Acquisition and Utilization of Usage Information for Language Resources

Shunsuke KOZAWA  Hitomi TOHYAMA  Kiyotaka UCHIMOTO  Shigeki MATSUBARA 

Publication
A - Abstracts of IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences (Japanese Edition)  Vol.J95-A  No.7  pp.611-622
Publication Date: 2012/07/01
Online ISSN: 1881-0195
Print ISSN: 0913-5707
Type of Manuscript: Special Section PAPER (Special Issue on Emerging Technologies in Electronics, Information and Communication)
Category: 
Keyword: 
information extraction,  language resource,  information retrieval,  metadata,  syntax analysis, 

Full Text(in Japanese): PDF(554.1KB)

Summary: 
Recently, language resources (LRs) are becoming indispensable for linguistic research. However, existing LRs are often not fully utilized because their variety of usage is not well known, indicating that their intrinsic value is not recognized very well either. This paper describes a method for automatically extracting usage information for LRs from texts written by the users of LRs and evaluates the validity and the availability of the extracted usage information. The method extracts usage information by rules based on syntactic information. The result has shown that the lists of usage information can be accurately extracted from academic articles using the described method and that the extracted usage information contributes LR searches.