Paper: A Scalable MMR Approach to Sentence Scoring for Multi-Document Update Summarization

ACL ID C08-2006
Title A Scalable MMR Approach to Sentence Scoring for Multi-Document Update Summarization
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2008
Authors

We present SMMR, a scalable sentence scoring method for query-oriented up- date summarization. Sentences are scored thanks to a criterion combining query rele- vance and dissimilarity with already read documents (history). As the amount of data in history increases, non-redundancy is prioritized over query-relevance. We show that SMMR achieves promising re- sults on the DUC 2007 update corpus.