Skip to Main content Skip to Navigation
Conference papers

Enriching a Text by Semantic Disambiguation for Information Extraction

Abstract : External linguistic resources have been used for a very long time in information extraction. These methods enrich a document with data that are semantically equivalent, in order to improve recall. For instance, some of these methods use synonym dictionaries. These dictionaries enrich a sentence with words that have a similar meaning. However, these methods present some serious drawbacks, since words are usually synonyms only in restricted contexts. The method we propose here consists of using word sense disambiguation rules (WSD) to restrict the selection of synonyms to only these that match a specific syntactico-semantic context. We show how WSD rules are built and how information extraction techniques can benefit from the application of these rules.
Complete list of metadata
Contributor : Bernard Jacquemin Connect in order to contact the contributor
Submitted on : Monday, June 20, 2005 - 11:20:17 AM
Last modification on : Monday, May 25, 2020 - 3:17:15 AM
Long-term archiving on: : Thursday, April 1, 2010 - 8:11:25 PM


Distributed under a Creative Commons Attribution - NonCommercial - ShareAlike 4.0 International License






Bernard Jacquemin, Caroline Brun, Claude Roux. Enriching a Text by Semantic Disambiguation for Information Extraction. Proceeding of the Workshop on Using Semantics for Information Retrieval and Filtering: State of the Art and Future Research (LREC 2002), May 2002, Las Palmas, Canary Islands, Spain. pp.45-51. ⟨halshs-00003968⟩



Record views


Files downloads