Sciweavers

Share
ACL
2011

Jointly Learning to Extract and Compress

8 years 2 months ago
Jointly Learning to Extract and Compress
We learn a joint model of sentence extraction and compression for multi-document summarization. Our model scores candidate summaries according to a combined linear model whose features factor over (1) the n-gram types in the summary and (2) the compressions used. We train the model using a marginbased objective whose loss captures end summary quality. Because of the exponentially large set of candidate summaries, we use a cutting-plane algorithm to incrementally detect and add active constraints efficiently. Inference in our model can be cast as an ILP and thereby solved in reasonable time; we also present a fast approximation scheme which achieves similar performance. Our jointly extracted and compressed summaries outperform both unlearned baselines and our learned extraction-only system on both ROUGE and Pyramid, without a drop in judged linguistic quality. We achieve the highest published ROUGE results to date on the TAC 2008 data set.
Taylor Berg-Kirkpatrick, Dan Gillick, Dan Klein
Added 23 Aug 2011
Updated 23 Aug 2011
Type Journal
Year 2011
Where ACL
Authors Taylor Berg-Kirkpatrick, Dan Gillick, Dan Klein
Comments (0)
books