SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents

Ramesh Nallapati, Feifei Zhai, Bowen Zhou

AAAI 2017 pp. 3075-3081

doi:10.1609/AAAI.V31I1.10958 /aaai/2017/nallapati2017aaai-summarunner/

Abstract

We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art. Our model has the additional advantage of being very interpretable, since it allows visualization of its predictions broken up by abstract features such as information content, salience and novelty. Another novel contribution of our work is abstractive training of our extractive model that can train on human generated reference summaries alone, eliminating the need for sentence-level extractive labels.

PDF AAAI Semantic Scholar

Cite

Text

Nallapati et al. "SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.10958

Markdown

[Nallapati et al. "SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/nallapati2017aaai-summarunner/) doi:10.1609/AAAI.V31I1.10958

BibTeX

@inproceedings{nallapati2017aaai-summarunner,
  title     = {{SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents}},
  author    = {Nallapati, Ramesh and Zhai, Feifei and Zhou, Bowen},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {3075-3081},
  doi       = {10.1609/AAAI.V31I1.10958},
  url       = {https://mlanthology.org/aaai/2017/nallapati2017aaai-summarunner/}
}