Heterogeneous Graph Neural Networks for Extractive Document Summarization

By Danqing Wang, Pengfei Liu, Yining Zheng, Xipeng Qiu, Xuanjing Huang. Annual Meeting of the Association for Computational Linguistics, 2020

300 citations recorded by the source corpus.

As a crucial step in extractive document summarization, learning cross-sentence relations has been explored by a plethora of approaches. An intuitive way is to put them in the graph-based neural network, which has a more complex structure for capturing inter-sentence relationships. In this paper, we present a heterogeneous graph-based neural network for extractive summarization (HETERSUMGRAPH), which contains semantic nodes of different granularity levels apart from sentences. These additional nodes act as the intermediary between sentences and enrich the cross-sentence relations. Besides, our graph structure is flexible in natural extension from a single-document setting to multi-document via introducing document nodes. To our knowledge, we are the first one to introduce different types of nodes into graph-based neural networks for extractive document summarization and perform a comprehensive qualitative analysis to investigate their benefits. The code will be released on Github.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/3b05f71ae4532aa4e66d6bb6e88a763e4770c2a7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization (2021, background): “…Chen and Bansal, 2018; Zhong et al., 2019a; Xu and Durrett, 2019; Liu and Lapata, 2019; Lebanoff et al., 2019; Cho et al., 2019; Zhong et al., 2020; Wang et al., 2020; Xu et al., 2019; Jia et al., 2020) investigate how to generate better summaries on news article data, such as CNN/DailyMail…”
Extractive Summarization as Text Matching (2020, methodology): “, 2019) or GNN (Wang et al., 2020) as encoder, non-auto-regressive (Narayan et al.”
Automatic Text Evaluation through the Lens of Wasserstein Barycenters (2021, unknown): “…et al., 2018; Dong et al., 2019; Liu and Lapata, 2019; Chen and Bansal, 2018; See et al., 2017) and 14 abstractive systems (Zhong et al., 2020; Wang et al., 2020; Zhong et al., 2019; Liu and Lapata, 2019; Zhou et al., 2018; Narayan et al., 2018; Dong et al., 2019; Kedzie et al., 2018; Zhou et…”
AgreeSum: Agreement-Oriented Multi-Document Summarization (2021, methodology): “In SDS tasks, Durmus et al. (2020) and Wang et al. (2020a) observe that ROUGE and BERTScore have a small correlation with summary factuality.”
How well do you know your summarization datasets? (2021, unknown): “…et al., 2017) For CNN/DM, we use the outputs of 11 top-performing summarization systems collected by Bhandari et al. (2020) 4 : (1) H ETER G RAPH (Wang et al., 2020), (2) M ATCH S UMM (Lewis et al., 2020), (3) R EFRESH (Narayan et al., 2018b) , (4) T WO S TAGE RL (Song et al., 2020), (5) N…”
RefSum: Refactoring Neural Summarization (2021, background): “6 In details, for §5.7 we use the following systems: pointer-generator+coverage (See et al., 2017), REFRESH (Narayan et al., 2018b), fastAbsRL-rank (Chen and Bansal, 2018), CNN-LSTM-BiClassiﬁer (Kedzie et al., 2018), CNN-Transformer-BiClassiﬁer (Zhong et al., 2019), CNN-Transformer-Pointer (Zhong et”
BARTScore: Evaluating Generated Text as Text Generation (2021, unknown): “Extractive Systems E1: BanditSum [11]; E2: Refresh [49]; E3: NeuSum [81]; E4: LSTM-PN-RL [80]; E5: BERT-TF-SL [80]; E6: BERT-TF-PN [80]; E7: BERT-LSTM-PN-RL [80]; E8: BERT-LSTM-PN [80]; E9: HeterGraph [69]; E10: MatchSum [79].”
Multi-document Summarization via Deep Learning Techniques: A Survey (2020, methodology): “Existing hierarchical concatenation methods either perform document-level condensing in a cluster separately [4] or process documents in word/sentence level inside a document cluster [6, 114, 160].”