Discourse Segmentation of Multi-Party Conversation

By Michel Galley, K. McKeown, Eric Fosler-Lussier, Hongyan Jing. Annual Meeting of the Association for Computational Linguistics, 2003

422 citations recorded by the source corpus.

We present a domain-independent topic segmentation algorithm for multi-party speech. Our feature-based algorithm combines knowledge about content using a text-based algorithm as a feature and about form using linguistic and acoustic cues about topic shifts extracted from speech. This segmentation algorithm uses automatically induced decision rules to combine the different features. The embedded text-based algorithm builds on lexical cohesion and has performance comparable to state-of-the-art algorithms based on lexical information. A significant error reduction is obtained by combining the two knowledge sources.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/118a331364f30592d12eafe9af8a8c84b59b961c

Citations in the corpus

• LLM-Enhanced Semantic Text Segmentation (2025, unknown): “Depending on the subject area for which segmentation is required, it can be the subject of separate studies [7], for example, whether the text system is used for dialogues, encyclopedic text, or a text-cleaning process or whether the system is supplemented with synthetic data.”