context for Natural Question and Response Generation\u201d","volume-title":"IJCNNLP","author":"Mostafazadeh","year":"2017"},{"key":"2026040314515463800_ref232","article-title":"\u201cCoupling distributed and symbolic execution for natural language queries\u201d","volume-title":"arXiv other arXiv:1612.02741","author":"Mou","year":"2016"},{"key":"2026040314515463800_ref233","first-page":"794","article-title":"\u201cMulti-domain Dialog State Tracking using Recurrent Neural Networks\u201d","volume-title":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Other on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL)","author":"Mrk\u0161i\u0107","year":"2015"},{"key":"2026040314515463800_ref234","first-page":"1777","article-title":"\u201cNeural Belief Tracker: Data-Driven Dialogue State Tracking\u201d","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Mrk\u0161i\u0107","year":"2017"},{"key":"2026040314515463800_ref235","first-page":"815","article-title":"\u201cFinite-Time Bounds for Sampling-Based Fitted Value Iteration\u201d","volume":"9","author":"Munos","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"2026040314515463800_ref236","first-page":"1","article-title":"\u201cLanguage Understanding for Text-based Games using Deep Reinforcement Learning\u201d","volume-title":"Proceedings of the 2015 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Narasimhan","year":"2015"},{"key":"2026040314515463800_ref237","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/P15-1016","article-title":"\u201cCompositional vector space models for knowledge base completion\u201d","volume-title":"arXiv other arXiv:1504.06662","author":"Neelakantan","year":"2015"},{"key":"2026040314515463800_ref238","article-title":"\u201cAn overview of embedding models of entities and relationships for knowledge base completion\u201d","volume-title":"arXiv other arXiv:1703.08098","author":"Nguyen","year":"2017"},{"key":"2026040314515463800_ref239","article-title":"\u201cMS MARCO: A human generated machine reading comprehension dataset\u201d","volume-title":"arXiv other arXiv:1611.09268","author":"Nguyen","year":"2016"},{"key":"2026040314515463800_ref240","first-page":"160","article-title":"\u201cMinimum Error Rate Training in Statistical Machine Translation\u201d","volume-title":"Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics","author":"Och","year":"2003"},{"key":"2026040314515463800_ref241","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1162\/089120103321337421","article-title":"\u201cA Systematic Comparison of Various Statistical Alignment Models\u201d","volume":"29","author":"Och","year":"2003","journal-title":"Computational Linguistics"},{"key":"2026040314515463800_ref242","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1162\/0891201042544884","article-title":"\u201cThe Alignment Template Approach to Statistical Machine Translation\u201d","volume":"30","author":"Och","year":"2004","journal-title":"Comput. Linguist."},{"key":"2026040314515463800_ref244","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1016\/S0885-2308(02)00012-8","article-title":"\u201cStochastic Natural Language Generation for Spoken Dialog Systems\u201d","volume":"16","author":"Oh","year":"2002","journal-title":"Computer Speech & Language"},{"key":"2026040314515463800_ref245","first-page":"4026","article-title":"\u201cDeep Exploration via Bootstrapped DQN\u201d","volume-title":"Advances in Neural Information Processing Systems 29 (NIPS-16)","author":"Osband","year":"2016"},{"key":"2026040314515463800_ref246","first-page":"2701","article-title":"\u201cWhy is Posterior Sampling Better than Optimism for Reinforcement Learning?\u201d","volume-title":"Proceedings of the 34th International Other on Machine Learning (ICML)","author":"Osband","year":"2017"},{"key":"2026040314515463800_ref247","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s10590-009-9060-y","article-title":"\u201cMeasuring Machine Translation Quality as Semantic Equivalence: A Metric Based on Entailment Features\u201d","author":"Pado","year":"2009","journal-title":"Machine Translation"},{"key":"2026040314515463800_ref248","first-page":"1","article-title":"\u201cEmpirical Methods for Evaluating Dialog Systems\u201d","volume-title":"Proceedings of the 2nd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Paek","year":"2001"},{"key":"2026040314515463800_ref249","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1016\/j.specom.2008.03.010","article-title":"\u201cAutomating Spoken Dialogue Management Design using Machine Learning: An Industry Perspective\u201d","volume":"50","author":"Paek","year":"2008","journal-title":"Speech Communication"},{"key":"2026040314515463800_ref250","first-page":"6064","article-title":"\u201cTowards Scalable Information-Seeking Multi-Domain Dialogue\u201d","volume-title":"Proceedings of the 2018 IEEE International Other on Acoustics, Speech and Signal Processing (ICASSP)","author":"Papangelis","year":"2018"},{"key":"2026040314515463800_ref251","doi-asserted-by":"crossref","first-page":"229","DOI":"10.18653\/v1\/W18-5025","article-title":"\u201cSpoken Dialogue for Information Navigation\u201d","volume-title":"Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL)","author":"Papangelis","year":"2018"},{"key":"2026040314515463800_ref252","first-page":"311","article-title":"\u201cBLEU: a method for automatic evaluation of machine translation\u201d","volume-title":"ACL","author":"Papineni","year":"2002"},{"key":"2026040314515463800_ref253","first-page":"1043","article-title":"\u201cReinforcement Learning with Hierarchies of Machines\u201d","volume-title":"Advances in Neural Information Processing Systems 10 (NIPS)","author":"Parr","year":"1998"},{"key":"2026040314515463800_ref254","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/P15-1142","article-title":"\u201cCompositional semantic parsing on semi-structured tables\u201d","volume-title":"arXiv other arXiv:1508.00305","author":"Pasupat","year":"2015"},{"key":"2026040314515463800_ref255","article-title":"\u201cIntegrating planning for task-completion dialogue policy learning\u201d","volume-title":"CoRR abs\/1801.06176","author":"Peng","year":"2018"},{"key":"2026040314515463800_ref256","first-page":"2231","article-title":"\u201cComposite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning\u201d","volume-title":"EMNLP","author":"Peng","year":"2017"},{"key":"2026040314515463800_ref257","first-page":"1532","article-title":"\u201cGloVe: Global vectors for word representation\u201d","volume-title":"Proceedings of the 2014 other on empirical methods in natural language processing (EMNLP)","author":"Pennington","year":"2014"},{"key":"2026040314515463800_ref258","first-page":"280","article-title":"\u201cNatural Actor-Critic\u201d","volume-title":"Proceedings of the 16th European Other on Machine Learning (ECML)","author":"Peters","year":"2005"},{"key":"2026040314515463800_ref259","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/N18-1202","article-title":"\u201cDeep contextualized word representations\u201d","volume-title":"arXiv other arXiv:1802.05365","author":"Peters","year":"2018"},{"key":"2026040314515463800_ref260","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1109\/TSA.2005.855836","article-title":"\u201cA Probabilistic Framework for Dialog Simulation and Optimal Strategy Learning\u201d","volume":"14","author":"Pietquin","year":"2006","journal-title":"IEEE Transactions on Audio, Speech & Language Processing"},{"key":"2026040314515463800_ref261","doi-asserted-by":"crossref","first-page":"7:1","DOI":"10.1145\/1966407.1966412","article-title":"\u201cSample-efficient Batch Reinforcement Learning for Dialogue Management Optimization\u201d","volume":"7","author":"Pietquin","year":"2011","journal-title":"ACM Transactions on Speech and Language Processing"},{"key":"2026040314515463800_ref262","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1017\/S0269888912000343","article-title":"\u201cA Survey on Metrics for the Evaluation of User Simulations\u201d","volume":"28","author":"Pietquin","year":"2013","journal-title":"The Knowledge Engineering Review"},{"key":"2026040314515463800_ref263","first-page":"759","article-title":"\u201cEligibility Traces for Off-Policy Policy Evaluation\u201d","volume-title":"Proceedings of the 17th International Other on Machine Learning (ICML)","author":"Precup","year":"2000"},{"key":"2026040314515463800_ref264","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/s10590-009-9065-6","article-title":"\u201cThe NIST 2008 Metrics for Machine Translation Challenge\u2014Overview, Methodology, Metrics, and Results\u201d","volume":"23","author":"Przybocki","year":"2009","journal-title":"Machine Translation"},{"key":"2026040314515463800_ref265","volume-title":"Wiley-Interscience","author":"Puterman","year":"1994"},{"key":"2026040314515463800_ref266","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P18-2124","article-title":"\u201cKnow What You Don\u2019t Know: Unanswerable Questions for SQuAD\u201d","volume-title":"arXiv other arXiv:1806.03822","author":"Rajpurkar","year":"2018"},{"key":"2026040314515463800_ref267","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D16-1264","article-title":"\u201cSQuAD: 100,000+ Questions for Machine Comprehension of Text\u201d","volume-title":"arXiv other arXiv:1606.05250","author":"Rajpurkar","year":"2016"},{"key":"2026040314515463800_ref268","article-title":"\u201cConversational AI: The Science Behind the Alexa Prize\u201d","volume-title":"CoRR abs\/1801.03604","author":"Ram","year":"2018"},{"key":"2026040314515463800_ref269","first-page":"82","article-title":"\u201cText Chunking using Transformation-based Learning\u201d","volume-title":"Third Workshop on Very Large Corpora (VLC at ACL)","author":"Ramshaw","year":"1995"},{"key":"2026040314515463800_ref270","article-title":"\u201cSequence Level Training with Recurrent Neural Networks\u201d","volume-title":"arXiv 1511.06732","author":"Ranzato","year":"2015"},{"key":"2026040314515463800_ref271","first-page":"135","article-title":"\u201cRecurrent Neural Network and LSTM Models for Lexical Utterance Classification\u201d","volume-title":"Proceedings of the 16th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Ravuri","year":"2015"},{"key":"2026040314515463800_ref272","first-page":"6075","article-title":"\u201cA Comparative Study of Recurrent Neural Network Models for Lexical Domain Classification\u201d","volume-title":"Proceedings of the 2016 IEEE International Other on Acoustics, Speech and Signal Processing (ICASSP)","author":"Ravuri","year":"2016"},{"key":"2026040314515463800_ref273","article-title":"\u201cCoQA: A Conversational Question Answering Challenge\u201d","volume-title":"arXiv other arXiv:1808.07042","author":"Reddy","year":"2018"},{"key":"2026040314515463800_ref274","first-page":"1715","article-title":"\u201cConversational Query Understanding Using Sequence to Sequence Modeling\u201d","volume-title":"Proceedings of the 2018 World Wide Web Other on World Wide Web","author":"Ren","year":"2018"},{"key":"2026040314515463800_ref275","first-page":"2780","article-title":"\u201cTowards Universal Dialogue State Tracking\u201d","volume-title":"Proceedings of the 2018 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Ren","year":"2018"},{"key":"2026040314515463800_ref276","first-page":"15","article-title":"\u201cCOLLAGEN: Applying Collaborative Discourse Theory to Human-Computer Interaction\u201d","volume":"22","author":"Rich","year":"2001","journal-title":"AI Magazine"},{"key":"2026040314515463800_ref277","first-page":"193","article-title":"\u201cMCTest: A challenge dataset for the open-domain machine comprehension of text\u201d","volume-title":"Proceedings of the 2013 Other on Empirical Methods in Natural Language Processing","author":"Richardson","year":"2013"},{"key":"2026040314515463800_ref278","first-page":"1098","article-title":"\u201cMindNet: acquiring and structuring semantic information from text\u201d","volume-title":"Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Other on Computational Linguistics-Volume 2","author":"Richardson","year":"1998"},{"key":"2026040314515463800_ref279","first-page":"638","article-title":"\u201cLearning Effective Multimodal Dialogue Strategies from Wizard-of-Oz Data: Bootstrapping and Evaluation\u201d","volume-title":"Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Rieser","year":"2008"},{"key":"2026040314515463800_ref280","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/978-3-642-15573-4_6","volume-title":"Empirical Methods in Natural Language Generation: Data-oriented Methods and Empirical Evaluation","author":"Rieser","year":"2010"},{"key":"2026040314515463800_ref281","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1162\/coli_a_00038","article-title":"\u201cLearning and Evaluation of Dialogue Strategies for New Applications: Empirical Methods for Optimization from Small Data Sets\u201d","volume":"37","author":"Rieser","year":"2011","journal-title":"Computational Linguistics"},{"key":"2026040314515463800_ref282","first-page":"1009","article-title":"\u201cOptimising Information Presentation for Spoken Dialogue Systems\u201d","volume-title":"Proceedings of the Forty-Eighth Annual Meeting of the Association for Computational Linguistics (ACL-10)","author":"Rieser","year":"2010"},{"key":"2026040314515463800_ref283","first-page":"583","article-title":"\u201cData-driven response generation in social media\u201d","volume-title":"EMNLP","author":"Ritter","year":"2011"},{"key":"2026040314515463800_ref284","article-title":"\u201cChoice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning\u201d","volume-title":"AAAI Spring Symposium - Technical Other","author":"Roemmele","year":"2011"},{"key":"2026040314515463800_ref285","article-title":"\u201cThe perceptron: A perceiving and recognizing automaton\u201d","volume-title":"Other No. 85-460-1","author":"Rosenblatt","year":"1957"},{"key":"2026040314515463800_ref286","author":"Rosenblatt","year":"1962"},{"key":"2026040314515463800_ref287","first-page":"627","article-title":"\u201cA Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning\u201d","volume-title":"Proceedings of the 14th International Other on Artificial Intelligence and Statistics (AISTATS)","author":"Ross","year":"2011"},{"key":"2026040314515463800_ref288","first-page":"93","article-title":"\u201cSpoken Dialogue Management using Probabilistic Reasoning\u201d","volume-title":"Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Roy","year":"2000"},{"key":"2026040314515463800_ref289","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000070","article-title":"\u201cA Tutorial on Thompson Sampling\u201d","volume":"11","author":"Russo","year":"2018","journal-title":"Foundations and Trends in Machine Learning"},{"key":"2026040314515463800_ref290","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11332","article-title":"\u201cComplex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph\u201d","volume-title":"arXiv other","author":"Saha","year":"2018"},{"key":"2026040314515463800_ref291","article-title":"\u201cImproved Techniques for Training GANs\u201d","volume-title":"CoRR","author":"Salimans","year":"2016"},{"key":"2026040314515463800_ref292","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1109\/TASLP.2014.2303296","article-title":"\u201cApplication of Deep Belief Networks for Natural Language Understanding\u201d","volume":"22","author":"Sarikaya","year":"2014","journal-title":"IEEE\/ACM Transactions on Audio, Speech & Language Processing"},{"key":"2026040314515463800_ref293","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1023\/A:1007649029923","article-title":"\u201cBoosTexter: A Boosting-based System for Text Categorization\u201d","volume":"39","author":"Schapire","year":"2000","journal-title":"Machine Learning"},{"key":"2026040314515463800_ref294","doi-asserted-by":"crossref","first-page":"45","DOI":"10.18653\/v1\/2005.sigdial-1.6","article-title":"\u201cQuantitative Evaluation of User Simulation Techniques for Spoken Dialogue Systems\u201d","volume-title":"Proceedings of the 6th SIGdial Workshop on Discourse and Dialogue","author":"Schatzmann","year":"2005"},{"key":"2026040314515463800_ref295","first-page":"220","article-title":"\u201cEffects of the User Model on Simulation-based Learning of Dialogue Strategies\u201d","volume-title":"Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","author":"Schatzmann","year":"2005"},{"key":"2026040314515463800_ref296","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1017\/S0269888906000944","article-title":"\u201cA Survey of Statistical User Simulation Techniques for Reinforcement-Learning of Dialogue Management Strategies\u201d","volume":"21","author":"Schatzmann","year":"2006","journal-title":"The Knowledge Engineering Review"},{"key":"2026040314515463800_ref297","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1109\/TASL.2008.2012071","article-title":"\u201cThe Hidden Agenda User Simulation Model\u201d","volume":"17","author":"Schatzmann","year":"2009","journal-title":"IEEE Transactions on Audio, Speech, & Language Processing"},{"key":"2026040314515463800_ref298","first-page":"1889","article-title":"\u201cTrust Region Policy Optimization\u201d","volume-title":"Proceedings of the Thirty-Second International Other on Machine Learning (ICML)","author":"Schulman","year":"2015"},{"key":"2026040314515463800_ref299","article-title":"\u201cHigh-Dimensional Continuous Control Using Generalized Advantage Estimation\u201d","volume-title":"arXiv other","author":"Schulman","year":"2015"},{"key":"2026040314515463800_ref300","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P17-1099","article-title":"\u201cGet to the point: Summarization with pointer-generator networks\u201d","volume-title":"arXiv other","author":"See","year":"2017"},{"key":"2026040314515463800_ref301","article-title":"\u201cBidirectional attention flow for machine comprehension\u201d","volume-title":"arXiv other","author":"Seo","year":"2016"},{"key":"2026040314515463800_ref302","article-title":"\u201cA Survey of Available Corpora for Building Data-Driven Dialogue Systems\u201d","volume-title":"arXiv other","author":"Serban","year":"2015"},{"key":"2026040314515463800_ref303","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5087\/dad.2018.101","article-title":"\u201cA Survey of Available Corpora for Building Data-Driven Dialogue Systems: The Journal Version\u201d","volume":"9","author":"Serban","year":"2018","journal-title":"Dialogue & Discourse"},{"key":"2026040314515463800_ref304","first-page":"3776","article-title":"\u201cBuilding End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models\u201d","volume-title":"AAAI","author":"Serban","year":"2016"},{"key":"2026040314515463800_ref305","first-page":"3295","article-title":"\u201cA hierarchical latent variable encoder\u2013decoder model for generating dialogues\u201d","volume-title":"AAAI","author":"Serban","year":"2017"},{"key":"2026040314515463800_ref306","first-page":"41","article-title":"\u201cBootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning\u201d","volume-title":"Proceedings of the 2018 Other of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Shah","year":"2018"},{"key":"2026040314515463800_ref307","first-page":"1577","article-title":"\u201cNeural Responding Machine for Short-Text Conversation\u201d","volume-title":"ACL-IJCNLP","author":"Shang","year":"2015"},{"key":"2026040314515463800_ref308","article-title":"\u201cDRCD: a Chinese Machine Reading Comprehension Dataset\u201d","volume-title":"arXiv other","author":"Shao","year":"2018"},{"key":"2026040314515463800_ref309","first-page":"2210","article-title":"\u201cGenerating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models\u201d","volume-title":"EMNLP","author":"Shao","year":"2017"},{"key":"2026040314515463800_ref310","article-title":"\u201cM-Walk: Learning to Walk in Graph with Monte Carlo Tree Search\u201d","volume-title":"CoRR","author":"Shen","year":"2018"},{"key":"2026040314515463800_ref311","first-page":"101","article-title":"\u201cA latent semantic model with convolutional-pooling structure for information retrieval\u201d","volume-title":"Proceedings of the 23rd ACM International Other on Other on Information and Knowledge Management","author":"Shen","year":"2014"},{"key":"2026040314515463800_ref312","article-title":"\u201cImplicit ReasoNet: Modeling Large-Scale Structured Relationships with Shared Memory\u201d","volume-title":"CoRR","author":"Shen","year":"2016"},{"key":"2026040314515463800_ref313","article-title":"\u201cTraversing Knowledge Graph in Vector Space without Symbolic Space Guidance\u201d","volume-title":"arXiv other","author":"Shen","year":"2017"},{"key":"2026040314515463800_ref314","first-page":"1047","article-title":"\u201cReasoNet: Learning to stop reading in machine comprehension\u201d","volume-title":"Proceedings of the 23rd ACM SIGKDD International Other on Knowledge Discovery and Data Mining","author":"Shen","year":"2017"},{"key":"2026040314515463800_ref315","article-title":"\u201cAn Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks\u201d","volume-title":"arXiv other","author":"Shen","year":"2017"},{"key":"2026040314515463800_ref316","doi-asserted-by":"crossref","DOI":"10.1631\/FITEE.1700826","article-title":"\u201cFrom Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots\u201d","volume-title":"CoRR","author":"Shum","year":"2018"},{"key":"2026040314515463800_ref317","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1613\/jair.859","article-title":"\u201cOptimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System\u201d","volume":"16","author":"Singh","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2026040314515463800_ref318","first-page":"926","article-title":"\u201cReasoning with neural tensor networks for knowledge base completion\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Socher","year":"2013"},{"key":"2026040314515463800_ref319","article-title":"\u201cIterative alternating neural attention for machine reading\u201d","volume-title":"arXiv other","author":"Sordoni","year":"2016"},{"key":"2026040314515463800_ref320","first-page":"553","article-title":"\u201cA Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion\u201d","volume-title":"Proceedings of the 24th ACM International Other on Information and Knowledge Management (CIKM \u201915)","author":"Sordoni","year":"2015"},{"key":"2026040314515463800_ref321","first-page":"196","article-title":"\u201cA neural network approach to context-sensitive generation of conversational responses\u201d","volume-title":"NAACL-HLT","author":"Sordoni","year":"2015"},{"key":"2026040314515463800_ref322","first-page":"202","article-title":"\u201cFitting Sentence Level Translation Evaluation with Many Dense Features\u201d","volume-title":"Proceedings of the 2014 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Stanojevi\u0107","year":"2014"},{"key":"2026040314515463800_ref323","first-page":"79","article-title":"\u201cTrainable Sentence Planning for Complex Information Presentations in Spoken Dialog Systems\u201d","volume-title":"Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Stent","year":"2004"},{"issue":"4","key":"2026040314515463800_ref324","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1046\/j.0824-7935.2003.00221.x","article-title":"\u201cMicroplanning with Communicative Intentions: The SPUD System\u201d","volume":"19","author":"Stone","year":"2003","journal-title":"Computational Intelligence"},{"key":"2026040314515463800_ref325","first-page":"2413","article-title":"\u201cReinforcement Learning in Finite MDPs: PAC Analysis\u201d","volume":"10","author":"Strehl","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"2026040314515463800_ref326","first-page":"2765","article-title":"\u201cEnd-to-end Optimization of Goal-driven and Visually Grounded Dialogue Systems\u201d","volume-title":"Proceedings of the 26th International Joint Other on Artificial Intelligence (IJCAI)","author":"Strub","year":"2017"},{"key":"2026040314515463800_ref327","first-page":"2431","article-title":"\u201cOn-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems\u201d","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Su","year":"2016"},{"key":"2026040314515463800_ref328","article-title":"\u201cContinuously Learning Neural Dialogue Management\u201d","author":"Su","year":"2016","journal-title":"arXiv other"},{"key":"2026040314515463800_ref329","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.csl.2018.02.003","article-title":"\u201cReward Estimation for Dialogue Policy Optimisation\u201d","volume":"51","author":"Su","year":"2018","journal-title":"Computer Speech & Language"},{"key":"2026040314515463800_ref330","first-page":"2007","article-title":"\u201cLearning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems\u201d","volume-title":"Proceedings of the 16th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Su","year":"2015"},{"key":"2026040314515463800_ref331","first-page":"3813","article-title":"\u201cDiscriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning\u201d","volume-title":"Proceedings of the 2018 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Su","year":"2018"},{"key":"2026040314515463800_ref332","first-page":"61","article-title":"\u201cNatural Language Generation by Hierarchical Decoding with Linguistic Patterns\u201d","volume-title":"Proceedings of the 2018 Other of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Su","year":"2018"},{"key":"2026040314515463800_ref333","first-page":"697","article-title":"\u201cYAGO: a core of semantic knowledge\u201d","volume-title":"Proceedings of the 16th International Other on World Wide Web","author":"Suchanek","year":"2007"},{"key":"2026040314515463800_ref334","article-title":"\u201cLearning to Map Context-Dependent Sentences to Executable Formal Queries\u201d","author":"Suhr","year":"2018","journal-title":"arXiv other"},{"key":"2026040314515463800_ref335","first-page":"3104","article-title":"\u201cSequence to sequence learning with neural networks\u201d","volume-title":"NIPS","author":"Sutskever","year":"2014"},{"key":"2026040314515463800_ref336","first-page":"216","article-title":"\u201cIntegrated architectures for learning, planning, and reacting based on approximating dynamic programming\u201d","volume-title":"Proceedings of the Seventh International Other on Machine Learning","author":"Sutton","year":"1990"},{"key":"2026040314515463800_ref337","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1023\/A:1022633531479","article-title":"\u201cLearning to Predict by the Methods of Temporal Differences\u201d","volume":"3","author":"Sutton","year":"1988","journal-title":"Machine Learning"},{"key":"2026040314515463800_ref338","author":"Sutton","year":"2018","edition":"2nd edition"},{"key":"2026040314515463800_ref339","first-page":"1057","article-title":"\u201cPolicy Gradient Methods for Reinforcement Learning with Function Approximation\u201d","volume-title":"Advances in Neural Information Processing Systems 12 (NIPS)","author":"Sutton","year":"1999"},{"key":"2026040314515463800_ref340","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","article-title":"\u201cBetween MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning\u201d","volume":"112","author":"Sutton","year":"1999","journal-title":"Artificial Intelligence"},{"key":"2026040314515463800_ref341","article-title":"\u201cIntriguing properties of neural networks\u201d","author":"Szegedy","year":"2013","journal-title":"CoRR"},{"key":"2026040314515463800_ref342","author":"Szepesv\u00e1ri","year":"2010"},{"key":"2026040314515463800_ref343","article-title":"\u201cThe Web as a Knowledge-base for Answering Complex Questions\u201d","author":"Talmor","year":"2018","journal-title":"arXiv other"},{"key":"2026040314515463800_ref344","first-page":"2298","article-title":"\u201cSubgoal Discovery for Hierarchical Dialogue Policy Learning\u201d","volume-title":"Proceedings of the 2018 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Tang","year":"2018"},{"key":"2026040314515463800_ref345","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/203330.203343","article-title":"\u201cTemporal Difference Learning and TD-Gammon\u201d","volume":"38","author":"Tesauro","year":"1995","journal-title":"Communications of the ACM"},{"issue":"3","key":"2026040314515463800_ref346","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/203330.203343","article-title":"\u201cTemporal Difference Learning and TD-Gammon\u201d","volume":"38","author":"Tesauro","year":"1995","journal-title":"Communications of the ACM"},{"key":"2026040314515463800_ref347","first-page":"2139","article-title":"\u201cData-Efficient Off-Policy Policy Evaluation for Reinforcement Learning\u201d","volume-title":"Proceedings of the 33rd International Other on Machine Learning (ICML)","author":"Thomas","year":"2016"},{"key":"2026040314515463800_ref348","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1093\/biomet\/25.3-4.285","article-title":"\u201cOn the Likelihood that One Unknown Probability Exceeds Another in View of the Evidence of Two Samples\u201d","volume":"25","author":"Thompson","year":"1933","journal-title":"Biometrika"},{"key":"2026040314515463800_ref349","first-page":"2214","article-title":"\u201cParallel Data, Tools and Interfaces in OPUS\u201d","volume-title":"Proceedings of the Eighth International Other on Language Resources and Evaluation (LREC\u201912)","author":"Tiedemann","year":"2012"},{"key":"2026040314515463800_ref350","doi-asserted-by":"crossref","first-page":"1434","DOI":"10.18653\/v1\/P16-1136","article-title":"\u201cCompositional learning of embeddings for relation paths in knowledge base and text\u201d","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Toutanova","year":"2016"},{"key":"2026040314515463800_ref351","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/978-94-015-9204-8_8","volume-title":"Foundations of Rational Agency","author":"Traum","year":"1999"},{"key":"2026040314515463800_ref352","article-title":"\u201cNewsQA: A machine comprehension dataset\u201d","author":"Trischler","year":"2016","journal-title":"arXiv other"},{"key":"2026040314515463800_ref353","first-page":"84","article-title":"\u201cCombinatorics of Go\u201d","volume-title":"Proceedings of the Fifth International Other on Computers and Games. Lecture Notes in Computer Science","author":"Tromp","year":"2006"},{"key":"2026040314515463800_ref354","author":"Tur","year":"2011"},{"key":"2026040314515463800_ref355","first-page":"1721","article-title":"\u201cDomain-Independent User Satisfaction Reward Estimation for Dialogue Policy Learning\u201d","volume-title":"Proceedings of the 18th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Ultes","year":"2017"},{"key":"2026040314515463800_ref356","first-page":"65","article-title":"\u201cReward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning\u201d","volume-title":"Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL)","author":"Ultes","year":"2017"},{"key":"2026040314515463800_ref357","first-page":"73","article-title":"\u201cPyDial: A Multi-Domain Statistical Dialogue System Toolkit\u201d","volume-title":"Proceedings of the Fifty-fifth Annual Meeting of the Association for Computational Linguistics (ACL), System Demonstrations","author":"Ultes","year":"2017"},{"key":"2026040314515463800_ref358","article-title":"\u201cWaveNet: A Generative Model for Raw Audio\u201d","volume-title":"arXiv other","author":"van den Oord","year":"2016"},{"key":"2026040314515463800_ref359","first-page":"2094","article-title":"\u201cDeep Reinforcement Learning with Double Q-learning\u201d","volume-title":"Proceedings of the Thirtieth AAAI Other on Artificial Intelligence (AAAI-16)","author":"van Hasselt","year":"2016"},{"key":"2026040314515463800_ref360","first-page":"5998","article-title":"\u201cAttention is All You Need\u201d","volume-title":"Advances in Neural Information Processing Systems 30","author":"Vaswani","year":"2017"},{"key":"2026040314515463800_ref361","first-page":"2692","article-title":"\u201cPointer Networks\u201d","volume-title":"Advances in Neural Information Processing Systems 28","author":"Vinyals","year":"2015"},{"key":"2026040314515463800_ref362","article-title":"\u201cA Neural Conversational Model\u201d","volume-title":"ICML Deep Learning Workshop","author":"Vinyals","year":"2015"},{"key":"2026040314515463800_ref363","first-page":"3156","article-title":"\u201cShow and Tell: A Neural Image Caption Generator\u201d","volume-title":"Proceedings of the IEEE Other on Computer Vision and Pattern Recognition","author":"Vinyals","year":"2015"},{"key":"2026040314515463800_ref364","first-page":"4466","article-title":"\u201cGuessWhat?! Visual Object Discovery through Multi-modal Dialogue\u201d","volume-title":"Proceedings of the 2017 IEEE Other on Computer Vision and Pattern Recognition (CVPR)","author":"Vries","year":"2017"},{"key":"2026040314515463800_ref365","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1613\/jair.713","article-title":"\u201cAn Application of Reinforcement Learning to Dialogue Strategy Selection in a Spoken Dialogue System for Email\u201d","author":"Walker","year":"2000","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2026040314515463800_ref366","doi-asserted-by":"crossref","first-page":"271","DOI":"10.3115\/976909.979652","article-title":"\u201cPARADISE: A Framework for Evaluating Spoken Dialogue Agents\u201d","volume-title":"Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Walker","year":"1997"},{"key":"2026040314515463800_ref367","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1006\/csla.1998.0110","article-title":"\u201cEvaluating Spoken Dialogue Agents with PARADISE: Two Case Studies\u201d","volume":"12","author":"Walker","year":"1998","journal-title":"Computer Speech & Language"},{"key":"2026040314515463800_ref368","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1613\/jair.2329","article-title":"\u201cIndividual and Domain Adaptation in Sentence Planning for Dialogue\u201d","author":"Walker","year":"2007","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2026040314515463800_ref369","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1017\/S1351324900002503","article-title":"\u201cTowards Developing General Models of Usability with PARADISE\u201d","volume":"6","author":"Walker","year":"2000","journal-title":"Natural Language Engineering"},{"key":"2026040314515463800_ref370","first-page":"3674","article-title":"\u201cSequence Modeling via Segmentations\u201d","volume-title":"Proceedings of the 34th International Other on Machine Learning","author":"Wang","year":"2017"},{"key":"2026040314515463800_ref371","doi-asserted-by":"crossref","first-page":"189","DOI":"10.18653\/v1\/P17-1018","article-title":"\u201cGated self-matching networks for reading comprehension and question answering\u201d","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Wang","year":"2017"},{"key":"2026040314515463800_ref372","first-page":"16","article-title":"\u201cSpoken Language Understanding: An Introduction to the Statistical Framework\u201d","volume":"22","author":"Wang","year":"2005","journal-title":"IEEE Signal Processing Magazine"},{"key":"2026040314515463800_ref373","first-page":"57","article-title":"\u201cPolicy Learning for Domain Selection in an Extensible Multi-domain Spoken Dialogue System\u201d","volume-title":"Proceedings of the 2014 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Wang","year":"2014"},{"key":"2026040314515463800_ref374","first-page":"1995","article-title":"\u201cDueling Network Architectures for Deep Reinforcement Learning\u201d","volume-title":"Proceedings of the Third International Other on Machine Learning (ICML-16)","author":"Wang","year":"2016"},{"key":"2026040314515463800_ref375","article-title":"\u201cLearning from Delayed Rewards\u201d","volume-title":"PhD other. UK: King\u2019s College, University of Cambridge","author":"Watkins","year":"1989"},{"key":"2026040314515463800_ref376","first-page":"3844","article-title":"\u201cAirDialogue: An Environment for Goal-oriented Dialogue Research\u201d","volume-title":"Proceedings of the 2018 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Wei","year":"2018"},{"key":"2026040314515463800_ref377","article-title":"\u201cFastQA: A simple and efficient neural architecture for question answering\u201d","volume-title":"arXiv other","author":"Weissenborn","year":"2017"},{"issue":"1","key":"2026040314515463800_ref378","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1145\/365153.365168","article-title":"\u201cELIZA: A Computer Program for the Study of Natural Language Communication Between Man and Machine\u201d","volume":"9","author":"Weizenbaum","year":"1966","journal-title":"Commun. ACM"},{"key":"2026040314515463800_ref379","article-title":"\u201cConstructing Datasets for Multi-hop Reading Comprehension Across Documents\u201d","volume-title":"arXiv other","author":"Welbl","year":"2017"},{"key":"2026040314515463800_ref380","first-page":"120","article-title":"\u201cMulti-domain Neural Network Language Generation for Spoken Dialogue Systems\u201d","volume-title":"Proceedings of the 2016 Other of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL)","author":"Wen","year":"2016"},{"key":"2026040314515463800_ref381","first-page":"1711","article-title":"\u201cSemantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems\u201d","volume-title":"Proceedings of the 2015 Other on Empirical Methods in Natural Language Processing (EMNLP)","author":"Wen","year":"2015"},{"key":"2026040314515463800_ref382","first-page":"438","article-title":"\u201cA Network-based End-to-End Trainable Task-oriented Dialogue System\u201d","volume-title":"Proceedings of the 15th Other of the European Chapter of the Association for Computational Linguistics (EACL)","author":"Wen","year":"2017"},{"key":"2026040314515463800_ref383","volume-title":"Springer","author":"Wiering","year":"2012"},{"key":"2026040314515463800_ref384","article-title":"\u201cPartially Observable Markov Decision Processes for Spoken Dialogue Management\u201d","volume-title":"PhD other. Cambridge, UK: Cambridge University","author":"Williams","year":"2006"},{"issue":"10","key":"2026040314515463800_ref385","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1016\/j.specom.2008.05.007","article-title":"\u201cEvaluating User Simulations with the Cram\u00e9r-von Mises Divergence\u201d","volume":"50","author":"Williams","year":"2008","journal-title":"Speech Communication"},{"key":"2026040314515463800_ref386","first-page":"665","article-title":"\u201cHybrid Code Networks: Practical and Efficient End-to-end Dialog Control with Supervised and Reinforcement Learning\u201d","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Williams","year":"2017"},{"issue":"4","key":"2026040314515463800_ref387","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1609\/aimag.v35i4.2558","article-title":"\u201cThe Dialog State Tracking Challenge Series\u201d","volume":"35","author":"Williams","year":"2014","journal-title":"AI Magazine"},{"key":"2026040314515463800_ref388","first-page":"404","article-title":"\u201cThe Dialog State Tracking Challenge\u201d","volume-title":"Proceedings of the 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Williams","year":"2013"},{"issue":"2","key":"2026040314515463800_ref389","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/j.csl.2006.06.008","article-title":"\u201cPartially Observable Markov Decision Processes for Spoken Dialog Systems\u201d","volume":"21","author":"Williams","year":"2007","journal-title":"Computer Speech and Language"},{"key":"2026040314515463800_ref390","article-title":"\u201cEnd-to-end LSTM-based Dialog Control Optimized with Supervised and Reinforcement Learning\u201d","volume-title":"","author":"Williams","year":"2016"},{"key":"2026040314515463800_ref391","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1022672621406","article-title":"\u201cSimple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning\u201d","volume":"8","author":"Williams","year":"1992","journal-title":"Machine Learning"},{"key":"2026040314515463800_ref392","first-page":"3437","article-title":"\u201cNora the empathetic psychologist\u201d","volume-title":"Proc. Interspeech","author":"Winata","year":"2017"},{"key":"2026040314515463800_ref393","first-page":"6154","article-title":"\u201cEnd-to-End Dynamic Query Memory Network for Entity-Value Independent Task-Oriented Dialog\u201d","volume-title":"Proceedings of the 2018 IEEE International Other on Acoustics, Speech and Signal Processing (ICASSP)","author":"Wu","year":"2018"},{"issue":"11","key":"2026040314515463800_ref394","doi-asserted-by":"crossref","first-page":"2026","DOI":"10.1109\/TASLP.2015.2462712","article-title":"\u201cA probabilistic framework for representing dialog systems and entropy-based dialog management through dynamic stochastic state evolution\u201d","volume":"23","author":"Wu","year":"2015","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing (TASLP)"},{"issue":"3","key":"2026040314515463800_ref395","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1007\/s10791-009-9112-1","article-title":"\u201cAdapting boosting for information retrieval measures\u201d","volume":"13","author":"Wu","year":"2010","journal-title":"Information Retrieval"},{"key":"2026040314515463800_ref396","article-title":"\u201cGoogle\u2019s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation\u201d","volume-title":"CoRR","author":"Wu","year":"2016"},{"key":"2026040314515463800_ref397","first-page":"5610","article-title":"\u201cHierarchical Recurrent Attention Network for Response Generation\u201d","volume-title":"AAAI","author":"Xing","year":"2018"},{"key":"2026040314515463800_ref398","article-title":"\u201cDynamic coattention networks for question answering\u201d","volume-title":"arXiv other","author":"Xiong","year":"2016"},{"key":"2026040314515463800_ref399","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D17-1060","article-title":"\u201cDeepPath: A reinforcement learning method for knowledge graph reasoning\u201d","volume-title":"arXiv other","author":"Xiong","year":"2017"},{"key":"2026040314515463800_ref400","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/W18-6243","article-title":"\u201cEmo2Vec: Learning Generalized Emotion Representation by Multi-task Training\u201d","volume-title":"arXiv other","author":"Xu","year":"2018"},{"key":"2026040314515463800_ref401","first-page":"617","article-title":"\u201cNeural Response Generation via GAN with an Approximate Embedding Layer\u201d","volume-title":"EMNLP","author":"Xu","year":"2017"},{"issue":"6","key":"2026040314515463800_ref402","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1109\/TASL.2008.2001106","article-title":"\u201cAn Integrative and Discriminative Technique for Spoken Utterance Classification\u201d","volume":"16","author":"Yaman","year":"2008","journal-title":"IEEE Transactions on Audio, Speech & Language Processing"},{"key":"2026040314515463800_ref403","first-page":"55","article-title":"\u201cLearning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System\u201d","volume-title":"Proceedings of the 39th International ACM SIGIR Other on Research and Development in Information Retrieval (SIGIR)","author":"Yan","year":"2016"},{"key":"2026040314515463800_ref404","article-title":"\u201cEmbedding entities and relations for learning and inference in knowledge bases\u201d","volume-title":"ICLR","author":"Yang","year":"2015"},{"key":"2026040314515463800_ref405","article-title":"\u201cDifferentiable learning of logical rules for knowledge base completion\u201d","volume-title":"CoRR","author":"Yang","year":"2017"},{"key":"2026040314515463800_ref406","first-page":"5690","article-title":"\u201cEnd-to-end Joint Learning of Natural Language Understanding and Dialogue Manager\u201d","volume-title":"Proceedings of the 2017 IEEE International Other on Acoustics, Speech and Signal Processing (ICASSP)","author":"Yang","year":"2017"},{"key":"2026040314515463800_ref407","first-page":"2524","article-title":"\u201cRecurrent Neural Networks for Language Understanding\u201d","volume-title":"Proceedings of the 14th Annual Other of the International Speech Communication Association (INTERSPEECH)","author":"Yao","year":"2013"},{"key":"2026040314515463800_ref408","article-title":"\u201cAttention with Intention for a Neural Network Conversation Model\u201d","volume-title":"NIPS Workshop on Machine Learning for Spoken Language Understanding and Interaction","author":"Yao","year":"2015"},{"key":"2026040314515463800_ref409","doi-asserted-by":"crossref","first-page":"956","DOI":"10.3115\/v1\/P14-1090","article-title":"\u201cInformation extraction over structured data: Question answering with Freebase\u201d","volume-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Yao","year":"2014"},{"key":"2026040314515463800_ref410","first-page":"1321","article-title":"\u201cSemantic parsing via staged query graph generation: Question answering with knowledge base\u201d","volume-title":"ACL","author":"Yih","year":"2015"},{"key":"2026040314515463800_ref411","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/N15-4004","article-title":"\u201cDeep Learning and Continuous Representations for Natural Language Processing\u201d","volume-title":"Proceedings of the 2015 Other of the North American Chapter of the Association for Computational Linguistics: Tutorial","author":"Yih","year":"2015"},{"key":"2026040314515463800_ref412","article-title":"\u201cDeep Learning and Continuous Representations for Natural Language Processing\u201d","volume-title":"IJCAI: Tutorial","author":"Yih","year":"2016"},{"issue":"2","key":"2026040314515463800_ref413","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.csl.2009.04.001","article-title":"\u201cThe Hidden Information State Model: A Practical Framework for POMDP-based Spoken Dialogue Management\u201d","volume":"24","author":"Young","year":"2010","journal-title":"Computer Speech & Language"},{"key":"2026040314515463800_ref414","first-page":"3","article-title":"\u201cEvaluation of Statistical POMDP-Based Dialogue Systems in Noisy Environments\u201d","volume-title":"Situated Dialog in Speech-Based Human-Computer Interaction. Signals and Communication Technology","author":"Young","year":"2016"},{"issue":"5","key":"2026040314515463800_ref415","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1109\/JPROC.2012.2225812","article-title":"\u201cPOMDP-based statistical spoken dialog systems: a review\u201d","volume":"101","author":"Young","year":"2013","journal-title":"Proceedings of the IEEE"},{"key":"2026040314515463800_ref416","article-title":"\u201cQANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension\u201d","volume-title":"arXiv other","author":"Yu","year":"2018"},{"key":"2026040314515463800_ref417","doi-asserted-by":"crossref","first-page":"140","DOI":"10.18653\/v1\/W18-5015","article-title":"\u201cMultimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog\u201d","volume-title":"Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL)","author":"Zhang","year":"2018"},{"key":"2026040314515463800_ref418","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.18653\/v1\/P18-1102","article-title":"\u201cLearning to Control the Specificity in Neural Response Generation\u201d","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Zhang","year":"2018"},{"key":"2026040314515463800_ref419","doi-asserted-by":"crossref","first-page":"2204","DOI":"10.18653\/v1\/P18-1205","article-title":"\u201cPersonalizing Dialogue Agents: I have a dog, do you have pets too?\u201d","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Zhang","year":"2018"},{"key":"2026040314515463800_ref420","article-title":"\u201cReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension\u201d","volume-title":"arXiv other","author":"Zhang","year":"2018"},{"key":"2026040314515463800_ref421","first-page":"1815","article-title":"\u201cGenerating Informative and Diverse Conversational Responses via Adversarial Information Maximization\u201d","volume-title":"NeurIPS","author":"Zhang","year":"2018"},{"key":"2026040314515463800_ref422","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18653\/v1\/W16-3601","article-title":"\u201cTowards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning\u201d","volume-title":"Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Zhao","year":"2016"},{"key":"2026040314515463800_ref423","first-page":"27","article-title":"\u201cGenerative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability\u201d","volume-title":"ACL","author":"Zhao","year":"2017"},{"key":"2026040314515463800_ref424","article-title":"\u201cThe design and implementation of XiaoIce, an empathetic social chatbot\u201d","volume-title":"arXiv other","author":"Zhou","year":"2018"}],"container-title":["Foundations and Trends\u00ae in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftinr\/article-pdf\/13\/2-3\/127\/11048220\/1500000074en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftinr\/article-pdf\/13\/2-3\/127\/11048220\/1500000074en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T14:29:56Z","timestamp":1777472996000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftinr\/article\/13\/2-3\/127\/1328681\/Neural-Approaches-to-Conversational-AI"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,21]]},"references-count":423,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2019,2,21]]}},"URL":"https:\/\/doi.org\/10.1561\/1500000074","relation":{},"ISSN":["1554-0669","1554-0677"],"issn-type":[{"value":"1554-0669","type":"print"},{"value":"1554-0677","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,21]]}}}