Presentation 1998/7/23
ENHANCE OF MACHINE TRANSLATION WITH GDA-TAGS
Christoph Neumann, Koiti Hasida,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The source text in the MT system comes with GDA tags, which are designed to provide disambiguation information needed for NLP applications. The tagged text matches, as a feature structure, patterns of structure transfer L1-L2. For 28 ambiguity problems in Japanese-English MT, such transfer patterns were created. For further semantic disambiguation, "metawords" and a WWW dictionary are used. Generation of actual L2-text involves again pattern matching rules. The pattern matching algorithm is implemented as a clause set, which is resolved in Prolog. The working strategy is explained through translation a multi-ambiguous example sentence. The system shows an unconventional way to MT and the feasibility of doing MT with GDA tags.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) GDA / machine translation / hypertext / PBMT / Prolog
Paper # NLC98-9
Date of Issue

Conference Information
Committee NLC
Conference Date 1998/7/23(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) ENHANCE OF MACHINE TRANSLATION WITH GDA-TAGS
Sub Title (in English)
Keyword(1) GDA
Keyword(2) machine translation
Keyword(3) hypertext
Keyword(4) PBMT
Keyword(5) Prolog
1st Author's Name Christoph Neumann
1st Author's Affiliation Tokyo Institute of Technology()
2nd Author's Name Koiti Hasida
2nd Author's Affiliation Electrotechnical Laboratory
Date 1998/7/23
Paper # NLC98-9
Volume (vol) vol.98
Number (no) 209
Page pp.pp.-
#Pages 8
Date of Issue