Latent Semantic Analysis for Text Segmentation

Freddy Y. Y. Choi, Peter Wiemer-Hastings, Johanna Moore

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This paper describes a method for linear text segmentation that is more accurate or at least as accurate as state-of-the-art methods (Utiyama and Isahara, 2001; Choi, 2000a). Inter-sentence similarity is estimated by latent semantic analysis (LSA). Boundary locations are discovered by divisive clustering. Test results show LSA is a more accurate similarity measure than the cosine metric (van Rijsbergen, 1979).
Original languageEnglish
Title of host publicationProceedings of the Conference on Empirical Methods in Natural Language Processing
Number of pages9
Publication statusPublished - 2001


Dive into the research topics of 'Latent Semantic Analysis for Text Segmentation'. Together they form a unique fingerprint.

Cite this