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

摘要

We present Smmr, a scalable sentence scoring method for query-oriented update summarization. Sentences are scored thanks to a criterion combining query relevance 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 results on the DUC 2007 update corpus.