Presentation 2019-02-23
Mining Semantic Patterns from Dependency Trees of Japanese Sentences
Ryo Suzuki, Ken Kaneiwa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Users can obtain information from large-scale web texts using keyword-based web search services. Such search services find information including keywords but not semantically matching information because natural language texts on the web are not machine-readable. In this paper, we develop a pattern mining method that extracts frequent semantic structures in the dependency trees of Japanese sentences. In order to deal with the flexible word order in Japanese, we propose feature expressions (SIT lists) consisting of the three sets of phase nodes in the dependency trees. In the evaluation experiment, we show that the pattern mining method for SIT lists enables us to flexibly extract common semantic patterns that are implicitly included in the dependency trees of Japanese sentences.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Text mining / Information extraction / Knowledge acquisition
Paper # AI2018-46
Date of Issue 2019-02-15 (AI)

Conference Information
Committee AI
Conference Date 2019/2/22(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tsunenori Mine(Kyushu Univ.)
Vice Chair Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.)
Secretary Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.)
Assistant Yuko Sakurai(AIST)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Mining Semantic Patterns from Dependency Trees of Japanese Sentences
Sub Title (in English)
Keyword(1) Text mining
Keyword(2) Information extraction
Keyword(3) Knowledge acquisition
1st Author's Name Ryo Suzuki
1st Author's Affiliation The University of Electro-Communications(The Univ. of Electro-Communications)
2nd Author's Name Ken Kaneiwa
2nd Author's Affiliation The University of Electro-Communications(The Univ. of Electro-Communications)
Date 2019-02-23
Paper # AI2018-46
Volume (vol) vol.118
Number (no) AI-453
Page pp.pp.51-55(AI),
#Pages 5
Date of Issue 2019-02-15 (AI)