Neural Document Summarization by Jointly Learning to Score and Select Sentences

Sentence scoring and sentence selection are two main steps in extractive document summarization systems. However, previous works treat them as two separated subtasks. In this paper, we present a novel end-to-end neural network framework for extractive document summarization by jointly learning to score and select sentences. It first reads the document sentences with a hierarchical encoder to obtain the representation of sentences. Then it builds the output summary by extracting sentences one by one. Different from previous methods, our approach integrates the selection strategy into the scoring model, which directly predicts the relative importance given previously selected sentences. Experiments on the CNN/Daily Mail dataset show that the proposed framework significantly outperforms the state-of-the-art extractive summarization models.

PDF Abstract ACL 2018 PDF ACL 2018 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Document Summarization CNN / Daily Mail NeuSUM ROUGE-1 41.59 # 15
ROUGE-2 19.01 # 14
ROUGE-L 37.98 # 16
Extractive Text Summarization CNN / Daily Mail NeuSUM ROUGE-2 19.01 # 8
ROUGE-1 41.59 # 9
ROUGE-L 37.98 # 7

Methods


No methods listed for this paper. Add relevant methods here