{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:18:45Z","timestamp":1777130325648,"version":"3.51.4"},"reference-count":81,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T00:00:00Z","timestamp":1628208000000},"content-version":"vor","delay-in-days":217,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We present a new method, Soloist,1 that uses transfer learning and machine teaching to build task bots at scale. We parameterize classical modular task-oriented dialog systems using a Transformer-based auto-regressive language model, which subsumes different dialog modules into a single neural model. We pre-train, on heterogeneous dialog corpora, a task-grounded response generation model, which can generate dialog responses grounded in user goals and real-world knowledge for task completion. The pre-trained model can be efficiently adapted to accomplish new tasks with a handful of task-specific dialogs via machine teaching, where training samples are generated by human teachers interacting with the system. Experiments show that (i)Soloist creates new state-of-the-art on well-studied task-oriented dialog benchmarks, including CamRest676 and MultiWOZ; (ii) in the few-shot fine-tuning settings, Soloist significantly outperforms existing methods; and (iii) the use of machine teaching substantially reduces the labeling cost of fine-tuning. The pre-trained models and codes are available at https:\/\/aka.ms\/soloist.<\/jats:p>","DOI":"10.1162\/tacl_a_00399","type":"journal-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T19:30:11Z","timestamp":1632166211000},"page":"807-824","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":58,"title":["S<scp>oloist<\/scp>: BuildingTask Bots at Scale with Transfer Learning and Machine Teaching"],"prefix":"10.1162","volume":"9","author":[{"given":"Baolin","family":"Peng","sequence":"first","affiliation":[{"name":"Microsoft Research, Redmond, United States. bapeng@microsoft.com"}]},{"given":"Chunyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, United States. chunyl@microsoft.com"}]},{"given":"Jinchao","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, United States. jincli@microsoft.com"}]},{"given":"Shahin","family":"Shayandeh","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, United States. shahins@microsoft.com"}]},{"given":"Lars","family":"Liden","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, United States. lars.liden@microsoft.com"}]},{"given":"Jianfeng","family":"Gao","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, United States. jfgao@microsoft.com"}]}],"member":"281","published-online":{"date-parts":[[2021,8,2]]},"reference":[{"key":"2021080620254546600_bib1","article-title":"Towards a human-like open-domain chatbot","author":"Adiwardana","year":"2020","journal-title":"arXiv preprint arXiv:2001.09977"},{"key":"2021080620254546600_bib2","doi-asserted-by":"publisher","first-page":"85","DOI":"10.18653\/v1\/2020.acl-main.9","article-title":"Plato: Pre-trained dialogue generation model with discrete latent variable","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Bao","year":"2020"},{"key":"2021080620254546600_bib3","article-title":"Rasa: Open source language understanding and dialogue management","author":"Bocklisch","year":"2017","journal-title":"CoRR"},{"key":"2021080620254546600_bib4","doi-asserted-by":"publisher","first-page":"15","DOI":"10.18653\/v1\/D19-5602","article-title":"Hello, it\u2019s GPT-2-How can I help you? Towards the use of pretrained language models for task-oriented dialogue systems","volume-title":"Proceedings of the 3rd Workshop on Neural Generation and Translation","author":"Budzianowski","year":"2019"},{"key":"2021080620254546600_bib5","doi-asserted-by":"publisher","first-page":"5016","DOI":"10.18653\/v1\/D18-1547","article-title":"Multiwoz-a large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue modelling","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Budzianowski","year":"2018"},{"key":"2021080620254546600_bib6","doi-asserted-by":"publisher","first-page":"4506","DOI":"10.18653\/v1\/D19-1459","article-title":"Taskmaster-1: Toward a realistic and diverse dialog dataset","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Byrne","year":"2019"},{"key":"2021080620254546600_bib7","doi-asserted-by":"publisher","first-page":"38","DOI":"10.18653\/v1\/2020.nlp4convai-1.5","article-title":"Efficient intent detection with dual sentence encoders","volume-title":"Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI","author":"Casanueva","year":"2020"},{"issue":"2","key":"2021080620254546600_bib8","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1145\/3166054.3166058","article-title":"A survey on dialogue systems: Recent advances and new frontiers","volume":"19","author":"Chen","year":"2017","journal-title":"Acm Sigkdd Explorations Newsletter"},{"key":"2021080620254546600_bib9","doi-asserted-by":"publisher","first-page":"7521","DOI":"10.1609\/aaai.v34i05.6250","article-title":"Schema-guided multi-domain dialogue state tracking with graph attention neural networks.","volume-title":"AAAI","author":"Chen","year":"2020"},{"key":"2021080620254546600_bib10","doi-asserted-by":"publisher","first-page":"3696","DOI":"10.18653\/v1\/P19-1360","article-title":"Semantically conditioned dialog response generation via hierarchical disentangled self-attention","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Chen","year":"2019"},{"key":"2021080620254546600_bib11","doi-asserted-by":"publisher","first-page":"107","DOI":"10.18653\/v1\/2020.acl-main.11","article-title":"Span-convert: Few-shot span extraction for dialog with pretrained conversational representations","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5\u201310, 2020","author":"Coope","year":"2020"},{"key":"2021080620254546600_bib12","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019"},{"key":"2021080620254546600_bib13","first-page":"13042","article-title":"Unified language model pre-training for natural language understanding and generation","volume-title":"Advances in Neural Information Processing Systems","author":"Li","year":"2019"},{"key":"2021080620254546600_bib14","first-page":"422","article-title":"Multiwoz 2.1: A consolidated multi-domain dialogue dataset with state corrections and state tracking baselines","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference","author":"Eric","year":"2020"},{"issue":"2\u20133","key":"2021080620254546600_bib15","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1561\/1500000074","article-title":"Neural approaches to conversational AI","volume":"13","author":"Gao","year":"2019","journal-title":"Foundations and Trends in Information Retrieval"},{"key":"2021080620254546600_bib16","article-title":"Robust conversational AI with grounded text generation","author":"Gao","year":"2020","journal-title":"CoRR"},{"key":"2021080620254546600_bib17","doi-asserted-by":"crossref","first-page":"264","DOI":"10.18653\/v1\/W19-5932","article-title":"Dialog state tracking: A neural reading comprehension approach","volume-title":"Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue","author":"Gao","year":"2019"},{"key":"2021080620254546600_bib18","doi-asserted-by":"publisher","first-page":"1458","DOI":"10.21437\/Interspeech.2019-1863","article-title":"Hyst: A hybrid approach for flexible and accurate dialogue state tracking","author":"Goel","year":"2019","journal-title":"Proceedings of Interspeech 2019"},{"key":"2021080620254546600_bib19","doi-asserted-by":"crossref","first-page":"583","DOI":"10.18653\/v1\/2020.acl-main.54","article-title":"End-to-end neural pipeline for goal-oriented dialogue systems using GPT-2","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Ham","year":"2020"},{"key":"2021080620254546600_bib20","doi-asserted-by":"crossref","first-page":"35","DOI":"10.18653\/v1\/2020.sigdial-1.4","article-title":"Trippy: A triple copy strategy for value independent neural dialog state tracking","volume-title":"Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue","author":"Heck","year":"2020"},{"key":"2021080620254546600_bib21","doi-asserted-by":"publisher","first-page":"2161","DOI":"10.18653\/v1\/2020.findings-emnlp.196","article-title":"Convert: Efficient and accurate conversational representations from transformers","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, EMNLP 2020, Online Event, 16-20 November 2020","author":"Henderson","year":"2020"},{"key":"2021080620254546600_bib22","article-title":"The curious case of neural text degeneration","volume-title":"International Conference on Learning Representations","author":"Holtzman","year":"2019"},{"key":"2021080620254546600_bib23","article-title":"A simple language model for task-oriented dialogue","author":"Hosseini-Asl","year":"2020","journal-title":"arXiv preprint arXiv:2005.00796"},{"key":"2021080620254546600_bib24","article-title":"Ctrl: A conditional transformer language model for controllable generation","author":"Keskar","year":"2019","journal-title":"arXiv preprint arXiv:1909.05858"},{"key":"2021080620254546600_bib25","article-title":"The eighth dialog system technology challenge","author":"Kim","year":"2019","journal-title":"arXiv preprint arXiv:1911.06394"},{"key":"2021080620254546600_bib26","doi-asserted-by":"crossref","first-page":"567","DOI":"10.18653\/v1\/2020.acl-main.53","article-title":"Efficient dialogue state tracking by selectively overwriting memory","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Kim","year":"2020"},{"key":"2021080620254546600_bib27","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"2021080620254546600_bib28","article-title":"Non-autoregressive dialog state tracking","author":"Le","year":"2020","journal-title":"arXiv preprint arXiv:2002.08024"},{"key":"2021080620254546600_bib29","doi-asserted-by":"crossref","first-page":"5478","DOI":"10.18653\/v1\/P19-1546","article-title":"SUMBT: Slot-utterance matching for universal and scalable belief tracking","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Lee","year":"2019"},{"key":"2021080620254546600_bib30","doi-asserted-by":"crossref","first-page":"64","DOI":"10.18653\/v1\/P19-3011","article-title":"ConvLab: Multi-domain end-to-end dialog system platform","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Lee","year":"2019"},{"key":"2021080620254546600_bib31","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P18-1133","article-title":"Sequicity: Simplifying task-oriented dialogue systems with single sequence-to-sequence architectures","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Lei","year":"2018"},{"key":"2021080620254546600_bib32","doi-asserted-by":"crossref","first-page":"4678","DOI":"10.18653\/v1\/2020.emnlp-main.378","article-title":"Optimus: Organizing sentences via pre-trained modeling of a latent space","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Li","year":"2020"},{"key":"2021080620254546600_bib33","article-title":"Results of the multi-domain task-completion dialog challenge","volume-title":"Proceedings of the 34th AAAI Conference on Artificial Intelligence, Eighth Dialog System Technology Challenge Workshop","author":"Li","year":"2020"},{"key":"2021080620254546600_bib34","article-title":"BiERU: Bidirectional emotional recurrent unit for conversational sentiment analysis","author":"Li","year":"2020","journal-title":"arXiv preprint arXiv:2006.00492"},{"key":"2021080620254546600_bib35","article-title":"End-to-end task-completion neural dialogue systems","author":"Li","year":"2017","journal-title":"arXiv preprint arXiv:1703.01008"},{"key":"2021080620254546600_bib36","doi-asserted-by":"crossref","first-page":"3391","DOI":"10.18653\/v1\/2020.emnlp-main.273","article-title":"MinTL: Minimalist transfer learning for task-oriented dialogue systems","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Lin","year":"2020"},{"key":"2021080620254546600_bib37","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692"},{"key":"2021080620254546600_bib38","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.inffus.2020.06.011","article-title":"A survey on empathetic dialogue systems","volume":"64","author":"Ma","year":"2020","journal-title":"Information Fusion"},{"key":"2021080620254546600_bib39","doi-asserted-by":"publisher","first-page":"3836","DOI":"10.18653\/v1\/P19-1373","article-title":"Pretraining methods for dialog context representation learning","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Mehri","year":"2019"},{"key":"2021080620254546600_bib40","doi-asserted-by":"publisher","first-page":"165","DOI":"10.18653\/v1\/W19-5921","article-title":"Structured fusion networks for dialog","volume-title":"Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue","author":"Mehri","year":"2019"},{"key":"2021080620254546600_bib41","article-title":"Toward scalable neural dialogue state tracking model","author":"Nouri","year":"2018","journal-title":"arXiv preprint arXiv:1812.00899"},{"key":"2021080620254546600_bib42","article-title":"A modular task-oriented dialogue system using a neural mixture-of-experts","author":"Pei","year":"2019","journal-title":"arXiv preprint arXiv:1907.05346"},{"key":"2021080620254546600_bib43","article-title":"RADDLE: An evaluation benchmark and analysis platform for robust task-oriented dialog systems","author":"Peng","year":"2020","journal-title":"CoRR"},{"key":"2021080620254546600_bib44","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.18653\/v1\/D17-1237","article-title":"Composite task-completion dialogue policy learning via hierarchical deep reinforcement learning","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Peng","year":"2017"},{"key":"2021080620254546600_bib45","doi-asserted-by":"publisher","first-page":"172","DOI":"10.18653\/v1\/2020.findings-emnlp.17","article-title":"Few-shot natural language generation for task-oriented dialog","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Peng","year":"2020"},{"key":"2021080620254546600_bib46","article-title":"Teacher-student framework enhanced multi-domain dialogue generation","author":"Peng","year":"2019","journal-title":"arXiv preprint arXiv:1908.07137"},{"key":"2021080620254546600_bib47","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"2021080620254546600_bib48","doi-asserted-by":"publisher","first-page":"432","DOI":"10.18653\/v1\/P18-2069","article-title":"Large-scale multi-domain belief tracking with knowledge sharing","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Ramadan","year":"2018"},{"key":"2021080620254546600_bib49","doi-asserted-by":"publisher","first-page":"8689","DOI":"10.1609\/aaai.v34i05.6394","article-title":"Towards scalable multi-domain conversational agents: The schema-guided dialogue dataset","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Rastogi","year":"2020"},{"key":"2021080620254546600_bib50","doi-asserted-by":"crossref","first-page":"1876","DOI":"10.18653\/v1\/D19-1196","article-title":"Scalable and accurate dialogue state tracking via hierarchical sequence generation","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Ren","year":"2019"},{"key":"2021080620254546600_bib51","article-title":"Open-domain conversational agents: Current progress, open problems, and future directions","author":"Roller","year":"2020","journal-title":"CoRR"},{"key":"2021080620254546600_bib52","article-title":"Recipes for building an open-domain chatbot","author":"Roller","year":"2020","journal-title":"arXiv preprint arXiv:2004.13637"},{"key":"2021080620254546600_bib53","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.18653\/v1\/P16-1162","article-title":"Neural machine translation of rare words with subword units","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Sennrich","year":"2016"},{"key":"2021080620254546600_bib54","doi-asserted-by":"publisher","first-page":"343","DOI":"10.18653\/v1\/2020.acl-demos.39","article-title":"Conversation learner-a machine teaching tool for building dialog managers for task-oriented dialog systems","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Shukla","year":"2020"},{"key":"2021080620254546600_bib55","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.18653\/v1\/2020.acl-main.222","article-title":"The dialogue dodecathlon: Open-domain knowledge and image grounded conversational agents","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5\u201310, 2020","author":"Shuster","year":"2020"},{"key":"2021080620254546600_bib56","article-title":"Machine teaching: A new paradigm for building machine learning systems","author":"Simard","year":"2017","journal-title":"CoRR"},{"key":"2021080620254546600_bib57","first-page":"438","article-title":"A network-based end-to-end trainable task-oriented dialogue system","volume-title":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers","author":"Wen","year":"2017"},{"key":"2021080620254546600_bib58","doi-asserted-by":"publisher","first-page":"665","DOI":"10.18653\/v1\/P17-1062","article-title":"Hybrid code networks: Practical and efficient end-to-end dialog control with supervised and reinforcement learning","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Williams","year":"2017"},{"key":"2021080620254546600_bib59","doi-asserted-by":"publisher","first-page":"82","DOI":"10.18653\/v1\/W17-5511","article-title":"Demonstration of interactive teaching for end-to-end dialog control with hybrid code networks","volume-title":"Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue","author":"Williams","year":"2017"},{"key":"2021080620254546600_bib60","doi-asserted-by":"publisher","first-page":"38","DOI":"10.18653\/v1\/2020.emnlp-demos.6","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Wolf","year":"2020"},{"key":"2021080620254546600_bib61","article-title":"Transfertransfo: A transfer learning approach for neural network based conversational agents","author":"Wolf","year":"2019","journal-title":"CoRR"},{"key":"2021080620254546600_bib62","first-page":"917","article-title":"TOD-BERT: Pre-trained natural language understanding for task-oriented dialogue","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Chien-Sheng","year":"2020"},{"key":"2021080620254546600_bib63","first-page":"808","article-title":"Transferable multi-domain state generator for task-oriented dialogue systems","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Chien-Sheng","year":"2019"},{"key":"2021080620254546600_bib64","article-title":"Alternating recurrent dialog model with large-scale pre-trained language models","author":"Qingyang","year":"2019","journal-title":"arXiv preprint arXiv:1910.03756"},{"key":"2021080620254546600_bib65","article-title":"A controllable model of grounded response generation","author":"Zeqiu","year":"2020","journal-title":"CoRR"},{"key":"2021080620254546600_bib66","first-page":"1","article-title":"End-to-end latent-variable task-oriented dialogue system with exact log-likelihood optimization","author":"Haotian","year":"2019","journal-title":"World Wide Web"},{"issue":"5","key":"2021080620254546600_bib67","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/JPROC.2012.2225812","article-title":"POMDP-based statistical spoken dialog systems: A review","volume":"101","author":"Young","year":"2013","journal-title":"Proceedings of IEEE"},{"key":"2021080620254546600_bib68","first-page":"4970","article-title":"Augmenting end-to-end dialogue systems with commonsense knowledge","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence","author":"Young","year":"2018"},{"key":"2021080620254546600_bib69","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.neucom.2019.12.126","article-title":"Dialogue systems with audio context","volume":"388","author":"Young","year":"2020","journal-title":"Neurocomputing"},{"key":"2021080620254546600_bib70","article-title":"Defending against neural fake news","volume-title":"Advances in Neural Information Processing Systems","author":"Zellers","year":"2019"},{"key":"2021080620254546600_bib71","first-page":"154","article-title":"Find or classify? dual strategy for slot-value predictions on multi-domain dialog state tracking","volume-title":"Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics","author":"Zhang","year":"2020"},{"key":"2021080620254546600_bib72","first-page":"9604","article-title":"Task-oriented dialog systems that consider multiple appropriate responses under the same context","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Zhang","year":"2020"},{"key":"2021080620254546600_bib73","doi-asserted-by":"publisher","first-page":"270","DOI":"10.18653\/v1\/2020.acl-demos.30","article-title":"DIALOGPT : Large-scale generative pre-training for conversational response generation","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Zhang","year":"2020"},{"key":"2021080620254546600_bib74","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18653\/v1\/W16-3601","article-title":"Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning","volume-title":"Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue","author":"Zhao","year":"2016"},{"key":"2021080620254546600_bib75","first-page":"1208","article-title":"Rethinking action spaces for reinforcement learning in end-to-end dialog agents with latent variable models","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Zhao","year":"2019"},{"key":"2021080620254546600_bib76","doi-asserted-by":"publisher","first-page":"1458","DOI":"10.18653\/v1\/P18-1135","article-title":"Global-locally self-attentive encoder for dialogue state tracking","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Zhong","year":"2018"},{"key":"2021080620254546600_bib77","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11325","article-title":"Emotional chatting machine: Emotional conversation generation with internal and external memory","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Zhou","year":"2018"},{"issue":"1","key":"2021080620254546600_bib78","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/coli_a_00368","article-title":"The design and implementation of xiaoice, an empathetic social chatbot","volume":"46","author":"Li","year":"2020","journal-title":"Computational Linguistics"},{"key":"2021080620254546600_bib79","article-title":"Multi-domain dialogue state tracking as dynamic knowledge graph enhanced question answering","author":"Li","year":"2019","journal-title":"arXiv preprint arXiv:1911.06192"},{"key":"2021080620254546600_bib80","doi-asserted-by":"publisher","first-page":"142","DOI":"10.18653\/v1\/2020.acl-demos.19","article-title":"ConvLab-2: An open-source toolkit for building, evaluating, and diagnosing dialogue systems","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Qi","year":"2020"},{"key":"2021080620254546600_bib81","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9761","article-title":"Machine teaching: An inverse problem to machine learning and an approach toward optimal education","volume-title":"Twenty-Ninth AAAI Conference on Artificial Intelligence","author":"Zhu","year":"2015"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00399\/1955175\/tacl_a_00399.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00399\/1955175\/tacl_a_00399.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T16:16:16Z","timestamp":1725812176000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00399\/106794\/Soloist-BuildingTask-Bots-at-Scale-with-Transfer"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00399","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021]]},"published":{"date-parts":[[2021]]}}}