Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization
arXiv:1906.00072
Abstract
The most important obstacles facing multi-document summarization include excessive redundancy in source descriptions and the looming shortage of training data. These obstacles prevent encoder-decoder models from being used directly, but optimization-based methods such as determinantal point processes (DPPs) are known to handle them well. In this paper we seek to strengthen a DPP-based method for extractive multi-document summarization by presenting a novel similarity measure inspired by capsule networks. The approach measures redundancy between a pair of sentences based on surface form and semantic information. We show that our DPP system with improved similarity measure performs competitively, outperforming strong summarization baselines on benchmark datasets. Our findings are particularly meaningful for summarizing documents created by multiple authors containing redundant yet lexically diverse expressions.
arXiv commentACL 2019 (Long Paper)
References in corpus (9)
- Teaching Machines to Read and Comprehend
- A Deep Reinforced Model for Abstractive Summarization
- SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
- Selective Encoding for Abstractive Sentence Summarization
- Neural Natural Language Inference Models Enhanced with External Knowledge
- Faithful to the Original: Fact Aware Neural Abstractive Summarization
- Learning Determinantal Point Processes
- A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
- Structure-Infused Copy Mechanisms for Abstractive Summarization