Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6244–6254 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 6244 Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization Hanqi Jin, Tianming Wang, Xiaojun Wan Wangxuan Institute of Computer Technology, Peking University Center for Data Science, Peking University The MOE Key Laboratory of Computational Linguistics, Peking University {jinhanqi,wangtm,wanxiaojun}@pku.edu.cn Abstract In this paper, we propose a multi-granularity interaction network for extractive and abstrac- tive multi-document summarization, which jointly learn semantic representations for words, sentences, and documents. The word representations are used to generate an abstrac- tive summary while the sentence representa- tions are used to produce an extractive sum- mary. We employ attention mechanisms to interact between different granularity of se- mantic representations, which helps to cap- ture multi-granularity key information and im- proves the performance of both abstractive and extractive summarization. Experiment results show that our proposed model substantially outperforms all strong baseline methods and achieves the best results on the Multi-News dataset. 1 Introduction Document summarization aims at producing a flu- ent, condensed summary for given documents. Sin- gle document summarization has shown promising results with sequence-to-sequence models that en- code a source document and then decode it into a summary (See et al., 2017; Paulus et al., 2018; Gehrmann et al., 2018; C¸ elikyilmaz et al., 2018). Multi-document summarization requires producing a summary from a cluster of thematically related documents, where the given documents comple- ment and overlap each other. Multi-document sum- marization involves identifying important informa- tion and filtering out redundant information from multiple input sources. There are two primary methodologies for multi- document summarization: extractive and abstrac- tive. Extractive methods directly select important sentences from the original, which are relatively simple. Cao et al. (2015) rank sentences with a recursive neural network. Yasunaga et al. (2017) employ a Graph Convolutional Network (GCN) to incorporate sentence relation graphs to improve the performance for the extractive summarization. Abstractive methods can generate new words and new sentences, but it is technically more difficult than extractive methods. Some works on multi- document summarization simply concatenate multi- ple source documents into a long flat sequence and model multi-document summarization as a long sequence-to-sequence task (Liu et al., 2018; Fab- bri et al., 2019). However, these approaches don’t take the hierarchical structure of document clus- ters into account, while the too-long input often leads to the degradation in document summariza- tion (Cohan et al., 2018; Liu and Lapata, 2019). Re- cently, hierarchical frameworks have shown their effectiveness on multi-document summarization (Zhang et al., 2018; Liu and Lapata, 2019). These approaches usually use multiple encoders to model hierarchical relationships in the discourse structure, but other methods to incorporate the structural se- mantic knowledge have not been explored. The combination of extractive and abstractive has been explored in single document summarization. Chen and Bansal (2018) use the extracted sentences as the input of the abstractive summarization. Sub- ramanian et al. (2019) concatenate the extracted summary to the original document …

Content truncated to 500 words