dc.contributor.author Nand, P
dc.contributor.author Yeap, W
dc.contributor.editor Hota, C
dc.contributor.editor Shanthi, V
dc.contributor.editor Sanjeevi, S
dc.date.accessioned 2012-05-16T21:42:33Z
dc.date.accessioned 2012-05-16T21:43:07Z
dc.date.accessioned 2012-05-17T03:07:21Z
dc.date.accessioned 2012-05-17T03:07:27Z
dc.date.available 2012-05-16T21:42:33Z
dc.date.available 2012-05-16T21:43:07Z
dc.date.available 2012-05-17T03:07:21Z
dc.date.available 2012-05-17T03:07:27Z
dc.date.copyright 2011-11-24
dc.date.issued 2012-05-17
dc.identifier.citation In proceedings of the 2nd Annual International Conference on Advanced Topics in Artificial Intelligence, Hotel Fort, Canning, Singapore. 24 to 25-11-2011. pp.44 - 49 (6)
dc.identifier.issn 2251-2233
dc.identifier.uri http://hdl.handle.net/10292/4192
dc.description.abstract In this paper we present a novel way to resolve indirect or bridging anaphora which gives us a richer interpretation then the current frameworks. The new framework uses the core set of relations that have been used to describe compound noun generation. We firstly argue that the linguistic processes of compound noun generation and the use of NP anaphora are based on a common relational framework. In order to validate this theory we used human annotators to interpret indirect anaphora from naturally occurring discourses. The annotators were asked to classify the relation between an anaphor and the antecedent into relation types that have been previously used to describe the relation between the modifier and the head noun of a compound noun. We obtained very encouraging results with a Fleiss's kappa value of 0.66 for inter-annotation agreement. This compares well with other similar annotation experiments for relation interpretation in compound nouns. The annotation results strongly indicate that anaphora and noun compounds are based on very similar relational framework, hence should treated the same.
dc.publisher Global science and Technology Forum (GSTF)
dc.relation.replaces http://hdl.handle.net/10292/4183
dc.relation.replaces 10292/4183
dc.relation.replaces http://hdl.handle.net/10292/4184
dc.relation.replaces 10292/4184
dc.relation.replaces http://hdl.handle.net/10292/4191
dc.relation.replaces 10292/4191
dc.relation.uri http://goo.gl/bh5Qk
dc.rights Copyright © 1993-2011 by Michael Ley (University of Trier, Informatik, ley@uni-trier.de) and Schloss Dagstuhl - Leibniz-Zentrum für Informatik GmbH. In the eyes of DBLP, a simple note refering to DBLP and/or a link back to DBLP's website is sufficient to meet the attribution criterion. Individual use of only a small number of records (such as a publication list of a few authors or the table of content of a proceedings volume) does not need attribution.
dc.subject Anaphora resolution; Noun phrase anaphora; Discourse structure; Noun compounds; Noun phrasenaphora resolution; Noun phrase anaphora; Discourse structure; Noun compounds; Noun phrase
dc.title A relational framework for interpreting anaphora
dc.type Conference Contribution
dc.rights.accessrights OpenAccess
dark.contributor.author Nand, P
dark.contributor.author Yeap, W
aut.conference.type Paper Published in Proceedings
aut.publication.place Singapore
aut.relation.endpage 49
aut.relation.pages 6
aut.relation.startpage 44

Search Scholarly Commons


Advanced Search

Browse

Theses and Dissertations

About Scholarly Commons

Usage Statistics

Share

  • Bookmark and Share