Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
arXiv:1808.06218
Abstract
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.
11 pages
References in corpus (14)
- A Deep Reinforced Model for Abstractive Summarization
- Selective Encoding for Abstractive Sentence Summarization
- Abstract Meaning Representation for Multi-Document Summarization
- A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
- Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting
- Structure-Infused Copy Mechanisms for Abstractive Summarization
- Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models
- Distraction-Based Neural Networks for Document Summarization
- Graph-based Neural Multi-Document Summarization
- Controlling Output Length in Neural Encoder-Decoders
- Language as a Latent Variable: Discrete Generative Models for Sentence Compression
- Bottom-Up Abstractive Summarization
- Abstractive Multi-Document Summarization via Phrase Selection and Merging
- Towards a Neural Network Approach to Abstractive Multi-Document Summarization