Subject-Keyphrase Extraction Based on Definition-Use Chain

• Published in: 2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) Vol. 3; pp. 199 - 202
• Main Authors: Hung-Min Hsu, Ray-I Chang, Yu-Jung Chang, Shu-Yu Lin, You-Jyun Wang, Jan-Ming Ho
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2015
• Subjects: Artificial intelligence; Computational linguistics; definition-use chain; Feature extraction; Information processing; Intelligent agents; Libraries; machine learning; Particle swarm optimization; Subject-keyphrase extraction
• DOI: 10.1109/WI-IAT.2015.192

In this paper, we propose a new concept called subject-keyphrase and also introduce a method to extract subject-keyphrases from a document. Subject-keyphrases refer to the words or phrases used to represent the sentence subjects of a document, i.e., the content of a document is organized around the subjects of the document. It can be expected that each sentence of a document is composed of a subject and an object, where the subject is defined in relation to its object. Using "definition" and "use" relations, we may thus identify the subjects in a given document by looking for keyphrases which appear frequently as subjects of sentences in the document. We thus present a subject-keyphrase extraction (SKE) algorithm based on the notion of definition-use chain (DU Chain) to identify subject-keyphrases. Experimental results show that SKE can successfully identify the subject-keyphrases to effectively capture the main idea of a document.