Using relations to interpret anaphora

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 linguist...

Full description

Bibliographic Details
Main Authors: Nand, Parma (Author), Yeap, W (Author)
Format: Others
Published: DBLP, 2012-05-16T23:44:55Z.
Subjects:
Online Access:Get fulltext
LEADER 01540 am a22002173u 4500
001 4188
042 |a dc 
100 1 0 |a Nand, Parma  |e author 
700 1 0 |a Yeap, W  |e author 
245 0 0 |a Using relations to interpret anaphora 
260 |b DBLP,   |c 2012-05-16T23:44:55Z. 
500 |a The Proceedings of the 4th International Conference on Agents and Artificial Intelligence, vol.1, pp.92 - 99 
520 |a 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. 
540 |a OpenAccess 
650 0 4 |a Anaphora resolution 
650 0 4 |a Noun phrase anaphora 
650 0 4 |a Discourse structure 
650 0 4 |a Noun compounds 
650 0 4 |a Noun phrases 
655 7 |a Conference Contribution 
856 |z Get fulltext  |u http://hdl.handle.net/10292/4188