Towards robust context-sensitive sentence alignment for monolingual corpora
View/ Open
Published Version
http://www.aclweb.org/anthology-new/E/E06/E06-1021.pdfMetadata
Show full item recordCitation
Rani Nelken and Stuart M. Shieber. Towards robust context-sensitive sentence alignment for monolingual corpora. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL-06), Trento, Italy, 3-7 April 2006.Abstract
Aligning sentences belonging to comparable monolingual corpora has been suggested as a first step towards training text rewriting algorithms, for tasks such as summarization or paraphrasing. We present here a new monolingual sentence alignment algorithm, combining a sentence-based TF*IDF score, turned into a probability distribution using logistic regression, with a global alignment dynamic programming algorithm. Our approach provides a simpler and more robust solution achieving a substantial improvement in accuracy over existing systems.Terms of Use
This article is made available under the terms and conditions applicable to Other Posted Material, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#LAACitable link to this page
http://nrs.harvard.edu/urn-3:HUL.InstRepos:2252597
Collections
- FAS Scholarly Articles [18292]
Contact administrator regarding this item (to report mistakes or request changes)