Neural Document Summarization by Jointly Learning to Score and Select Sentences
This addresses the problem of improving summarization quality for users needing concise document overviews, representing an incremental advance over prior separated approaches.
The paper tackles extractive document summarization by jointly learning to score and select sentences, resulting in a framework that significantly outperforms state-of-the-art models on the CNN/Daily Mail dataset.
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.