{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T09:17:21Z","timestamp":1767777441376,"version":"3.41.2"},"reference-count":90,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T00:00:00Z","timestamp":1734566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Multimodal dialogue involving multiple participants presents complex computational challenges, primarily due to the rich interplay of diverse communicative modalities including speech, gesture, action, and gaze. These modalities interact in complex ways that traditional dialogue systems often struggle to accurately track and interpret. To address these challenges, we extend the textual enrichment strategy of Dense Paraphrasing (DP), by translating each nonverbal modality into linguistic expressions. By normalizing multimodal information into a language-based form, we hope to both simplify the representation for and enhance the computational understanding of situated dialogues. We show the effectiveness of the dense paraphrased language form by evaluating instruction-tuned Large Language Models (LLMs) against the Common Ground Tracking (CGT) problem using a publicly available collaborative problem-solving dialogue dataset. Instead of using multimodal LLMs, the dense paraphrasing technique represents the dialogue information from multiple modalities in a compact and structured machine-readable text format that can be directly processed by the language-only models. We leverage the capability of LLMs to transform machine-readable paraphrases into human-readable paraphrases, and show that this process can further improve the result on the CGT task. Overall, the results show that augmenting the context with dense paraphrasing effectively facilitates the LLMs' alignment of information from multiple modalities, and in turn largely improves the performance of common ground reasoning over the baselines. Our proposed pipeline with original utterances as input context already achieves comparable results to the baseline that utilized decontextualized utterances which contain rich coreference information. When also using the decontextualized input, our pipeline largely improves the performance of common ground reasoning over the baselines. We discuss the potential of DP to create a robust model that can effectively interpret and integrate the subtleties of multimodal communication, thereby improving dialogue system performance in real-world settings.<\/jats:p>","DOI":"10.3389\/frai.2024.1479905","type":"journal-article","created":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T06:24:53Z","timestamp":1734589493000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Dense Paraphrasing for multimodal dialogue interpretation"],"prefix":"10.3389","volume":"7","author":[{"given":"Jingxuan","family":"Tu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyeongmin","family":"Rim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingyang","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenneth","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Pustejovsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,12,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.08774","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv"},{"key":"B2","first-page":"34","article-title":"\u201cNaturalLI: natural logic inference for common sense reasoning,\u201d","author":"Angeli","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"B3","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1023\/A:1026346605477","article-title":"Common ground, corrections, and coordination","volume":"17","author":"Asher","year":"2003","journal-title":"Argumentation"},{"key":"B4","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: a survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B5","first-page":"111","article-title":"\u201cUsing lexical chains for text summarization,\u201d","author":"Barzilay","year":"1997","journal-title":"Intelligent Scalable Text Summarization"},{"key":"B6","first-page":"13","article-title":"\u201cFrom full generation to \u2018near-templates' without losing generality,\u201d","volume-title":"Proceedings of the KI'99 Workshop \u2018May I Speak Freely'","author":"Bateman","year":"1999"},{"key":"B7","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1162\/COLI_a_00166","article-title":"What is a paraphrase?","volume":"39","author":"Bhagat","year":"2013","journal-title":"Comp. Linguist"},{"key":"B8","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1111\/j.1467-8640.1985.tb00063.x","article-title":"Generating paraphrases from meaning-text semantic networks","volume":"1","author":"Boyer","year":"1985","journal-title":"Comp. Intell"},{"key":"B9","first-page":"1877","article-title":"\u201cLanguage models are few-shot learners,\u201d","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems, Vol. 33"},{"key":"B10","first-page":"1576","article-title":"\u201cAbstract meaning representation for gesture,\u201d","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","author":"Brutti","year":"2022"},{"key":"B11","doi-asserted-by":"crossref","first-page":"5016","DOI":"10.18653\/v1\/D18-1547","article-title":"\u201cMultiWOZ - a large-scale multi-domain Wizard-of-Oz dataset for task-oriented dialogue modelling,\u201d","author":"Budzianowski","year":"2018","journal-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing"},{"key":"B12","article-title":"A flexible shallow approach to text generation","author":"Busemann","year":"1998","journal-title":"arXiv"},{"volume-title":"Resolving Pronominal Reference to Abstract Entities","year":"2002","author":"Byron","key":"B13"},{"key":"B14","article-title":"\u201cEvaluating coreference resolvers on community-based question answering: from rule-based to state of the art,\u201d","volume-title":"CRAC","author":"Chai","year":"2022"},{"key":"B15","doi-asserted-by":"crossref","first-page":"1657","DOI":"10.18653\/v1\/P17-1152","article-title":"\u201cEnhanced LSTM for natural language inference,\u201d","author":"Chen","year":"2017","journal-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1007\/s00530-023-01051-8","article-title":"A literature survey on multimodal and multilingual automatic hate speech identification","volume":"29","author":"Chhabra","year":"2023","journal-title":"Multim. Syst"},{"key":"B17","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1162\/tacl_a_00377","article-title":"Decontextualization: making sentences stand-alone","volume":"9","author":"Choi","year":"2021","journal-title":"Transact. Assoc. Comp. Linguist"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1570","article-title":"Speechbert: an audio-and-text jointly learned language model for end-to-end spoken question answering","author":"Chuang","year":"2020","journal-title":"arXiv"},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.1037\/10096-006","volume-title":"Grounding in Communication","author":"Clark","year":"1991"},{"key":"B20","first-page":"78","article-title":"Paraphrase generation and information retrieval from stored text","volume":"11","author":"Culicover","year":"1968","journal-title":"Mech. Transl. Comput. Linguistics"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3586075","article-title":"Multimodal sentiment analysis: a survey of methods, trends, and challenges","volume":"55","author":"Das","year":"2023","journal-title":"ACM Comp. Surv"},{"key":"B22","doi-asserted-by":"crossref","first-page":"70","DOI":"10.18653\/v1\/2022.nlp4convai-1.7","article-title":"\u201cFrom rewriting to remembering: common ground for conversational QA models,\u201d","author":"Del Tredici","year":"2022","journal-title":"Proceedings of the 4th Workshop on NLP for Conversational AI"},{"key":"B23","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1162\/tacl_a_00397","article-title":"Towards question-answering as an automatic metric for evaluating the content quality of a summary","volume":"9","author":"Deutsch","year":"2021","journal-title":"Transact. Assoc. Comp. Linguist"},{"key":"B24","article-title":"\u201cThe NICE framework: analyzing students' nonverbal interactions during collaborative learning,\u201d","volume-title":"Pre-conference Workshop on Collaboration Analytics at 13th International Learning Analytics and Knowledge Conference (LAK 2023)","author":"Dey","year":"2023"},{"key":"B25","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the amount of ecologic association between species","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"key":"B26","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1207\/s15327809jls1501_9","article-title":"Sharing solutions: persistence and grounding in multimodal collaborative problem solving","volume":"15","author":"Dillenbourg","year":"2006","journal-title":"J. Learn. Sci"},{"key":"B27","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/978-3-031-06018-2_21","article-title":"\u201cTowards situated AMR: creating a corpus of gesture AMR,\u201d","volume-title":"Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Health, Operations Management, and Design","author":"Donatelli","year":"2022"},{"key":"B28","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1093\/jos\/17.1.51","article-title":"Dialogue acts, synchronizing units, and anaphora resolution","volume":"17","author":"Eckert","year":"2000","journal-title":"J. Semant"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.02498","article-title":"Honest students from untrusted teachers: learning an interpretable question-answering pipeline from a pretrained language model","author":"Eisenstein","year":"2022","journal-title":"arXiv"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00488","article-title":"Text-based np enrichment","author":"Elazar","year":"2021","journal-title":"arXiv"},{"key":"B31","doi-asserted-by":"crossref","first-page":"1949","DOI":"10.18653\/v1\/D18-1220","article-title":"\u201cA knowledge hunting framework for common sense reasoning,\u201d","author":"Emami","year":"2018","journal-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing"},{"key":"B32","first-page":"3938","article-title":"\u201cQuestion answering as an automatic evaluation metric for news article summarization,\u201d","author":"Eyal","year":"2019","journal-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)"},{"key":"B33","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1609\/aimag.v32i4.2377","article-title":"How people talk with robots: designing dialog to reduce user uncertainty","volume":"32","author":"Fischer","year":"2011","journal-title":"AI Mag"},{"key":"B34","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780199697922.001.0001","volume-title":"The Interactive Stance: Meaning for Conversation","author":"Ginzburg","year":"2012"},{"key":"B35","first-page":"481","volume-title":"Sentence Paraphrasing From a Conceptual Base","author":"Goldman","year":"1977"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.04790","article-title":"Multimodal-GPT: a vision and language model for dialogue with humans","author":"Gong","year":"2023","journal-title":"arXiv"},{"key":"B37","first-page":"518","article-title":"\u201cUsing question answering rewards to improve abstractive summarization,\u201d","author":"Gunasekara","year":"2021","journal-title":"Findings of the Association for Computational Linguistics: EMNLP 2021"},{"key":"B38","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1038\/s44159-021-00008-w","article-title":"A review of theories and methods in the science of face-to-face social interaction","volume":"1","author":"Hadley","year":"2022","journal-title":"Nat. Rev. Psychol"},{"key":"B39","doi-asserted-by":"crossref","first-page":"336","DOI":"10.18653\/v1\/2022.sigdial-1.33","article-title":"\u201c\u201cdo you follow me?\u201d: a survey of recent approaches in dialogue state tracking,\u201d","volume-title":"Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue","author":"Jacqmin","year":"2022"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.188","article-title":"Inferring implicit relations in complex questions with language models","author":"Katz","year":"2022","journal-title":"arXiv"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.5334\/johd.168","article-title":"The weights task dataset: a multimodal dataset of collaboration in a situated task","author":"Khebour","year":"2023","journal-title":"J. Open Human. Data"},{"key":"B42","first-page":"3587","article-title":"\u201cCommon ground tracking in multimodal dialogue,\u201d","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Khebour","year":""},{"key":"B43","first-page":"1","article-title":"\u201cThe CODI-CRAC 2021 shared task on anaphora, bridging, and discourse deixis in dialogue,\u201d","author":"Khosla","year":"2021","journal-title":"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue"},{"key":"B44","first-page":"44","article-title":"\u201cGenerating a novel dataset of multimodal referring expressions,\u201d","author":"Krishnaswamy","year":"2019","journal-title":"Proceedings of the 13th International Conference on Computational Semantics"},{"key":"B45","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1007\/978-3-642-11694-0_8","article-title":"\u201cSituated dialogue processing for human-robot interaction,\u201d","volume-title":"Cognitive Systems","author":"Kruijff","year":"2010"},{"key":"B46","doi-asserted-by":"crossref","first-page":"8730","DOI":"10.18653\/v1\/2020.acl-main.771","article-title":"\u201cNILE: natural language inference with faithful natural language explanations,\u201d","author":"Kumar","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"},{"key":"B47","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1162\/tacl_a_00384","article-title":"Dialogue state tracking with incremental reasoning","volume":"9","author":"Liao","year":"2021","journal-title":"Transact. Assoc. Comp. Linguist"},{"key":"B48","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1145\/3240508.3240605","article-title":"\u201cKnowledge-aware multimodal dialogue systems,\u201d","volume-title":"Proceedings of the 26th ACM International Conference on Multimedia","author":"Liao","year":"2018"},{"key":"B49","first-page":"1274","article-title":"\u201cCommon sense beyond English: evaluating and improving multilingual language models for commonsense reasoning,\u201d","author":"Lin","year":"2021","journal-title":"em Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)"},{"key":"B50","first-page":"988","article-title":"\u201cImproving neural story generation by targeted common sense grounding,\u201d","author":"Mao","year":"2019","journal-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)"},{"key":"B51","first-page":"1","article-title":"Paraphrasing questions using given and new information","volume":"9","author":"McKeown","year":"1983","journal-title":"Am. J. Comp. Linguist"},{"key":"B52","doi-asserted-by":"crossref","first-page":"9737","DOI":"10.18653\/v1\/2022.emnlp-main.660","article-title":"\u201cLeveraging QA datasets to improve generative data augmentation,\u201d","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Mekala","year":"2022"},{"key":"B53","unstructured":"M\u00fcller\n              M.-C.\n            \n          \n          T\u00fcbingen, Germany\n          Universit\u00e4t T\u00fcbingen\n          Fully Automatic Resolution of \u2018it'\n          \n          2008"},{"key":"B54","doi-asserted-by":"crossref","DOI":"10.3115\/991813.991851","article-title":"\u201cOn a semantic model for multi-lingual paraphrasing,\u201d","volume-title":"Coling 1982: Proceedings of the Ninth International Conference on Computational Linguistics","author":"Muraki","year":"1982"},{"key":"B55","doi-asserted-by":"crossref","DOI":"10.1145\/3206505.3206607","article-title":"\u201cEnvisioning conversation: toward understanding and augmenting common ground,\u201d","volume-title":"Proceedings of the 2018 International Conference on Advanced Visual Interfaces, AVI '18","author":"Nishida","year":"2018"},{"key":"B56","unstructured":"\u201cSemantically enriched text generation for QA through dense paraphrasing,\u201d\n          \n          279\n          286\n          \n            \n              Obiso\n              T.\n            \n            \n              Ye\n              B.\n            \n            \n              Rim\n              K.\n            \n            \n              Pustejovsky\n              J.\n            \n          \n          Proceedings of the 7th International Conference on Natural Language and Speech Processing (ICNLSP 2024)\n          \n          2024"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.13176","article-title":"Emergence of hierarchical reference systems in multi-agent communication","author":"Ohmer","year":"2022","journal-title":"arXiv"},{"journal-title":"Gpt-4 Technical Report","year":"2024","author":"Achiam","key":"B58"},{"journal-title":"Gpt-4 Technical Report","year":"2023","key":"B59"},{"key":"B60","doi-asserted-by":"crossref","first-page":"6137","DOI":"10.18653\/v1\/2024.naacl-long.341","article-title":"\u201cDialogBench: evaluating LLMs as human-like dialogue systems,\u201d","author":"Ou","year":"2024","journal-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)"},{"key":"B61","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-67149-9","volume-title":"Neighborhood Semantics for Modal Logic","author":"Pacuit","year":"2017"},{"key":"B62","doi-asserted-by":"crossref","first-page":"2249","DOI":"10.18653\/v1\/D16-1244","article-title":"\u201cA decomposable attention model for natural language inference,\u201d","author":"Parikh","year":"2016","journal-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing"},{"key":"B63","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.knosys.2014.06.011","article-title":"Emosenticspace: a novel framework for affective common-sense reasoning","volume":"69","author":"Poria","year":"2014","journal-title":"Knowl. Based Syst"},{"key":"B64","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3225.001.0001","volume-title":"The Generative Lexicon","author":"Pustejovsky","year":"1995"},{"key":"B65","first-page":"4606","article-title":"\u201cVoxML: A visualization modeling language,\u201d","author":"Pustejovsky","year":"2016","journal-title":"Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)"},{"key":"B66","first-page":"12448","article-title":"\u201cThe coreference under transformation labeling dataset: entity tracking in procedural texts using event models,\u201d","author":"Rim","year":"2023","journal-title":"Findings of the Association for Computational Linguistics: ACL 2023"},{"key":"B67","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11331","article-title":"\u201cTowards building large scale multimodal domain-aware conversation systems,\u201d","author":"Saha","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence, Vol"},{"key":"B68","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1609\/aimag.v32i4.2381","article-title":"Toward humanlike task-based dialogue processing for human robot interaction","volume":"32","author":"Scheutz","year":"2011","journal-title":"Ai Mag"},{"key":"B69","first-page":"255","article-title":"\u201cExploiting cloze-questions for few-shot text classification and natural language inference,\u201d","author":"Schick","year":"2021","journal-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume"},{"key":"B70","first-page":"1","article-title":"A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on danish commons","volume":"5","author":"S\u00f8rensen","year":"1948","journal-title":"Biologiske Skrifter"},{"key":"B71","doi-asserted-by":"publisher","first-page":"103672","DOI":"10.1016\/j.compedu.2019.103672","article-title":"Towards a generalized competency model of collaborative problem solving","volume":"143","author":"Sun","year":"2020","journal-title":"Comput. Educ"},{"key":"B72","article-title":"\u201cCross-modal embeddings for video and audio retrieval,\u201d","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","author":"Sur\u00eds","year":"2018"},{"key":"B73","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.09288","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"key":"B74","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/978-981-10-8438-6_6","article-title":"\u201cSemantic refinement gru-based neural language generation for spoken dialogue systems,\u201d","volume-title":"Computational Linguistics: 15th International Conference of the Pacific Association for Computational Linguistics, PACLING 2017, Yangon, Myanmar, August 16-18, 2017, Revised Selected Papers 15","author":"Tran","year":"2018"},{"volume-title":"A Computational Theory of Grounding in Natural Language Conversation","year":"1994","author":"Traum","key":"B75"},{"key":"B76","first-page":"1244","article-title":"\u201cSemEval-2022 task 9: R2VQ - competence-based multimodal question answering,\u201d","author":"Tu","year":"","journal-title":"Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)"},{"key":"B77","first-page":"7746","article-title":"\u201cGLAMR: augmenting AMR with GL-VerbNet event structure,\u201d","author":"Tu","year":"2024","journal-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)"},{"key":"B78","first-page":"39","article-title":"\u201cDense paraphrasing for textual enrichment,\u201d","author":"Tu","year":"2023","journal-title":"Proceedings of the 15th International Conference on Computational Semantics"},{"key":"B79","first-page":"1521","article-title":"\u201cCompetence-based question generation,\u201d","author":"Tu","year":"","journal-title":"Proceedings of the 29th International Conference on Computational Linguistics"},{"key":"B80","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.apal.2013.07.007","article-title":"Evidence and plausibility in neighborhood structures","volume":"165","author":"van Benthem","year":"2014","journal-title":"Ann. Pure Appl. Logic"},{"key":"B81","article-title":"A neural conversational model","author":"Vinyals","year":"2015","journal-title":"arXiv"},{"key":"B82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.679","article-title":"Conqrr: Conversational query rewriting for retrieval with reinforcement learning","author":"Wu","year":"2021","journal-title":"arXiv"},{"key":"B83","unstructured":"\u201cInterpreting logical metonymy through dense paraphrasing,\u201d\n          \n          \n            \n              Ye\n              B.\n            \n            \n              Tu\n              J.\n            \n            \n              Jezek\n              E.\n            \n            \n              Pustejovsky\n              J.\n            \n          \n          Toronto, ON\n          Proceedings of the 44th Annual Meeting of the Cognitive Science Society, CogSci 2022\n          \n          2022"},{"key":"B84","doi-asserted-by":"crossref","first-page":"1157","DOI":"10.18653\/v1\/2022.emnlp-main.76","article-title":"\u201cMetaASSIST: robust dialogue state tracking with meta learning,\u201d","author":"Ye","year":"2022","journal-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing"},{"key":"B85","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.18013","article-title":"A survey on recent advances in llm-based multi-turn dialogue systems","author":"Yi","year":"2024","journal-title":"arXiv"},{"key":"B86","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403","article-title":"A survey on multimodal large language models","author":"Yin","year":"2023","journal-title":"arXiv"},{"key":"B87","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.18653\/v1\/2022.semeval-1.177","article-title":"\u201cHIT&QMUL at SemEval-2022 task 9: Label-enclosed generative question answering (LEG-QA),\u201d","author":"Zhai","year":"2022","journal-title":"Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)"},{"key":"B88","doi-asserted-by":"crossref","first-page":"9","DOI":"10.18653\/v1\/2023.nlrse-1.2","article-title":"\u201cExploring the curious case of code prompts,\u201d","author":"Zhang","year":"2023","journal-title":"Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE)"},{"key":"B89","first-page":"4736","article-title":"\u201cRetrieving multimodal information for augmented generation: a survey,\u201d","author":"Zhao","year":"2023","journal-title":"Findings of the Association for Computational Linguistics: EMNLP 2023"},{"key":"B90","article-title":"\u201cContext-aware natural language generation for spoken dialogue systems,\u201d","author":"Zhou","year":"2016","journal-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 2032-2041"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1479905\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T06:25:23Z","timestamp":1734589523000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1479905\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,19]]},"references-count":90,"alternative-id":["10.3389\/frai.2024.1479905"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1479905","relation":{},"ISSN":["2624-8212"],"issn-type":[{"type":"electronic","value":"2624-8212"}],"subject":[],"published":{"date-parts":[[2024,12,19]]},"article-number":"1479905"}}