Summary Level Training of Sentence Rewriting for Abstractive Summarization

Information

Title Summary Level Training of Sentence Rewriting for Abstractive Summarization

Authors

Sanghwan Bae, Taeuk Kim, Jihoon Kim, Sang-goo Lee

Year 2019 / 11

Keywords natural language processing, text summarization, reinforcement learning

Acknowledgement HPC

Publication Type International Conference

Publication The Second Workshop on New Frontiers in Summarization 2019 (EMNLP Workshop)

Link url

Abstract

As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then paraphrasing the selected ones to generate a summary. However, the existing models in this framework mostly rely on sentence-level rewards or suboptimal labels, causing a mismatch between a training objective and evaluation metric. In this paper, we present a novel training signal that directly maximizes summary-level ROUGE scores through reinforcement learning. In addition, we incorporate BERT into our model, making good use of its ability on natural language understanding. In extensive experiments, we show that a combination of our proposed model and training procedure obtains new state-of-the-art performance on both CNN/Daily Mail and New York Times datasets. We also demonstrate that it generalizes better on DUC-2002 test set.