mlsanityData to 7 Oct 2026

Structural Characterization for Dialogue Disentanglement

arXiv 2110.08018 ↗First posted 15 Oct 2021cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Tangled multi-party dialogue contexts lead to challenges for dialogue reading comprehension, where multiple dialogue threads flow simultaneously within a common dialogue record, increasing difficulties in understanding the dialogue history for both human and machine. Previous studies mainly focus on utterance encoding methods with carefully designed features but pay inadequate attention to characteristic features of the structure of dialogues. We specially take structure factors into account and design a novel model for dialogue disentangling. Based on the fact that dialogues are constructed on successive participation and interactions between speakers, we model structural information of dialogues in two aspects: 1)speaker property that indicates whom a message is from, and 2) reference dependency that shows whom a message may refer to. The proposed method achieves new state-of-the-art on the Ubuntu IRC benchmark dataset and contributes to dialogue-related comprehension.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 32 of its 66 references that are in the map. First posted on arXiv 15 Oct 2021.

Builds on

32 of 66 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  5. 2015Pointer Networkscited by 882
  6. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  7. 2018CoQA: A Conversational Question Answering Challengecited by 674
  8. 2018QuAC : Question Answering in Contextcited by 379
  9. 2018Graph Convolutional Networks for Text Classificationcited by 345
  10. 2016A Decomposable Attention Model for Natural Language Inferencecited by 214
  11. 2016Enhanced LSTM for Natural Language Inferencecited by 199
  12. 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
20 more
  1. 2019DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehensioncited by 156
  2. 2020You Impress Me: Dialogue Generation via Mutual Persona Perceptioncited by 85
  3. 2020Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbotscited by 73
  4. 2021DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversationscited by 71
  5. 2018Modeling Multi-turn Conversation with Deep Utterance Aggregationcited by 65
  6. 2020Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structurecited by 60
  7. 2018A Deep Sequential Model for Discourse Parsing on Multi-Party Dialoguescited by 38
  8. 2020Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialoguecited by 26
  9. 2020Response Selection for Multi-Party Conversations with Dynamic Topic Trackingcited by 26
  10. 2020Multi-turn Response Selection using Dialogue Dependency Relationscited by 23
  11. 2021Better Feature Integration for Named Entity Recognitioncited by 22
  12. 2021Structural Pre-training for Dialogue Comprehensioncited by 20
  13. 2019Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformercited by 16
  14. 2021DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehensioncited by 16
  15. 2020Online Conversation Disentanglement with Pointer Networkscited by 14
  16. 2020DDRel: A New Dataset for Interpersonal Relation Classification in Dyadic Dialoguescited by 13
  17. 2021Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehensioncited by 13
  18. 2020DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglementcited by 12
  19. 2021Unsupervised Conversation Disentanglement through Co-Trainingcited by 8
  20. 2021Dialogue Disentanglement in Software Engineering: How Far are We?cited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5; 2024: 1.

7 papers.

  1. 2023EM Pre-training for Multi-party Dialogue Response Generationcited by 7
  2. 2022Conversation Disentanglement with Bi-Level Contrastive Learningcited by 6
  3. 2023Pre-training Multi-party Dialogue Models with Latent Discourse Inferencecited by 4
  4. 2023Dramatic Conversation Disentanglementcited by 2
  5. 2023Revisiting Conversation Discourse for Dialogue Disentanglementcited by 2
  6. 2024Thread Detection and Response Generation using Transformers with Prompt Optimisationcited by 2
  7. 2023Coreference-aware Double-channel Attention Network for Multi-party Dialogue Reading Comprehensioncited by 0