RECORD
Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring
Computation and Language · Submitted 12 Jun 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experiments on three public datasets in English and Chinese demonstrate that our proposal outperforms the state-of-the-art baselines.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Dialogue topic segmentation is critical in several dialogue modeling problems. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. | gap 0.90 | 0.06 | 0.02 | asserted 1.00 |
| s2 | In this work, we address this limitation by leveraging supervisory signals from the utterance-pair coherence scoring task. | contribution 0.92 | 0.76 | 0.06 | asserted 0.94 |
| s3 | First, we present a simple yet effective strategy to generate a training corpus for utterance-pair coherence scoring. | method 0.93 | 0.95 | 0.02 | asserted 0.98 |
| s4 | Then, we train a BERT-based neural utterance-pair coherence model with the obtained training corpus. | method 0.99 | 0.96 | 0.03 | asserted 0.98 |
| s5 | Finally, such model is used to measure the topical relevance between utterances, acting as the basis of the segmentation inference. | method 1.00 | 0.88 | 0.06 | asserted 1.00 |
| s6 | Experiments on three public datasets in English and Chinese demonstrate that our proposal outperforms the state-of-the-art baselines. | result 1.00 | 0.96 | 0.88 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
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.
Human review
How the literature uses it
3 arXiv papers cite this in 8 sentences
Papers citing it · 5 sentences without a confident label
Cites it as background 2 papers
-
In low-resource (or no-resource) settings, one can proceed without supervision, as has been done traditionally [ref] .
Structured Summarization: Unified Text Segmentation and Segment Labeling as a Generation Task · Background: Text Segmentation and Segment Labeling · 0.97
-
For instance, [ref] aims to enhance coherence scoring by training on diverse utterance pairs and defining relative scores.
A Novel LLM-based Two-stage Summarization Approach for Long Dialogues · Unsupervised Topic Segmentation · 0.85
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.