Using relations to interpret anaphora

Nand, Parma
Yeap, W
Item type
Conference Contribution
Degree name
Journal Title
Journal ISSN
Volume Title

In this paper we present a novel framework for resolving bridging anaphora. The new framework is based on the core set of relations that have been used to describe an entirely different linguistic process, the process of generating a compound noun from two different nouns. We argue that the linguistic processes of compound noun generation and the use of NP anaphora are alike hence have to use the same relational framework. We validated this hypothesis by using human annotators to interpret indirect anaphora from naturally occurring discourses. The annotators were asked to classify the relations between anaphor-antecedent pairs into relation types that have been previously used to describe the relations between a modifier and the head noun of a compound noun. We obtained very encouraging results with a Fleiss’s k value of 0.66 for inter-annotation agreement.

Anaphora resolution , Noun phrase anaphora , Discourse structure , Noun compounds , Noun phrases
The Proceedings of the 4th International Conference on Agents and Artificial Intelligence, vol.1, pp.92 - 99
Rights statement
Copyright © 1993-2011 by Michael Ley (University of Trier, Informatik, 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.