University of Wolverhampton
Browse
Collection All
bullet
bullet
bullet
bullet
Listed communities
bullet
bullet
bullet
bullet
bullet
bullet
bullet
bullet
bullet
bullet
bullet
bullet
bullet

Wolverhampton Intellectual Repository and E-Theses > Research Institutes > Research Institute in Information and Language Processing > Computational Linguistics Group > NP animacy identification for anaphora resolution

Please use this identifier to cite or link to this item: http://hdl.handle.net/2436/27896
    Del.icio.us     LinkedIn     Citeulike     Connotea     Facebook     Stumble it!



Title: NP animacy identification for anaphora resolution
Authors: Orasan, Constantin
Evans, Richard
Citation: Journal of Artificial Intelligence Research, 29 (2007): 79-103
Publisher: American Association for Artificial Intelligence
Journal: Journal of Artificial Intelligence Research
Issue Date: 2007
URI: http://hdl.handle.net/2436/27896
Additional Links: http://www.jair.org/
http://www.jair.org/media/2179/live-2179-3273-jair.pdf
Abstract: In anaphora resolution for English, animacy identification can play an integral role in the application of agreement restrictions between pronouns and candidates, and as a result, can improve the accuracy of anaphora resolution systems. In this paper, two methods for animacy identification are proposed and evaluated using intrinsic and extrinsic measures. The first method is a rule-based one which uses information about the unique beginners in WordNet to classify NPs on the basis of their animacy. The second method relies on a machine learning algorithm which exploits a WordNet enriched with animacy information for each sense. The effect of word sense disambiguation on the two methods is also assessed. The intrinsic evaluation reveals that the machine learning method reaches human levels of performance. The extrinsic evaluation demonstrates that animacy identification can be beneficial in anaphora resolution, especially in the cases where animate entities are identified with high precision.
Type: Article
Language: en
Keywords: Anaphora resolution
Animacy identification
Artificial Intelligence
ISSN: 11076 - 9757
Appears in Collections: Computational Linguistics Group
Computational Linguistics Group

Files in This Item:

There are no files associated with this item.



All Items in WIRE are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Fairtrade - Guarantees a better deal for Third World Producers

University of Wolverhampton, Wulfruna Street, Wolverhampton, WV1 1LY

Course enquiries: 0800 953 3222, General enquiries: 01902 321000,
Email: enquiries@wlv.ac.uk | Freedom of Information | Disclaimer and copyright | Website feedback | The University as a charity

OR Logo Powered by Open Repository | Cookies