Paper: Improving LSA-Based Summarization With Anaphora Resolution

ACL ID H05-1001
Title Improving LSA-Based Summarization With Anaphora Resolution
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors

We propose an approach to summarization exploiting both lexical information and the output of an automatic anaphoric re- solver, and using Singular Value Decom- position (SVD) to identify the main terms. We demonstrate that adding anaphoric information results in significant perfor- mance improvements over a previously developed system, in which only lexical terms are used as the input to SVD. How- ever, we also show that how anaphoric in- formation is used is crucial: whereas using this information to add new terms does re- sult in improved performance, simple sub- stitution makes the performance worse.