{"url":"/task/dialogue-understanding","name":"Dialogue Understanding","slug":"dialogue-understanding","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":79,"papers_with_code":35,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":9,"subtasks":2,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/doc2dial-1","name":"Doc2Dial","full_name":"Doc2Dial: Document-grounded Dialogue","num_papers_in_archive":36},{"url":"/dataset/molweni","name":"Molweni","full_name":"","num_papers_in_archive":29},{"url":"/dataset/prosocialdialog","name":"ProsocialDialog","full_name":"","num_papers_in_archive":13},{"url":"/dataset/mutualfriends","name":"MutualFriends","full_name":"","num_papers_in_archive":7},{"url":"/dataset/diaasq","name":"DiaASQ","full_name":"Conversational Aspect-based Sentiment Quadruple Extraction","num_papers_in_archive":4},{"url":"/dataset/emotional-dialogue-acts","name":"Emotional Dialogue Acts","full_name":"","num_papers_in_archive":3},{"url":"/dataset/wdc-dialogue","name":"WDC-Dialogue","full_name":"","num_papers_in_archive":3},{"url":"/dataset/harry-potter-dialogue-dataset","name":"Harry Potter Dialogue Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/the-mafia-dataset","name":"The Mafia Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/dialogue-safety-prediction","name":"Dialogue Safety Prediction"},{"url":"/task/spoken-language-understanding","name":"Spoken Language Understanding"}],"parent_tasks":[{"url":"/task/dialogue","name":"Dialogue"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":35,"tagged_in_all":79,"items":[{"url":"/paper/unsupervised-abstractive-meeting","title":"Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization","date":"2018-05-14","arxiv_id":"1805.05271","repositories_listed":4,"syntology":null},{"url":"/paper/atco2-corpus-a-large-scale-dataset-for","title":"ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications","date":"2022-11-08","arxiv_id":"2211.04054","repositories_listed":3,"syntology":null},{"url":"/paper/teach-task-driven-embodied-agents-that-chat","title":"TEACh: Task-driven Embodied Agents that Chat","date":"2021-10-01","arxiv_id":"2110.00534","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/190406472","title":"A Repository of Conversational Datasets","date":"2019-04-13","arxiv_id":"1904.06472","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/utterance-level-dialogue-understanding-an","title":"Utterance-level Dialogue Understanding: An Empirical Study","date":"2020-09-29","arxiv_id":"2009.13902","repositories_listed":2,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/masking-orchestration-multi-task-pretraining","title":"Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning","date":"2020-02-27","arxiv_id":"2003.04994","repositories_listed":2,"syntology":null},{"url":"/paper/a-zero-shot-open-vocabulary-pipeline-for","title":"A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding","date":"2024-09-24","arxiv_id":"2409.15861","repositories_listed":1,"syntology":null},{"url":"/paper/visualizing-dialogues-enhancing-image","title":"Visualizing Dialogues: Enhancing Image Selection through Dialogue Understanding with Large Language Models","date":"2024-07-04","arxiv_id":"2407.03615","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-machine-generated-rationales-to","title":"Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations","date":"2024-06-27","arxiv_id":"2406.19545","repositories_listed":1,"syntology":null},{"url":"/paper/dialsim-a-real-time-simulator-for-evaluating","title":"DialSim: A Real-Time Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents","date":"2024-06-19","arxiv_id":"2406.13144","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":11}},{"url":"/paper/sd-eval-a-benchmark-dataset-for-spoken","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","date":"2024-06-19","arxiv_id":"2406.13340","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/mathchat-benchmarking-mathematical-reasoning","title":"MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions","date":"2024-05-29","arxiv_id":"2405.19444","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/promptcblue-a-chinese-prompt-tuning-benchmark","title":"PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain","date":"2023-10-22","arxiv_id":"2310.14151","repositories_listed":1,"syntology":null},{"url":"/paper/from-multilingual-complexity-to-emotional","title":"From Multilingual Complexity to Emotional Clarity: Leveraging Commonsense to Unveil Emotions in Code-Mixed Dialogues","date":"2023-10-19","arxiv_id":"2310.13080","repositories_listed":1,"syntology":null},{"url":"/paper/revisit-input-perturbation-problems-for-llms","title":"Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task","date":"2023-10-10","arxiv_id":"2310.06504","repositories_listed":1,"syntology":null},{"url":"/paper/vstar-a-video-grounded-dialogue-dataset-for","title":"VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions","date":"2023-05-30","arxiv_id":"2305.18756","repositories_listed":1,"syntology":null},{"url":"/paper/medical-dialogue-generation-via-dual-flow","title":"Medical Dialogue Generation via Dual Flow Modeling","date":"2023-05-29","arxiv_id":"2305.18109","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-dialogue-understanding-with-1","title":"Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention","date":"2023-04-29","arxiv_id":"2305.00262","repositories_listed":1,"syntology":null},{"url":"/paper/towards-generalized-and-explainable-long","title":"DialoGen: Generalized Long-Range Context Representation for Dialogue Systems","date":"2022-10-12","arxiv_id":"2210.06282","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-based-pre-training-for-dialogue","title":"Semantic-based Pre-training for Dialogue Understanding","date":"2022-09-19","arxiv_id":"2209.09146","repositories_listed":1,"syntology":null},{"url":"/paper/learning-dialogue-representations-from","title":"Learning Dialogue Representations from Consecutive Utterances","date":"2022-05-26","arxiv_id":"2205.13568","repositories_listed":1,"syntology":null},{"url":"/paper/feta-a-benchmark-for-few-sample-task-transfer","title":"FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue","date":"2022-05-12","arxiv_id":"2205.06262","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/user-centric-conversational-recommendation","title":"User-Centric Conversational Recommendation with Multi-Aspect User Modeling","date":"2022-04-20","arxiv_id":"2204.09263","repositories_listed":1,"syntology":null},{"url":"/paper/a-benchmark-for-automatic-medical","title":"A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets","date":"2022-04-19","arxiv_id":"2204.08997","repositories_listed":1,"syntology":null},{"url":"/paper/csagn-conversational-structure-aware-graph","title":"CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling","date":"2021-09-23","arxiv_id":"2109.11541","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/dialoglm-pre-trained-model-for-long-dialogue","title":"DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization","date":"2021-09-06","arxiv_id":"2109.02492","repositories_listed":1,"syntology":null},{"url":"/paper/m2h2-a-multimodal-multiparty-hindi-dataset","title":"M2H2: A Multimodal Multiparty Hindi Dataset For Humor Recognition in Conversations","date":"2021-08-03","arxiv_id":"2108.01260","repositories_listed":1,"syntology":null},{"url":"/paper/a-structure-self-aware-model-for-discourse","title":"A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semantic-representation-for-dialogue-modeling","title":"Semantic Representation for Dialogue Modeling","date":"2021-05-21","arxiv_id":"2105.10188","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/cread-combined-resolution-of-ellipses-and","title":"CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues","date":"2021-05-20","arxiv_id":"2105.09914","repositories_listed":1,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}