BP-Seg: A graphical model approach to unsupervised and non-contiguous text segmentation using belief propagation

ACL ARR 2025 May Submission1617 Authors

Abstract: Text segmentation based on the semantic meaning of sentences is a fundamental task with broad utility in many downstream applications. In this paper, we propose a graphical model-based unsupervised learning approach, named BP-Seg for efficient text segmentation. Our method not only considers local coherence, capturing the intuition that adjacent sentences are often more related, but also effectively groups sentences that are distant in the text yet semantically similar. This is achieved through belief propagation on the carefully constructed graphical models. Experimental results on both an illustrative example and a dataset with long-form documents demonstrate that our method performs favorably compared to competing approaches.

Paper Type: Short

Research Area: Machine Learning for NLP

Research Area Keywords: graph-based methods, graphical models

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Submission Number: 1617