Towards a Neural Network Approach to Abstractive Multi-Document Summarization
arXiv:1804.09010
Abstract
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.
10 pages
References in corpus (5)
- Adam: A Method for Stochastic Optimization
- Neural Machine Translation by Jointly Learning to Align and Translate
- A Deep Reinforced Model for Abstractive Summarization
- Generating Wikipedia by Summarizing Long Sequences
- Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models
Cited by in corpus (6)
- Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
- Leveraging Graph to Improve Abstractive Multi-Document Summarization
- Massive Multi-Document Summarization of Product Reviews with Weak Supervision
- MS2: Multi-Document Summarization of Medical Studies
- TWAG: A Topic-Guided Wikipedia Abstract Generator
- A Comprehensive Attempt to Research Statement Generation