# CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentation

arXiv: https://arxiv.org/abs/2605.30668 · HTML: https://mlsanity.com/paper/2605.30668/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 57 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue](https://mlsanity.com/paper/2004.06871/) (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)
- [Topic-Aware Multi-turn Dialogue Modeling](https://mlsanity.com/paper/2009.12539/) (2020)
- [Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation](https://mlsanity.com/paper/2001.00891/) (2020)
- [Unsupervised Topic Segmentation of Meetings with BERT Embeddings](https://mlsanity.com/paper/2106.12978/) (2021)
- [OTTers: One-turn Topic Transitions for Open-Domain Dialogue](https://mlsanity.com/paper/2105.13710/) (2021)
- [Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring](https://mlsanity.com/paper/2106.06719/) (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)
- [Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study](https://mlsanity.com/paper/2305.08391/) (2023)
- [TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling](https://mlsanity.com/paper/2109.04562/) (2021)
- [Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence](https://mlsanity.com/paper/2110.07160/) (2021)
- [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)
- [Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation](https://mlsanity.com/paper/2305.02747/) (2023)
- [SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation](https://mlsanity.com/paper/2305.08371/) (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)
- [Multi-turn Dialogue Comprehension from a Topic-aware Perspective](https://mlsanity.com/paper/2309.09666/) (2023)
- [MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs](https://mlsanity.com/paper/2403.05814/) (2024)
- [Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation](https://mlsanity.com/paper/2505.21033/) (2025)
- [Unsupervised Mutual Learning of Discourse Parsing and Topic Segmentation in Dialogue](https://mlsanity.com/paper/2405.19799/) (2024)
- [An Unsupervised Dialogue Topic Segmentation Model Based on Utterance Rewriting](https://mlsanity.com/paper/2409.07672/) (2024)

## Abstract (arXiv)

Dialogue topic segmentation is critical in many human-AI collaborative applications which requires identifying heterogeneous boundary cues, including lexical transitions near utterance edges and semantic discontinuities across utterances. Existing utterance models often dilute these local lexical signals. We propose CobSeg, a novel multi-branch architecture that separates coherence-level semantic continuity from lexical boundary transitions and recovers both through directional boundary prediction. CobSeg further uses boundary informativeness weighting to emphasize high-utility utterance positions, and incorporates a corpus-derived topic coherence cue with learned combination weights. While CobSeg is evaluated as a compact trainable segmenter under supervised gold-boundary training and a pseudo-label setting with automatically induced boundaries, it performs enhanced boundary prediction without LLM calls during inference. Across five benchmarks, it improves Pk and Wd particularly when local lexical cues are prominent: under gold supervision, it reduces Pk by 0.7 points and Wd by 0.6 points on VHF, and reaches Pk of 1.0 on DialSeg711; with induced boundaries, it reduces Pk by 14.8 points on VHF, by 1.5 points on DialSeg711, and by 1.1 points on TIAGE, outperforming prior non-LLM approaches.