Presentation 1999/12/3
Sentence Generation from Table Structure of Extracted Important Data
Kazutaka SHIMADA, Tsutomu ENDO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Specifications contain many data, but it is not clear which is the most important data in them. In this paper, we propose a method for extracting important data from specifications of computer system and generating sentence from extracted important data. First, the table structure is generated from specifications written in HTML. The key data items such as the uppermost model and standard values are then extracted from the table structure. Next, important data are determined by comparing each data item with the key data. Finally, sentences are generated from sentence frames of which the slots are filled with important data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Specifications / Table structure / Surface expression / Important data / Sentence generation
Paper # TL99-29
Date of Issue

Conference Information
Committee TL
Conference Date 1999/12/3(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) Sentence Generation from Table Structure of Extracted Important Data
Sub Title (in English)
Keyword(1) Specifications
Keyword(2) Table structure
Keyword(3) Surface expression
Keyword(4) Important data
Keyword(5) Sentence generation
1st Author's Name Kazutaka SHIMADA
1st Author's Affiliation Department of Computer Science and Intelligent Systems, Oita University()
2nd Author's Name Tsutomu ENDO
2nd Author's Affiliation Department of Computer Science and Intelligent Systems, Oita University
Date 1999/12/3
Paper # TL99-29
Volume (vol) vol.99
Number (no) 487
Page pp.pp.-
#Pages 7
Date of Issue