Summary of the paper

Title Evaluating the Impact of Some Linguistic Information on the Performances of a Similarity-based and Translation-oriented Word-Sense Disambiguation Method
Authors Myriam Rakho and Matthieu Constant
Abstract In this article, we present an experiment of linguistic parameter tuning in therepresentation of the semantic space of polysemous words. We evaluatequantitatively the influence of some basic linguistic knowledge (lemmas,multi-word expressions, grammatical tags and syntactic relations) on theperformances of a similarity-based Word-Sense disambiguation method. Thequestion we try to answer, by this experiment, is which kinds of linguisticknowledge are most useful for the semantic disambiguation of polysemous words,in a multilingual framework. The experiment is about 20 French polysemous words(16 nouns and 4 verbs) and we make use of the French-English part of thesentence-aligned EuroParl Corpus for training and testing. Our results show astrong correlation between the system accuracy and the degree of precision ofthe linguistic features used, particularly the syntactic dependency relations.Furthermore, the lemma-based approach absolutely outperforms the wordform-based approach. The best accuracy achieved by our system amounts to 90%.
Language MultiWord Expressions & Collocations
Topics Word Sense Disambiguation, Statistical and machine learning methods, MultiWord Expressions & Collocations
Full paper Evaluating the Impact of Some Linguistic Information on the Performances of a Similarity-based and Translation-oriented Word-Sense Disambiguation Method
Bibtex @InProceedings{RAKHO10.687,
  author = {Myriam Rakho and Matthieu Constant},
  title = {Evaluating the Impact of Some Linguistic Information on the Performances of a Similarity-based and Translation-oriented Word-Sense Disambiguation Method},
  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