mlsanityData to 7 Oct 2026

Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News

arXiv 2104.12918 ↗First posted 27 Apr 2021cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

In this paper, we explore the construction of natural language explanations for news claims, with the goal of assisting fact-checking and news evaluation applications. We experiment with two methods: (1) an extractive method based on Biased TextRank -- a resource-effective unsupervised graph-based algorithm for content extraction; and (2) an abstractive method based on the GPT-2 language model. We perform comparative evaluations on two misinformation datasets in the political and health news domains, and find that the extractive method shows the most promise.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 27 Apr 2021.

Builds on

18 of 26 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  6. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  7. 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 428
  8. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  9. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 209
  10. 2017Automatic Detection of Fake Newscited by 145
  11. 2020Generating Fact Checking Explanationscited by 132
  12. 2019Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systemscited by 110
6 more
  1. 2020GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Mediacited by 108
  2. 2018Automated Fact Checking: Task formulations, methods and future directionscited by 96
  3. 2020NILE : Natural Language Inference with Faithful Natural Language Explanationscited by 96
  4. 2020Consistency of a Recurrent Language Model With Respect to Incomplete Decodingcited by 54
  5. 2020Generating Fact Checking Briefscited by 50
  6. 2020Biased TextRank: Unsupervised Graph-Based Content Extractioncited by 14

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 2; 2024: 2.

8 papers.

  1. 2022End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Modelscited by 105
  2. 2022Matching Tweets With Applicable Fact-Checks Across Languagescited by 15
  3. 2023Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AIcited by 9
  4. 2023Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Modelscited by 7
  5. 2021Like Article, Like Audience: Enforcing Multimodal Correlations for Disinformation Detectioncited by 2
  6. 2024Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functionscited by 2
  7. 2021Assessing Effectiveness of Using Internal Signals for Check-Worthy Claim Identification in Unlabeled Data for Automated Fact-Checkingcited by 1
  8. 2024Generating Zero-shot Abstractive Explanations for Rumour Verificationcited by 1