Premium
Acquisition of term knowledge from operating manuals for information equipment by using the structure of headline sentences
Author(s) -
Imamura Makoto,
Takayama Yasuhiro,
Akiyoshi Masanori,
Komoda Norihisa
Publication year - 2010
Publication title -
electronics and communications in japan
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.131
H-Index - 13
eISSN - 1942-9541
pISSN - 1942-9533
DOI - 10.1002/ecj.10314
Subject(s) - headline , relation (database) , computer science , term (time) , matching (statistics) , natural language processing , hierarchy , artificial intelligence , relationship extraction , information retrieval , information extraction , data mining , linguistics , mathematics , statistics , quantum mechanics , economics , market economy , philosophy , physics
This paper proposes a method for automatically extracting term knowledge such as case relations and IS‐A relations between words in the headline sentences of the operating manuals for information equipment. The proposed method acquires term knowledge by the following iterative processing: case relation extraction using correspondence relations between the surface cases and the deep cases; case and IS‐A relation extraction using compound word structures; and IS‐A relation extraction using correspondence between the case structures in the hierarchical headline sentences. The distinctive feature of our method is that it extracts new case relations and IS‐A relations by comparison and matching of the case relations extracted from the super and sub headline sentences, using the headline hierarchy. We confirmed that the proposed method could achieve approximately 90% recall and precision for the extraction of case relations and IS‐A relations from the operating manuals of a car navigation system and a mobile phone. © 2010 Wiley Periodicals, Inc. Electron Comm Jpn, 93(11): 8–19, 2010; Published online in Wiley Online Library ( wileyonlinelibrary.com ). DOI 10.1002/ecj.10314