Presentation 2004/10/28
Sentence Generation Using Mental-image Directed Semantic Theory and HPSG
Koichi RYU, Masao Yokota,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The use of mental-image directed semantic theory (MIDST) for HPSG makes it possible to build a system which has the merits of the both theories. The system can deal with deep meaning and exceptional language phenomena. Such a system is suitable for machine translation, because processing deep meaning is valid for rising accuracy of translation, and the system can describe exceptional language phenomena occurring on a word's level without additional grammar rules. Machine translation usually needs a large scale of grammar rules, and it is difficult to add new grammar rules with whole consistency maintained. Since we have already developed a syntactic and semantic analysis system, we have constructed a sentence generation system by way of experiment in this research. The utilized algorithm is chart generation, and the efficiency of generation process is increased by indices.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) mental-image directed semantic theory / HPSG / sentence generation / chart generation / machine translation
Paper # NLC2004-22
Date of Issue

Conference Information
Committee NLC
Conference Date 2004/10/28(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) Sentence Generation Using Mental-image Directed Semantic Theory and HPSG
Sub Title (in English)
Keyword(1) mental-image directed semantic theory
Keyword(2) HPSG
Keyword(3) sentence generation
Keyword(4) chart generation
Keyword(5) machine translation
1st Author's Name Koichi RYU
1st Author's Affiliation Faculty of Information Engineering, Fukuoka Institute of Technology()
2nd Author's Name Masao Yokota
2nd Author's Affiliation Faculty of Information Engineering, Fukuoka Institute of Technology
Date 2004/10/28
Paper # NLC2004-22
Volume (vol) vol.104
Number (no) 416
Page pp.pp.-
#Pages 6
Date of Issue