# Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring

arXiv: https://arxiv.org/abs/2106.06719 · HTML: https://mlsanity.com/paper/2106.06719/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 12 Jun 2021.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Key-Value Retrieval Networks for Task-Oriented Dialogue](https://mlsanity.com/paper/1705.05414/) (2017)
- [Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks](https://mlsanity.com/paper/2010.08240/) (2020)
- [doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset](https://mlsanity.com/paper/2011.06623/) (2020)
- [Text Segmentation as a Supervised Learning Task](https://mlsanity.com/paper/1803.09337/) (2018)
- [GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems](https://mlsanity.com/paper/2010.03994/) (2020)
- [Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph](https://mlsanity.com/paper/2009.11692/) (2020)
- [SECTOR: A Neural Model for Coherent Topic Segmentation and Classification](https://mlsanity.com/paper/1902.04793/) (2019)
- [Topic-Aware Multi-turn Dialogue Modeling](https://mlsanity.com/paper/2009.12539/) (2020)
- [NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation](https://mlsanity.com/paper/2103.02548/) (2021)
- [Attention-based Neural Text Segmentation](https://mlsanity.com/paper/1808.09935/) (2018)
- [Response Selection for Multi-Party Conversations with Dynamic Topic Tracking](https://mlsanity.com/paper/2010.07785/) (2020)
- [Improving Context Modeling in Neural Topic Segmentation](https://mlsanity.com/paper/2010.03138/) (2020)
- [A Cross-Domain Transferable Neural Coherence Model](https://mlsanity.com/paper/1905.11912/) (2019)
- [Dialogue Session Segmentation by Embedding-Enhanced TextTiling](https://mlsanity.com/paper/1610.03955/) (2016)
- [Is this Dialogue Coherent? Learning from Dialogue Acts and Entities](https://mlsanity.com/paper/2006.10157/) (2020)
- [Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths](https://mlsanity.com/paper/2009.11753/) (2020)
- [A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph](https://mlsanity.com/paper/2010.05511/) (2020)

## Built on by (most cited first, 29 of 29)

- [MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents](https://mlsanity.com/paper/2109.12595/) (2021)
- [PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation](https://mlsanity.com/paper/2203.09100/) (2022)
- [Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study](https://mlsanity.com/paper/2305.08391/) (2023)
- [Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling](https://mlsanity.com/paper/2310.11772/) (2023)
- [Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation](https://mlsanity.com/paper/2305.02747/) (2023)
- [VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions](https://mlsanity.com/paper/2305.18756/) (2023)
- [SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation](https://mlsanity.com/paper/2305.08371/) (2023)
- [Abstractive Meeting Summarization: A Survey](https://mlsanity.com/paper/2208.04163/) (2022)
- [S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs](https://mlsanity.com/paper/2309.08827/) (2023)
- [Structured Summarization: Unified Text Segmentation and Segment Labeling as a Generation Task](https://mlsanity.com/paper/2209.13759/) (2022)
- [Multi-Granularity Prompts for Topic Shift Detection in Dialogue](https://mlsanity.com/paper/2305.14006/) (2023)
- [Improving Topic Segmentation by Injecting Discourse Dependencies](https://mlsanity.com/paper/2209.08626/) (2022)
- [An Empirical Study of Topic Transition in Dialogue](https://mlsanity.com/paper/2111.14188/) (2021)
- [Unsupervised Dialogue Topic Segmentation in Hyperdimensional Space](https://mlsanity.com/paper/2308.10464/) (2023)
- [Unsupervised Mutual Learning of Discourse Parsing and Topic Segmentation in Dialogue](https://mlsanity.com/paper/2405.19799/) (2024)
- [A Novel LLM-based Two-stage Summarization Approach for Long Dialogues](https://mlsanity.com/paper/2410.06520/) (2024)
- [Leveraging Collection-Wide Similarities for Unsupervised Document Structure Extraction](https://mlsanity.com/paper/2402.13906/) (2024)
- [MoviePuzzle: Visual Narrative Reasoning through Multimodal Order Learning](https://mlsanity.com/paper/2306.02252/) (2023)
- [Multimodal Fusion and Coherence Modeling for Video Topic Segmentation](https://mlsanity.com/paper/2408.00365/) (2024)
- [BoundRL: Efficient Structured Text Segmentation through Reinforced Boundary Generation](https://mlsanity.com/paper/2510.20151/) (2025)
- [When F1 Fails: Granularity-Aware Evaluation for Dialogue Topic Segmentation](https://mlsanity.com/paper/2512.17083/) (2025)
- [Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension](https://mlsanity.com/paper/2210.14456/) (2022)
- [Tracing Influence at Scale: A Contrastive Learning Approach to Linking Public Comments and Regulator Responses](https://mlsanity.com/paper/2311.14871/) (2023)
- [Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation](https://mlsanity.com/paper/2312.00220/) (2023)
- [With a Little Help from my (Linguistic) Friends: Topic Segmentation of Multi-party Casual Conversations](https://mlsanity.com/paper/2402.02837/) (2024)
- [From Words to Wisdom: Discourse Annotation and Baseline Models for Student Dialogue Understanding](https://mlsanity.com/paper/2511.20547/) (2025)
- [CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generation](https://mlsanity.com/paper/2512.21715/) (2025)
- [Codebook-Injected Dialogue Segmentation for Multi-Utterance Constructs Annotation: LLM-Assisted and Gold-Label-Free Evaluation](https://mlsanity.com/paper/2601.12061/) (2026)
- [CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentation](https://mlsanity.com/paper/2605.30668/) (2026)

## Abstract (arXiv)

Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. In this work, we address this limitation by leveraging supervisory signals from the utterance-pair coherence scoring task. First, we present a simple yet effective strategy to generate a training corpus for utterance-pair coherence scoring. Then, we train a BERT-based neural utterance-pair coherence model with the obtained training corpus. Finally, such model is used to measure the topical relevance between utterances, acting as the basis of the segmentation inference. Experiments on three public datasets in English and Chinese demonstrate that our proposal outperforms the state-of-the-art baselines.