Normalization and paraphrasing using symbolic methods
Caroline Brun, Caroline Hagege
We describe ongoing work in information extraction considered as a text normalization task.
The normalized representation is a mean to detect paraphrases in texts. Normalization and paraphrase
detection tasks are built on top of a robust analyzer for English and are exclusively achieved using symbolic
methods. Both rules and information extraction rules are expressed within the same formalism and are
developed in an integrated way. The experiment we describe in the paper is evaluated and presents
ACL: Second International workshop on Paraphrasing, Paraphrase Acquisition and Applications, Sapporo, Japan, July 7-12, 2003.