Summary of the paper

Title Homographic Ideogram Understanding Using Contextual Dynamic Network
Authors Jun Okamoto and Shun Ishizaki
Abstract Conventional methods for disambiguation problems have been using statisticalmethods with co-occurrence of words in their contexts. It seems thathuman-beings assign appropriate word senses to the given ambiguous word in thesentence depending on the words which followed the ambiguous word when theycould not disambiguate by using the previous contextual information. In thisresearch, Contextual Dynamic Network Model is developed using the AssociativeConcept Dictionary which includes semantic relations among concepts/words andthe relations can be represented with quantitative distances among them. Inthis model, an interactive activation method is used to identify a word’smeaning on the Contextual Semantic Network where the activation values on thenetwork are calculated using the distances. The proposed method constructsdynamically the Contextual Semantic Network according to the input wordssequentially that appear in the sentence including an ambiguous word.Therefore, in this research, after the model calculates the activation values,if there is little difference between the activation values, it reconstructsthe network depending on the next words in input sentence. The evaluation ofproposed method showed that the accuracy rates are high when ContextualSemantic Network has high density whose node are extended using around theambiguous word.
Language Tools, systems, applications
Topics Word Sense Disambiguation, Ontologies, Tools, systems, applications
Full paper Homographic Ideogram Understanding Using Contextual Dynamic Network
Bibtex @InProceedings{OKAMOTO10.331,
  author = {Jun Okamoto and Shun Ishizaki},
  title = {Homographic Ideogram Understanding Using Contextual Dynamic Network},
  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