8th International Conference on Speech, Text and Dialogue
September 2005, Carlsbad, Czech Republic

AARLISS – an Algorithm for Anaphora Resolution in Long-distance Inter Sentential Scenarios


Miroslav Martinovic, A. Curley, J. Gaskins



 
 
 
 

TOPIC AREA: Information Retrieval, Question Answering, NLP Tools and Resources
 



ABSTRACT

 
We present a novel approach for boosting the performance of pro-nominal anaphora resolution algorithms when search for antecedents has to span over a multi-sentential text passage. The approach is based on  the identi-fication of sentences which are ”most semantically related” to the sentence with anaphora. The context sharing level between each possible referent sentence and the anaphoric sentence gets established utilizing an open-domain external knowledge base. Sentences with scores higher than a threshold level are con-sidered the “most semantically related” and ranked accordingly. The qualified sentences accompanied with their context sharing scores represent a new, re-duced in size, and a more semantically focused search space. Their respective scores are utilized as separate preference factors in a final phase of the resolu-tion process – the antecedent selection. We pioneer three implementations for the algorithm with their corresponding evaluation data.