Extractive Summarization as Text Matching

By Ming Zhong, Pengfei Liu, Yiran Chen, Danqing Wang, Xipeng Qiu, Xuanjing Huang. 2020

521 citations recorded by the source corpus.

This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems. Instead of following the commonly used framework of extracting sentences individually and modeling the relationship between sentences, we formulate the extractive summarization task as a semantic text matching problem, in which a source document and candidate summaries will be (extracted from the original text) matched in a semantic space. Notably, this paradigm shift to semantic matching framework is well-grounded in our comprehensive analysis of the inherent gap between sentence-level and summary-level extractors based on the property of the dataset. Besides, even instantiating the framework with a simple form of a matching model, we have driven the state-of-the-art extractive result on CNN/DailyMail to a new level (44.41 in ROUGE-1). Experiments on the other five datasets also show the effectiveness of the matching framework. We believe the power of this matching-based summarization framework has not been fully exploited. To encourage more instantiations in the future, we have released our codes, processed dataset, as well as generated summaries in https://github.com/maszhongming/MatchSum.

Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing

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

In Molecular Biology

In Natural Language Processing

Citations in the corpus

Prefix-Tuning: Optimizing Continuous Prompts for Generation (2021, methodology): “For extractive and abstractive summarization, researchers fine-tune masked language models (e.g., BERT; Devlin et al., 2019) and encode-decoder models (e.g., BART; Lewis et al., 2020), respectively (Zhong et al., 2020; Liu and Lapata, 2019; Raffel et al., 2020).”
Measuring Attribution in Natural Language Generation Models (2021, methodology): “First, we used MatchSum (Zhong et al., 2020), a state-of-theart extractive summarization model.”
Pre-trained models for natural language processing: A survey (2020, background): “[236] proposed a novel summary-level framework MATCHSUM and conceptualized extractive summarization as a semantic text matching problem.”
Detecting Hallucinated Content in Conditional Neural Sequence Generation (2020, methodology): “For the extractive system, we use the recent proposed MatchSum (Zhong et al., 2020) as the distillation model.”
Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation (2022, methodology): “MatchSum (Zhong et al., 2020) propose a summary-level extractive system using semantic match between the extracted summary and the source document.”
Dialect Diversity in Text Summarization on Twitter (2020, methodology): “Beyond unsupervised approaches, supervised techniques for summarization classify whether a sentence is important to the summary or not [30, 42, 51, 71, 72].”
Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarization (2021, background): “…development of neural networks in text summarization (Liu and Lapata, 2019; Liu, 2019; Zhong et al., 2019; Zhang et al., 2019; Lewis et al., 2019; Zhong et al., 2020; Liu and Liu, 2021), especially the use of contextualized pre-trained models (Devlin et al., 2019; Lewis et al., 2019), the…”
TLDR: Extreme Summarization of Scientific Documents (2020, methodology): “For our supervised baselines, we use BERTSUMEXT (Liu and Lapata, 2019), which uses BERT as a sentence encoder augmented with inter-sentence Transformer layers to capture interactions, and MatchSum (Zhong et al., 2020), which uses a BERT Siamese network to score whole summaries.”
Automatic Text Evaluation through the Lens of Wasserstein Barycenters (2021, background): “, 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 al., 2018).”
Heterogeneous Graph Neural Networks for Extractive Document Summarization (2020, methodology): “Recently, pre-trained language models are also applied in summarization for contextual word representations (Zhong et al., 2019a; Liu and Lapata, 2019b; Xu et al., 2019; Zhong et al., 2020).”
Re-evaluating Evaluation in Text Summarization (2020, background): “We use CNN-LSTM-BiClassiﬁer (CLSTM-SL; Kedzie et al. (2018)), Latent (Zhang et al., 2018), Ban-ditSum (Dong et al., 2018), REFRESH (Narayan et al., 2018), NeuSum (Zhou et al., 2018), HIBERT (Zhang et al., 2019b), Bert-Sum-Ext (Liu and Lapata, 2019a), CNN-Transformer-BiClassiﬁer (CTrans-SL; Zhong et ”
GSum: A General Framework for Guided Neural Abstractive Summarization (2020, methodology): “At test time, we use pretrained extractive summarization models (BertExt (Liu and Lapata, 2019) or Match-Sum (Zhong et al., 2020) in our experiments) to perform automatic prediction.”
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization (2021, background): “Most prior work in text summarization (Rush et al., 2015; Chopra et al., 2016; Nallapati et al., 2016; See et al., 2017; Celikyilmaz et al., 2018; 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”
RefSum: Refactoring Neural Summarization (2021, methodology): “Learning Objective We use a ranking loss to learn the parameter Θ refactor , inspired by the assumption (Zhong et al., 2020) that a good candidate summary should be as close with the source document as possible.”
Multi-document Summarization via Deep Learning Techniques: A Survey (2020, background): “Among the reviewed papers [2, 85, 94, 122, 147, 188], multiple works adopt pre-trained LMs for MDS and achieve promising improvements.”
How well do you know your summarization datasets? (2021, unknown): “Apart from the improvements in the summarization model architectures (Zhang et al., 2019; Zhong et al., 2020), this growth has been aided by large-scale datasets (Nallapati et al., 2016; Narayan et al., 2018a; Sharma et al., 2019) and automatic evaluation metrics (Lin, 2004; Zhao et al., 2019; and…”
On Learning Universal Representations Across Languages (2020, methodology): “Zhong et al. (2020) formulated the extractive summarization task as a semantic text matching problem and proposed a Siamese-BERT architecture to compute the similarity between the source document and the candidate summary, which leverages the pre-trained BERT in a Siamese network structure.”