paper

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

arXiv:1611.04230

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.

Published at AAAI 2017, The Thirty-First AAAI Conference on Artificial Intelligence (AAAI-2017)

Cited by in corpus (5)

SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents · wovepaper