Summary of the paper
| Title | Study of Word Sense Disambiguation System that uses Contextual Features - Approach of Combining Associative Concept Dictionary and Corpus - |
|---|---|
| Authors | Kyota Tsutsumida, Jun Okamoto, Shun Ishizaki, Makoto Nakatsuji, Akimichi Tanaka and Tadasu Uchiyama |
| Abstract | We propose a Word Sense Disambiguation (WSD) method that accurately classifiesambiguous words to concepts in the Associative Concept Dictionary (ACD) evenwhen the test corpus and the training corpus for WSD are acquired fromdifferent domains. Many WSD studies determine the context of the targetambiguous word by analyzing sentences containing the target word. However, theyoffer poor performance when they are applied to a corpus that differs from thetraining corpus. One solution is to use associated words that aredomain-independently assigned to the concept in ACD; i.e. many users commonlyimagine those words against a given concept. Furthermore, by using theassociated words of a concept as search queries for a training corpus, ourmethod extracts relevant words, those that are computationally judged to berelated to that concept. By checking the frequency of associated words andrelevant words that appear near to the target word in a sentence in the testcorpus, our method classifies the target word to the concept in ACD. Ourevaluation using two different types of corpus demonstrates its good accuracy. |
| Language | Document Classification, Text categorisation |
| Topics | Word Sense Disambiguation, Lexicon, lexical database, Document Classification, Text categorisation |
Full paper  |
Study of Word Sense Disambiguation System that uses Contextual Features - Approach of Combining Associative Concept Dictionary and Corpus - |
| Bibtex | @InProceedings{TSUTSUMIDA10.192, author = {Kyota Tsutsumida, Jun Okamoto, Shun Ishizaki, Makoto Nakatsuji, Akimichi Tanaka and Tadasu Uchiyama}, title = {Study of Word Sense Disambiguation System that uses Contextual Features - Approach of Combining Associative Concept Dictionary and Corpus -}, 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} } |