A Statistical Model for Domain-Independent Text Segmentation
By Masso Utiyama, Hitoshi Isahara. Annual Meeting of the Association for Computational Linguistics, 2001
333 citations recorded by the source corpus.
We propose a statistical method that finds the maximum-probability segmentation of a given text. This method does not require training data because it estimates probabilities from the given text. Therefore, it can be applied to any text in any domain. An experiment showed that the method is more accurate than or at least as accurate as a state-of-the-art text segmentation system.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/4b5a3e77fa3ca6b2cf91cda4e602bdf2ad3e9969
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- K. McKeown
- Mirella Lapata
- Eric Fosler-Lussier
- Michel Galley
- Hongyan Jing
- Mohit Bansal
- Christopher D. Manning
- Jianfeng Gao
Citations in the corpus
- Discourse Segmentation of Multi-Party Conversation (2003, methodology): “It is not clear whether our algorithm is better than (Utiyama and Isahara, 2001) (U00).”
- Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation (2025, unknown): “Examples include TextTiling [14], C99 [15], U00 [16], and BayesSeg [17].”