Home // eKNOW 2013, The Fifth International Conference on Information, Process, and Knowledge Management // View article

Extraction of Semantic Relationships from Academic Papers using Syntactic Patterns

Authors:
Akihiro Kameda
Kiyoko Uchiyama
Hideaki Takeda
Akiko Aizawa

Keywords: Relation extraction, Citation context, Knowledge extraction

Abstract:
Integrating concept and citation networks on a specific research subject can help researchers focus their own work or use methods described in prior works. In this paper, we propose a method to extract semantic relations from concepts and citation in the descriptions of related work. Specifically, we examined (i) topic-paper relations between research topics and reference papers and (ii) method-purpose relations between research topics. We also defined 15 lexico-syntactic patterns for the relation extraction. Results of experiments using a manually annotated dataset of 15 papers demonstrated the effectiveness of using the proposed lexico-syntactic patterns.

Pages: 32 to 35

Copyright: Copyright (c) IARIA, 2013

Publication date: February 24, 2013

Published in: conference

ISSN: 2308-4375

ISBN: 978-1-61208-254-7

Location: Nice, France

Dates: from February 24, 2013 to March 1, 2013