dc.contributor.author Ho, H.
dc.contributor.author Min, K.
dc.contributor.author Yeap, W.
dc.date.accessioned 2009-05-27T22:22:16Z
dc.date.available 2009-05-27T22:22:16Z
dc.date.copyright 2004
dc.date.created 2004
dc.date.issued 2009-05-27T22:22:16Z
dc.identifier.uri http://hdl.handle.net/10292/637
dc.description.abstract This paper describes a knowledge-poor anaphora resolution approach based on a shallow meaning representation of sentences. The structure afforded in such a representation provides immediate identification of local domains which are required for resolving pronominal anaphora. Other kinds of information used include syntactic information, structure parallelism and salience weights. We collected 111 singular 3rd person pronouns from open domain resources such as children's novel and examples from several anaphora resolution papers. There are 111 third-person singular pronouns in the experiment data set and 94 of them demonstrate pronominal anaphora in domain of test data. The system successfully resolves 78.4% of anaphoric examples. © Springer-Verlag Berlin Heidelberg 2004.
dc.publisher Springer
dc.publisher AUT University
dc.relation.uri http://dx.doi.org/10.1007/b99563
dc.rights The original publication is available at www.springerlink.com.
dc.source Lecture Notes in Artificial Intelligence, 3157, 862-871
dc.title Pronominal anaphora resolution using a shallow meaning representation of sentences
dc.type Journal Article
dc.rights.accessrights OpenAccess

Search Scholarly Commons


Advanced Search

Browse

Theses and Dissertations

About Scholarly Commons

Usage Statistics

Share

  • Bookmark and Share