# Extractive Summarization as Text Matching

arXiv: https://arxiv.org/abs/2004.08795 · HTML: https://mlsanity.com/paper/2004.08795/

## Key facts

- Cited by 189 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2020.

## Built on by (most cited first, 30 of 189)

- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [BRIO: Bringing Order to Abstractive Summarization](https://mlsanity.com/paper/2203.16804/) (2022)
- [Compositional Exemplars for In-context Learning](https://mlsanity.com/paper/2302.05698/) (2023)
- [Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation](https://mlsanity.com/paper/2212.07981/) (2022)
- [SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization](https://mlsanity.com/paper/2106.01890/) (2021)
- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [Evaluating the Factual Consistency of Large Language Models Through News Summarization](https://mlsanity.com/paper/2211.08412/) (2022)
- [Align and Attend: Multimodal Summarization with Dual Contrastive Losses](https://mlsanity.com/paper/2303.07284/) (2023)
- [ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts](https://mlsanity.com/paper/2210.12467/) (2022)
- [Extractive Summarization via ChatGPT for Faithful Summary Generation](https://mlsanity.com/paper/2304.04193/) (2023)
- [SummIt: Iterative Text Summarization via ChatGPT](https://mlsanity.com/paper/2305.14835/) (2023)
- [A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models](https://mlsanity.com/paper/2406.11289/) (2024)
- [Prompted Opinion Summarization with GPT-3.5](https://mlsanity.com/paper/2211.15914/) (2022)
- [Paradigm Shift in Natural Language Processing](https://mlsanity.com/paper/2109.12575/) (2021)
- [Automatic Text Evaluation through the Lens of Wasserstein Barycenters](https://mlsanity.com/paper/2108.12463/) (2021)
- [Coherence boosting: When your pretrained language model is not paying enough attention](https://mlsanity.com/paper/2110.08294/) (2021)
- [Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metrics](https://mlsanity.com/paper/2204.10216/) (2022)
- [InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation](https://mlsanity.com/paper/2112.01589/) (2021)
- [Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization](https://mlsanity.com/paper/2209.03549/) (2022)
- [Sequence Level Contrastive Learning for Text Summarization](https://mlsanity.com/paper/2109.03481/) (2021)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information](https://mlsanity.com/paper/2203.09629/) (2022)
- [RefSum: Refactoring Neural Summarization](https://mlsanity.com/paper/2104.07210/) (2021)
- [DiffuSum: Generation Enhanced Extractive Summarization with Diffusion](https://mlsanity.com/paper/2305.01735/) (2023)
- [OASum: Large-Scale Open Domain Aspect-based Summarization](https://mlsanity.com/paper/2212.09233/) (2022)
- [CoNT: Contrastive Neural Text Generation](https://mlsanity.com/paper/2205.14690/) (2022)

## Abstract (arXiv)

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.