SOTAVerified

A Deep Reinforced Model for Abstractive Summarization

2017-05-11ICLR 2018Code Available1· sign in to hype

Romain Paulus, Caiming Xiong, Richard Socher

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Attentional, RNN-based encoder-decoder models for abstractive summarization have achieved good performance on short input and output sequences. For longer documents and summaries however these models often include repetitive and incoherent phrases. We introduce a neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and reinforcement learning (RL). Models trained only with supervised learning often exhibit "exposure bias" - they assume ground truth is provided at each step during training. However, when standard word prediction is combined with the global sequence prediction training of RL the resulting summaries become more readable. We evaluate this model on the CNN/Daily Mail and New York Times datasets. Our model obtains a 41.16 ROUGE-1 score on the CNN/Daily Mail dataset, an improvement over previous state-of-the-art models. Human evaluation also shows that our model produces higher quality summaries.

Tasks

Abstractive Text SummarizationDecodermodelPredictionReinforcement LearningReinforcement Learning (RL)Text Summarization

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
CNN / Daily MailML + RL (Paulus et al., 2017)ROUGE-139.87—Unverified
CNN / Daily MailML + Intra-Attention (Paulus et al., 2017)ROUGE-138.3—Unverified

Reproductions