Towards a Neural Network Approach to Abstractive Multi-Document Summarization
This addresses the challenge of multi-document summarization for researchers and practitioners, but it is incremental as it extends existing methods rather than introducing a new paradigm.
The paper tackles the problem of applying neural abstractive summarization to multi-document summarization by adapting a state-of-the-art single-document model with fine-tuning on limited multi-document data, achieving results that outperform baseline neural models on benchmark DUC datasets.
Till now, neural abstractive summarization methods have achieved great success for single document summarization (SDS). However, due to the lack of large scale multi-document summaries, such methods can be hardly applied to multi-document summarization (MDS). In this paper, we investigate neural abstractive methods for MDS by adapting a state-of-the-art neural abstractive summarization model for SDS. We propose an approach to extend the neural abstractive model trained on large scale SDS data to the MDS task. Our approach only makes use of a small number of multi-document summaries for fine tuning. Experimental results on two benchmark DUC datasets demonstrate that our approach can outperform a variety of baseline neural models.