mlsanityData to 7 Oct 2026

Improving Multi-turn Dialogue Modelling with Utterance ReWriter

arXiv 1906.07004 ↗First posted 14 Jun 2019cs.CL cs.AIcited by 57

Not on the map. Why?

Abstract (arXiv)

Recent research has made impressive progress in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information omission in our daily conversation, making it hard for machines to understand the real intention. In this paper, we propose rewriting the human utterance as a pre-process to help multi-turn dialgoue modelling. Each utterance is first rewritten to recover all coreferred and omitted information. The next processing steps are then performed based on the rewritten utterance. To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network. We show the proposed architecture achieves remarkably good performance on the utterance rewriting task. The trained utterance rewriter can be easily integrated into online chatbots and brings general improvement over different domains.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 14; 2023: 13; 2024: 6; 2025: 9; 2026: 6.

57 papers.

Sort:

By area:

  1. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  2. 2024CodeR: Issue Resolving with Multi-Agent and Task Graphscited by 89
  3. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 56
  4. 2024Can Large Language Models Understand Context?cited by 26
  5. 2025Adaptive Social Learning via Mode Policy Optimization for Language Agentscited by 15
  6. 2026Benchmarking LLM Tool-Use in the Wildcited by 15
  7. 2023ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Humancited by 14
  8. 2021CREAD: Combined Resolution of Ellipses and Anaphora in Dialoguescited by 13
  9. 2022Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generationcited by 9
  10. 2022UniDU: Towards A Unified Generative Dialogue Understanding Frameworkcited by 9
  11. 2023A Survey on Zero Pronoun Translationcited by 9
  12. 2023Mining Clues from Incomplete Utterance: A Query-enhanced Network for Incomplete Utterance Rewritingcited by 9
38 more
  1. 2025C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversationscited by 9
  2. 2021Conversational Semantic Role Labelingcited by 8
  3. 2023Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understandingcited by 8
  4. 2021Towards Standard Criteria for human evaluation of Chatbots: A Surveycited by 6
  5. 2022McQueen: a Benchmark for Multimodal Conversational Query Rewritecited by 6
  6. 2021Conversational Query Rewriting with Self-supervised Learningcited by 5
  7. 2022Hierarchical Context Tagging for Utterance Rewritingcited by 4
  8. 2022Improving Bot Response Contradiction Detection via Utterance Rewritingcited by 4
  9. 2025C3-Bench: The Things Real Disturbing LLM based Agent in Multi-Taskingcited by 4
  10. 2022Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AIcited by 3
  11. 2022A General Contextualized Rewriting Framework for Text Summarizationcited by 3
  12. 2022PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstandingcited by 3
  13. 2023KG-ECO: Knowledge Graph Enhanced Entity Correction for Query Rewritingcited by 3
  14. 2021A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational Speechcited by 2
  15. 2022Self-Attention for Incomplete Utterance Rewritingcited by 2
  16. 2022What Did You Say? Task-Oriented Dialog Datasets Are Not Conversational!?cited by 2
  17. 2022IRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response Selectioncited by 2
  18. 2023Incomplete Utterance Rewriting as Sequential Greedy Taggingcited by 2
  19. 2023Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewritingcited by 2
  20. 2025Freeze and Reveal: Exposing Modality Bias in Vision-Language Modelscited by 2
  21. 2022Utterance Rewriting with Contrastive Learning in Multi-turn Dialoguecited by 1
  22. 2023Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehensioncited by 1
  23. 2023QURG: Question Rewriting Guided Context-Dependent Text-to-SQL Semantic Parsingcited by 1
  24. 2023On the Robustness of Question Rewriting Systems to Questions of Varying Hardnesscited by 1
  25. 2025Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentationcited by 1
  26. 2026HiMeS: Hippocampus-inspired Memory System for Personalized AI Assistantscited by 1
  27. 2026MedAidDialog: A Multilingual Multi-Turn Medical Dialogue Dataset for Accessible Healthcarecited by 1
  28. 2026Evaluating Temporal Consistency in Multi-Turn Language Modelscited by 1
  29. 2021Coreference Augmentation for Multi-Domain Task-Oriented Dialogue State Trackingcited by 0
  30. 2021Learning to Ask Conversational Questions by Optimizing Levenshtein Distancecited by 0
  31. 2021Action based Network for Conversation Question Reformulationcited by 0
  32. 2022Zero-shot Cross-lingual Conversational Semantic Role Labelingcited by 0
  33. 2022Meeting Decision Tracker: Making Meeting Minutes with De-Contextualized Utterancescited by 0
  34. 2023Channel-aware Decoupling Network for Multi-turn Dialogue Comprehensioncited by 0
  35. 2023Friend-training: Learning from Models of Different but Related Taskscited by 0
  36. 20235IDER: Unified Query Rewriting for Steering, Intent Carryover, Disfluencies, Entity Carryover and Repaircited by 0
  37. 2024Making a Long Story Short in Conversation Modelingcited by 0
  38. 2024CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewritecited by 0

50 most cited of 57 All 57 (JSON)