A Framework for Interpreting Bridging Anaphora

In this paper we present a novel framework for resolving bridging anaphora. We argue that anaphora, particularly bridging anaphora, is used as a shortcut device similar to the use of compound nouns. Hence, the two natural language usage phenomena would have to be based on the same theoretical framework. We use an existing theory on compound nouns to test its validity for anaphora usages. To do this, we used 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 an average Fleiss’s

κ

value of 0.66 for inter-annotation agreement. The results were evaluated against other similar natural language interpretation annotation experiments and were found to compare well.

In order to determine the prevalence of the proposed set of anaphora relations we did a detailed analysis of a subset 20 newspaper articles. The results obtained from this also indicated that a majority (98%) of the relations could be described by the relations in the framework. The results from this analysis also showed the distribution of the relation types in the genre of news paper article discourses.