Presentation 2009-02-27
Search Method for Parallel Texts Using N-gram
Hiroaki TABUCHI, Hiroshi SAKAMOTO, Yasuhiko KITAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have collected a lot of medical parallel texts with translations to support multilingual medical interpretation services for foreign visitors. When we retrieve parallel texts, we face a problem concerning narrowing the search result and ambiguous expression of parallel texts. We propose a parallel text retrieval method based on similarity measure using N-gram, and show its performance. This method provides an advantage that we can utilize the search inputs as cues to collect new parallel texts.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Similarity Search / N-gram / Information Retrieval / Parallel Text
Paper # AI2008-52
Date of Issue

Conference Information
Committee AI
Conference Date 2009/2/20(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 Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Search Method for Parallel Texts Using N-gram
Sub Title (in English)
Keyword(1) Similarity Search
Keyword(2) N-gram
Keyword(3) Information Retrieval
Keyword(4) Parallel Text
1st Author's Name Hiroaki TABUCHI
1st Author's Affiliation Graduate School of Engineering, Kwansei Gakuin University()
2nd Author's Name Hiroshi SAKAMOTO
2nd Author's Affiliation Faculty of Engineering, Kwansei Gakuin University
3rd Author's Name Yasuhiko KITAMURA
3rd Author's Affiliation Faculty of Engineering, Kwansei Gakuin University
Date 2009-02-27
Paper # AI2008-52
Volume (vol) vol.108
Number (no) 441
Page pp.pp.-
#Pages 6
Date of Issue