Summary of the paper

Title Can Syntactic and Logical Graphs help Word Sense Disambiguation?
Authors Amal Zouaq, Michel Gagnon and Benoit Ozell
Abstract This paper presents a word sense disambiguation (WSD) approach based onsyntactic and logical representations. The objective here is to run a number ofexperiments to compare standard contexts (word windows, sentence windows) withcontexts provided by a dependency parser (syntactic context) and a logicalanalyzer (logico-semantic context). The approach presented here relies on adependency grammar for the syntactic representations. We also use a patternknowledge base over the syntactic dependencies to extract flat predicativelogical representations. These representations (syntactic and logical) are thenused to build context vectors that are exploited in the WSD process. Variousstate-of-the-art algorithms including Simplified Lesk, Banerjee and Pedersenand frequency of co-occurrences are tested with these syntactic and logicalcontexts. Preliminary results show that defining context vectors based on thesefeatures may improve WSD by comparison with classical word and sentence contextwindows. However, future experiments are needed to provide more evidence overthese issues.
Language Text mining
Topics Word Sense Disambiguation, Semantics, Text mining
Full paper Can Syntactic and Logical Graphs help Word Sense Disambiguation?
Bibtex @InProceedings{ZOUAQ10.374,
  author = {Amal Zouaq, Michel Gagnon and Benoit Ozell},
  title = {Can Syntactic and Logical Graphs help Word Sense Disambiguation?},
  booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)},
  year = {2010},
  month = {may},
  date = {19-21},
  address = {Valletta, Malta},
  editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {2-9517408-6-7},
  language = {english}
 }
Powered by ELDA © 2010 ELDA/ELRA