mlsanityData to 7 Oct 2026

Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation

arXiv 2305.02747 ↗First posted 4 May 2023cs.CL cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Dialogue Topic Segmentation (DTS) plays an essential role in a variety of dialogue modeling tasks. Previous DTS methods either focus on semantic similarity or dialogue coherence to assess topic similarity for unsupervised dialogue segmentation. However, the topic similarity cannot be fully identified via semantic similarity or dialogue coherence. In addition, the unlabeled dialogue data, which contains useful clues of utterance relationships, remains underexploited. In this paper, we propose a novel unsupervised DTS framework, which learns topic-aware utterance representations from unlabeled dialogue data through neighboring utterance matching and pseudo-segmentation. Extensive experiments on two benchmark datasets (i.e., DialSeg711 and Doc2Dial) demonstrate that our method significantly outperforms the strong baseline methods. For reproducibility, we provide our code and data at:https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/dial-start.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 4 May 2023.

Builds on

29 of 43 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  4. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  5. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  6. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
  7. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  8. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
  9. 2020Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarizationcited by 72
  10. 2021DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarizationcited by 72
  11. 2022UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognitioncited by 61
  12. 2019Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinementcited by 56
17 more
  1. 2019Evaluating Coherence in Dialogue Systems using Entailmentcited by 53
  2. 2020Topic-Aware Multi-turn Dialogue Modelingcited by 46
  3. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  4. 2021Unsupervised Topic Segmentation of Meetings with BERT Embeddingscited by 30
  5. 2021Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoringcited by 29
  6. 2022Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systemscited by 28
  7. 2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
  8. 2021Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherencecited by 22
  9. 2020Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoderscited by 16
  10. 2020Modeling Topical Relevance for Multi-Turn Dialogue Generationcited by 15
  11. 2022A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slotscited by 13
  12. 2016Dialogue Session Segmentation by Embedding-Enhanced TextTilingcited by 12
  13. 2022CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluationcited by 9
  14. 2023Empathetic Response Generation via Emotion Cause Transition Graphcited by 8
  15. 2022Structured Summarization: Unified Text Segmentation and Segment Labeling as a Generation Taskcited by 6
  16. 2017Learning to Rank Question-Answer Pairs using Hierarchical Recurrent Encoder with Latent Topic Clusteringcited by 3
  17. 2022Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddingscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 4; 2025: 1; 2026: 2.

11 papers.

  1. 2023Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Studycited by 24
  2. 2023UniSA: Unified Generative Framework for Sentiment Analysiscited by 17
  3. 2024The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trendscited by 11
  4. 2023SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentationcited by 10
  5. 2023Self-Explanation Prompting Improves Dialogue Understanding in Large Language Modelscited by 5
  6. 2024MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphscited by 4
  7. 2024Unsupervised Mutual Learning of Discourse Parsing and Topic Segmentation in Dialoguecited by 3
  8. 2024A Novel LLM-based Two-stage Summarization Approach for Long Dialoguescited by 3
  9. 2025CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generationcited by 0
  10. 2026Codebook-Injected Dialogue Segmentation for Multi-Utterance Constructs Annotation: LLM-Assisted and Gold-Label-Free Evaluationcited by 0
  11. 2026CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentationcited by 0