Presentation 2010-06-25
Semantic Relation Extraction from Documents Using Technical Term Extraction
Shinichi NAGANO, Masumi INABA, Takahiro KAWAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Ontologies and fact data have been well-known as fundamental resources for knowledge management, and their development has been encouraged around the world. They are often provided in a machine-readable, reusable, and extensible from, and that makes it possible to develop an ontology for a certain purpose without building up from scratch. However, ontologies and fact data used for enterprise is often local, particular, and domain dependent. The paper proposes a new method that extracts semantic relations from enterprise documents in order to realize enterprise ontology learning. It shows a preliminary study to clarify problems in order to achieve its practical performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Ontology learning / semantic relation extraction / term extraction
Paper # AI2010-2
Date of Issue

Conference Information
Committee AI
Conference Date 2010/6/18(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) Semantic Relation Extraction from Documents Using Technical Term Extraction
Sub Title (in English)
Keyword(1) Ontology learning
Keyword(2) semantic relation extraction
Keyword(3) term extraction
1st Author's Name Shinichi NAGANO
1st Author's Affiliation Corporate R&D Center, Toshiba Corporation()
2nd Author's Name Masumi INABA
2nd Author's Affiliation Platform Solutions Division, Toshiba Solutions Corporation
3rd Author's Name Takahiro KAWAMURA
3rd Author's Affiliation Corporate R&D Center, Toshiba Corporation
Date 2010-06-25
Paper # AI2010-2
Volume (vol) vol.110
Number (no) 105
Page pp.pp.-
#Pages 5
Date of Issue