2.50
Hdl Handle:
http://hdl.handle.net/2436/27793
Title:
A New, Fully Automatic Version of Mitkov's Knowledge-Poor Pronoun Resolution Method
Authors:
Mitkov, Ruslan; Evans, Richard; Orasan, Constantin
Abstract:
This paper describes a new, advanced and completely revamped version of Mitkov's knowledge-poor approach to pronoun resolution. In contrast to most anaphora resolution approaches, the new system, referred to as MARS, operates in fully automatic mode. It benefits from purpose-built programs for identifying occurrences of non-nominal anaphora (including pleonastic pronouns) and for recognition of animacy, and employs genetic algorithms to achieve optimal performance. The paper features extensive evaluation and discusses important evaluation issues in anaphora resolution.
Citation:
In: Gelbukh, A. (Ed), Computational Linguistics and Intelligent Text Processing: Third International Conference on Intelligent Text Processing and Computational Linguistics: 168-186
Publisher:
Springer
Issue Date:
2002
URI:
http://hdl.handle.net/2436/27793
Additional Links:
http://clg.wlv.ac.uk/papers/ciclingAR19.pdf
Type:
Book chapter
Language:
en
ISBN:
3540432191
Appears in Collections:
Computational Linguistics Group ; Computational Linguistics Group

Full metadata record

DC FieldValue Language
dc.contributor.authorMitkov, Ruslan-
dc.contributor.authorEvans, Richard-
dc.contributor.authorOrasan, Constantin-
dc.date.accessioned2008-05-22T16:08:24Z-
dc.date.available2008-05-22T16:08:24Z-
dc.date.issued2002-
dc.identifier.citationIn: Gelbukh, A. (Ed), Computational Linguistics and Intelligent Text Processing: Third International Conference on Intelligent Text Processing and Computational Linguistics: 168-186en
dc.identifier.isbn3540432191-
dc.identifier.urihttp://hdl.handle.net/2436/27793-
dc.description.abstractThis paper describes a new, advanced and completely revamped version of Mitkov's knowledge-poor approach to pronoun resolution. In contrast to most anaphora resolution approaches, the new system, referred to as MARS, operates in fully automatic mode. It benefits from purpose-built programs for identifying occurrences of non-nominal anaphora (including pleonastic pronouns) and for recognition of animacy, and employs genetic algorithms to achieve optimal performance. The paper features extensive evaluation and discusses important evaluation issues in anaphora resolution.en
dc.language.isoenen
dc.publisherSpringeren
dc.relation.urlhttp://clg.wlv.ac.uk/papers/ciclingAR19.pdfen
dc.titleA New, Fully Automatic Version of Mitkov's Knowledge-Poor Pronoun Resolution Methoden
dc.typeBook chapteren
All Items in WIRE are protected by copyright, with all rights reserved, unless otherwise indicated.