Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
This addresses the problem of multi-document summarization for NLP applications, offering a robust, data-efficient solution that is incremental in adapting existing frameworks.
The paper tackles the challenge of adapting neural encoder-decoder models from single-document to multi-document summarization by proposing a novel adaptation method that uses maximal marginal relevance for sentence selection and an abstractive model for fusion, achieving favorable results compared to state-of-the-art approaches as judged by automatic metrics and human assessors.
Generating a text abstract from a set of documents remains a challenging task. The neural encoder-decoder framework has recently been exploited to summarize single documents, but its success can in part be attributed to the availability of large parallel data automatically acquired from the Web. In contrast, parallel data for multi-document summarization are scarce and costly to obtain. There is a pressing need to adapt an encoder-decoder model trained on single-document summarization data to work with multiple-document input. In this paper, we present an initial investigation into a novel adaptation method. It exploits the maximal marginal relevance method to select representative sentences from multi-document input, and leverages an abstractive encoder-decoder model to fuse disparate sentences to an abstractive summary. The adaptation method is robust and itself requires no training data. Our system compares favorably to state-of-the-art extractive and abstractive approaches judged by automatic metrics and human assessors.