Multi-document summarization

Automatic summarization

Operating system

Recurrent neural network

Political science

Politics

Computer science

Encoder

Natural language processing

Machine learning

Representation (politics)

Sentence

Selection (genetic algorithm)

Artificial intelligence

Artificial neural network

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.

Neural Document Summarization by Jointly Learning to Score and Select Sentences