Presentation 2000/11/27
A Method of Metaphoricity Detection using Statistical Measures
Fumito MASUI, Takehiro TAZOE, Tsutomu SHIINO, Jun'ichi FUKUMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a method of metaphoricity detection using two statistical measures to compute metaphrical expression. In the first place, we recommend two measures, which are disparity and novelty. disparity shows saliency gap between concepts and novelty show novelty in a pare of words. Secondaly, we explain how to calculate two measures and discuss about construction of knowledge base for metaphoricity detection. Knowledge base was constructed with co-occurrences("noun and adjective/adverb" and "noun and noun")from corpora. In the experiment, we used 50 pares of nouns which human extracted from newspapar articles, books and journals for test data. Result says over 80 percent accuracy in each of recall, precision and F-measure in the case of novelty preference.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Metaphoricity / Statistical measure / Co-occurance / Corpus / Knowledge base
Paper # TL2000-28
Date of Issue

Conference Information
Committee TL
Conference Date 2000/11/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Method of Metaphoricity Detection using Statistical Measures
Sub Title (in English)
Keyword(1) Metaphoricity
Keyword(2) Statistical measure
Keyword(3) Co-occurance
Keyword(4) Corpus
Keyword(5) Knowledge base
1st Author's Name Fumito MASUI
1st Author's Affiliation Department of Information Engineering, Faculty of Engineering, Mie University()
2nd Author's Name Takehiro TAZOE
2nd Author's Affiliation Department of Information Engineering, Faculty of Engineering, Mie University
3rd Author's Name Tsutomu SHIINO
3rd Author's Affiliation Department of Information Engineering, Faculty of Engineering, Mie University
4th Author's Name Jun'ichi FUKUMOTO
4th Author's Affiliation Department of Computer Science, Ritsumeikan University
Date 2000/11/27
Paper # TL2000-28
Volume (vol) vol.100
Number (no) 480
Page pp.pp.-
#Pages 8
Date of Issue