Unsupervised Sentence Enhancement for Automatic Summarization

We present sentence enhancement as a novel technique for text-to-text generation in abstractive summarization. Compared to extraction or previous approaches to sentence fusion, sentence enhancement increases the range of possible summary sentences by allowing the combination of dependency subtrees from any sentence from the source text. Our experiments indicate that our approach yields summary sentences that are competitive with a sentence fusion baseline in terms of content quality, but better in terms of grammaticality, and that the benefit of sentence enhancement relies crucially on an event coreference resolution algorithm using distributional semantics. We also consider how text-to-text generation approaches to summarization can be extended beyond the source text by examining how human summary writers incorporate source-text-external elements into their summary sentences.