Event Information Extraction Using Link Grammar

Madhyastha, Harsha V and Balakrishnan, N and Ramakrishnan, KR (2003) Event Information Extraction Using Link Grammar. In: 13th International WorkShop on Research Issues in Data Engineering: Multi-lingual Information Management (RIDE'03), March 10 - 11, 2003, Hyderabad, India, pp. 16-22.

Preview

PDF EVENT_INFORMATION_EXTRACTION_USING_LINK_GRAMMAR.pdf Download (748kB)

Abstract

In this paper, we present a scheme for identifying instances of events and extracting information about them. The scheme can handle all events with which an action can be associated, which covers most types of events. Our system basically tries to extract semantic information from the syntactic structure given by the link grammar system [Carnegie Mellon University Computer Science technical report] to any English sentence. The instances of events are identified by finding all sentences in the text where the verb, which best represents the action in the event, or one of its synonyms/hyponyms occurs as a main verb. Then, information about that instance of the event is derived using a set of rules which we have developed to identify the subject and object as well as the modifiers of all verbs and nouns in any English sentence, making use of the structure given by the link parser. The scheme was tested on the Reuters corpus and gave recall and precision even upto 100%.

Item Type:	Conference Paper
Publisher:	IEEE
Additional Information:	©2003 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Keywords:	Information extraction
Department/Centre:	Division of Interdisciplinary Sciences > Supercomputer Education & Research Centre
Date Deposited:	23 Jul 2004
Last Modified:	19 Sep 2010 04:14
URI:	http://eprints.iisc.ac.in/id/eprint/1140

Actions (login required)

View Item