Summary of the paper
| Title | Detection of Peculiar Examples using LOF and One Class SVM |
|---|---|
| Authors | Hiroyuki Shinnou and Minoru Sasaki |
| Abstract | This paper proposes the method to detect peculiar examples of the target wordfrom a corpus. In this paper we regard following examples aspeculiarexamples: (1) a meaning of the target word in the example is new, (2) acompound word consisting of the target word in the example is new or verytechnical.The peculiar example is regarded as an outlier in the given example set.Therefore we can apply many methods proposed in the data mining domain to ourtask. In this paper, we propose the method to combine the density based method,Local Outlier Factor (LOF), and One Class SVM, which are representative outlierdetection methods in the data mining domain.In the experiment, we use the Whitepaper text in BCCWJ as the corpus, and 10noun words as target words. Our method improved precision and recall of LOFand One Class SVM. And we show that our method can detect new meanings by usingthe noun `midori (green)'. The main reason of un-detections and wrong detectionis that similarity measure of two examples is inadequacy. In future, we mustimprove it. |
| Language | Lexicon, lexical database |
| Topics | Text mining, Word Sense Disambiguation, Lexicon, lexical database |
Full paper  |
Detection of Peculiar Examples using LOF and One Class SVM |
| Bibtex | @InProceedings{SHINNOU10.167, author = {Hiroyuki Shinnou and Minoru Sasaki}, title = {Detection of Peculiar Examples using LOF and One Class SVM}, 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} } |