Presentation 1994/5/13
Automatic Acquisition of Tarnslation Knowledge from Parallel Bilingual Corpus
Mihoko Kitamura, Yuji Matsumoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Machine translation,which is one of the applications for natural language processing techniques,has become increasingly useful in recent years.However,there is the problem of how we should acquire the information needed for translation,such as grammar rules and lexical rules.This paper presents a method for automatic extraction of necessary information for translation.The process uses both the similarities of word pairs obtained statistically from parallel bilingual corpus and the similarities of subgraphs of dependency trees from parsed parallel sentences.The experimental result using 36,000 sentences shows that this method is useful for obtaining rules and patterns for translation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Natural Language Processing / parallel corpus / structual alignment / acquistion of translation knowledge / machine translation
Paper # NLC94-2
Date of Issue

Conference Information
Committee NLC
Conference Date 1994/5/13(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic Acquisition of Tarnslation Knowledge from Parallel Bilingual Corpus
Sub Title (in English)
Keyword(1) Natural Language Processing
Keyword(2) parallel corpus
Keyword(3) structual alignment
Keyword(4) acquistion of translation knowledge
Keyword(5) machine translation
1st Author's Name Mihoko Kitamura
1st Author's Affiliation Graduate School of Information Science,Nara Institute of Science and Technology()
2nd Author's Name Yuji Matsumoto
2nd Author's Affiliation Graduate School of Information Science,Nara Institute of Science and Technology
Date 1994/5/13
Paper # NLC94-2
Volume (vol) vol.94
Number (no) 32
Page pp.pp.-
#Pages 8
Date of Issue