Paper: Abstractive Meeting Summarization with Entailment and Fusion

ACL ID W13-2117
Title Abstractive Meeting Summarization with Entailment and Fusion
Venue European Workshop on Natural Language Generation
Session
Year 2013
Authors

Abstractive Meeting Summarization with Entailment and Fusion Yashar Mehdad ? Giuseppe Carenini ? Frank W. Tompa ?? Raymond T. NG ? Department of Computer Science ?University of British Columbia ??University of Waterloo {mehdad, carenini, rng}@cs.ubc.ca fwtompa@cs.uwaterloo.ca Abstract We propose a novel end-to-end frame- work for abstractive meeting summariza- tion. We cluster sentences in the in- put into communities and build an entail- ment graph over the sentence communi- ties to identify and select the most relevant sentences. We then aggregate those se- lected sentences by means of a word graph model. We exploit a ranking strategy to select the best path in the word graph as an abstract sentence. Despite not relying on the syntactic structure, our approach significantly outperforms p...