English

Bottom-Up Abstractive Summarization

Computation and Language 2018-10-10 v2 Artificial Intelligence Machine Learning

Abstract

Neural network-based methods for abstractive summarization produce outputs that are more fluent than other techniques, but which can be poor at content selection. This work proposes a simple technique for addressing this issue: use a data-efficient content selector to over-determine phrases in a source document that should be part of the summary. We use this selector as a bottom-up attention step to constrain the model to likely phrases. We show that this approach improves the ability to compress text, while still generating fluent summaries. This two-step process is both simpler and higher performing than other end-to-end content selection models, leading to significant improvements on ROUGE for both the CNN-DM and NYT corpus. Furthermore, the content selector can be trained with as little as 1,000 sentences, making it easy to transfer a trained summarizer to a new domain.

Keywords

Cite

@article{arxiv.1808.10792,
  title  = {Bottom-Up Abstractive Summarization},
  author = {Sebastian Gehrmann and Yuntian Deng and Alexander M. Rush},
  journal= {arXiv preprint arXiv:1808.10792},
  year   = {2018}
}

Comments

EMNLP 2018