Elamur Research⌕
☰
home / papers / 2022 / Fact Checking with Insufficient Evidence

Fact Checking with Insufficient Evidence

Paper · 2022 · Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma et al.

Summary

Automated fact-checking (FC) systems usually output a verdict even when the evidence they receive lacks something crucial, for example when a claim is new or a knowledge source is incomplete. Atanasova et al. introduce Evidence Sufficiency Prediction, a task in which a model must recognise whether the given evidence actually supports any decision. They build an omission procedure that removes optional constituents or whole sentences while keeping the text grammatical. They then test BERT, RoBERTa and ALBERT on the reduced evidence from FEVER, HoVer and VitaminC. Human annotators judged whether each removal destroyed information needed for the verdict, which produced the diagnostic dataset SufficientFacts. The models often treated incomplete evidence as adequate. To fix this, the authors used the omission method to generate training data, labelled it through agreement of three models (tri-training), and trained with counterfactual augmentation (CAD) or a contrastive loss (CL). Both clearly improved sufficiency detection and gave modest gains in ordinary verdict accuracy. The work points toward FC systems that abstain rather than guess.

Key points

  • Detection varies by what is removed: models identified missing evidence only 21% of the time when adverbial modifiers were omitted, versus 63% for omitted date modifiers.
  • Training gains: omission-based augmentation with tri-training improved Evidence Sufficiency Prediction by up to 17.8 F1 and standard FC performance by up to 2.6 F1.
  • Bias reduction: CAD/CL training reduced the claim–evidence word-overlap bias on HoVer (61%→68%) and FEVER (63%→65%). The authors found CAD more effective than CL at preventing spurious correlations.
  • Open resources: SufficientFacts and the code are public on Hugging Face (copenlu/sufficient_facts) and GitHub (copenlu/sufficient_facts).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of CopenhagenCopenhagen · Denmark115 works · 15,292 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksSocial Sciences · 1,772 worksSociology and Political Science · 577 works

Cite

Cite as Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma and Isabelle Augenstein. 2022. Fact Checking with Insufficient Evidence. Transactions of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/tacl_a_00486

@article{atanasova2022fact,
  title = {{Fact Checking with Insufficient Evidence}},
  author = {Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma and Isabelle Augenstein},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2022},
  doi = {10.1162/tacl\_a\_00486},
  url = {https://doi.org/10.1162/tacl_a_00486}
}

References

40 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Bayu Distiawan, Gerhard Weikum, Jianzhong Qi, and Rui Zhang. 2019. Neural relation extraction for knowledge base enrichment. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 229–240. find
  2. Pepa Atanasova, Dustin Wright, and Isabelle Augenstein. 2020. Generating label cohesive and well-formed adversarial claims. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3168–3177, Online. Association for Computational Linguistics. https://… find
  3. Yanai Elazar, Shauli Ravfogel, Alon Jacovi, and Yoav Goldberg. 2021. Amnesic probing: Behavioral explanation with amnesic counterfactuals. Transactions of the Association for Computational Linguistics, 9:160–175. https://doi.org/10.1162/tacl a 00359 ↗
  4. Isabelle Augenstein. 2021. Towards Explainable Fact Checking. Dr. Scient. thesis, University of Copenhagen, Faculty of Science. find
  5. Paul L. Garvin. 1958. Syntactic units and operations. In Proceedings of the 8th International Congress of Linguists at Oslo, pages 58–59. De Gruyter Mouton. find
  6. Ann Bies, Justin Mott, and Colin Warner. 2015. English news text treebank: Penn treebank revised. https://doi.org/10.35111/m5b6-4m82 ↗
  7. Christopher Hidey, Tuhin Chakrabarty, Tariq Alhindi, Siddharth Varia, Kriste Krstovski, Mona Diab, and Smaranda Muresan. 2020. DeSePtion: Dual sequence prediction and adversarial examples for improved fact-checking. In Proceedings of the 58th Annual Meeting of the Association for Computational Lingu… find
  8. Kersti Börjars and Kate Burridge. 2019. Introducing English Grammar. Routledge. https://doi.org/10.4324/9780429023293 — [doi:10.4324/9780429023293](https://doi.org/10.4324/9780429023293) ↗
  9. Keith Brown, Jim Miller, and James Edward Miller. 1991. Syntax: A Linguistic Introduction to Sentence Structure. Psychology Press. find
  10. Noel Burton-Roberts. 2016. Analysing Sentences: An Introduction to English Syntax. Routledge. https://doi.org/10.4324/9781315646046 ↗
  11. Jiaao Chen, Zichao Yang, and Diyi Yang. 2020. MixText: Linguistically-informed interpolation of hidden space for semi-supervised text classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2147–2157, Online. Association for Computational Lin…
  12. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  13. Rodney Huddleston and Geoffrey Pullum. 2005. The Cambridge grammar of the English language. Zeitschrift für Anglistik und Amerikanistik, 53(2):193–194. https://doi.org/10.1515/zaa-2005-0209 — [doi:10.1515/zaa-2005-0209](https://doi.org/10.1515/zaa-2005-0209) ↗
  14. Mohit Iyyer, John Wieting, Kevin Gimpel, and Luke Zettlemoyer. 2018. Adversarial example generation with syntactically controlled paraphrase networks. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vo…
  15. Yichen Jiang, Shikha Bordia, Zheng Zhong, Charles Dognin, Maneesh Singh, and Mohit Bansal. 2020. HoVer: A dataset for many-hop fact extraction and claim verification. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3441–3460, Online. Association for Computational Ling…
  16. Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692.
  17. Divyansh Kaushik, Eduard Hovy, and Zachary Lipton. 2020. Learning the difference that makes a difference with counterfactually-augmented data. In International Conference on Learning Representations. https://openreview.net/forum?id=Sklgs0NFvr Ji-Seong Kim and Key-Sun Choi. 2021. Fact checking in kn… ↗
  18. Nishtha Madaan, Inkit Padhi, Naveen Panwar, and Diptikalyan Saha. 2021. Generate your counterfactuals: Towards controlled counterfactual generation for text. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 13516–13524. https://ojs.aaai.org/index.php/AAAI/article /… ↗
  19. Jiho Kim, Kijong Han, and Key-Sun Choi. 2018. KBCNN: A knowledge base completion model based on convolutional neural networks. In Annual Conference on Human and Language Technology, pages 465–469. Human and Language Technology. find
  20. Ryan Kiros, Yukun Zhu, Russ R. Salakhutdinov, Richard Zemel, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. 2015. Skip-thought vectors. In Advances in neural information processing systems, pages 3294–3302. https://proceedings.neurips.cc/paper/2015/file/f442d33fa06832082290ad8544a 8da27-Paper… ↗
  21. Nikita Kitaev and Dan Klein. 2018. Constituency parsing with a self-attentive encoder. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2676–2686. https://doi.org/10.18653/v1/P18 -1249 ↗
  22. Malte Ostendorff, Nils Rethmeier, Isabelle Augenstein, Bela Gipp, and Georg Rehm. 2022. Neighborhood contrastive learning for scientific document representations with citation embeddings. In arXiv:2202.06671. find
  23. Wojciech Ostrowski, Arnav Arora, Pepa Atanasova, and Isabelle Augenstein. 2021. Multi-hop fact checking of political claims. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pages 3892–3898. International Joint Conferences on Artificial Intelligenc… find
  24. Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A lite BERT for self-supervised learning of language representations. In International Conference on Learning Representations. https://openreview.net/forum?id=H1eA7AEtvS Markus Leippold and T… ↗
  25. Ankur Parikh, Oscar Täckström, Dipanjan Das, and Jakob Uszkoreit. 2016. A decomposable attention model for natural language inference. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2249–2255, Austin, Texas. Association for Computational Linguistic…
  26. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, lation models with monolingual data. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 86–96, Berlin, Germany. Association for Computational Lin… find
  27. Yanru Qu, Dinghan Shen, Yelong Shen, Sandra Sajeev, Weizhu Chen, and Jiawei Han. 2021. CoDA: Contrast-enhanced and diversity-promoting data augmentation for natural language understanding. In International Conference on Learning Representations. https://openreview.net/forum?id =Ozk9MrX1hvA Damien Te… — [doi:10.1007/978-3-030-58607-2](https://doi.org/10.1007/978-3-030-58607-2) ↗
  28. Nils Rethmeier and Isabelle Augenstein. 2021. A primer on contrastive pretraining in language processing: Methods, lessons learned and perspectives. arXiv preprint arXiv:2102.12982. — [arXiv:2102.12982](https://arxiv.org/abs/2102.12982) find
  29. James Thorne and Andreas Vlachos. 2021. Evidence-based factual error correction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3298–3309, Online. Ass… find
  30. Nils Rethmeier and Isabelle Augenstein. 2022. Long-tail zero and few-shot learning via contrastive pretraining on and for small data. In Proceedings of AAAI 2022 Workshop on Artificial Intelligence with Biased or Scarce Data (AIBSD 2022). find
  31. Mattia Samory, Indira Sen, Julian Kohne, Fabian Flöck, and Claudia Wagner. 2021. Call me sexist, but...: Revisiting sexism detection using psychological scales and adversarial samples. In Proceedings of the Fifteenth International Conference on Web and Social Media. AAAI Press. https://ojs.aaai.org… ↗
  32. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vo…
  33. Tal Schuster, Adam Fisch, and Regina Barzilay. 2021. Get your vitamin C! Robust fact verification with contrastive evidence. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 624–643, Online. Assoc…
  34. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2019. Evaluating adversarial attacks against multiple fact verification systems. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natur… find
  35. Tal Schuster, Darsh Shah, Yun Jie Serene Yeo, Daniel Roberto Filizzola Ortiz, Enrico Santus, and Regina Barzilay. 2019. Towards debiasing fact verification models. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on…
  36. Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2019. Super-GLUE: A stickier benchmark for general-purpose language understanding systems. In Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Improving neural machine tran… — [arXiv:2203.12990](https://arxiv.org/abs/2203.12990) find
  37. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 353–355,…
  38. Xing Wu, Shangwen Lv, Liangjun Zang, Jizhong Han, and Songlin Hu. 2019. Conditional BERT contextual augmentation. In Computational Science – ICCS 2019, pages 84–95, Cham. Springer International Publishing. https://doi.org/10.1007/978-3-030-22747-0 7 — [doi:10.1007/978-3-030-22747-0](https://doi.org/10.1007/978-3-030-22747-0) ↗
  39. Zhi-Hua Zhou and Ming Li. 2005. Tri-training: Exploiting unlabeled data using three classifiers. IEEE Transactions on Knowledge and Data Engineering, 17(11):1529–1541. https://doi.org/10.1109/TKDE.2005 .186 — [doi:10.1109/tkde.2005](https://doi.org/10.1109/tkde.2005) ↗
  40. Dustin Wright, David Wadden, Kyle Lo, Bailey Kuehl, Arman Cohan, Isabelle Augenstein, and Lucy Lu Wang. 2022. Generating scientific claims for zero-shot scientific fact find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/atanasova-2022-fact-checking-insufficient-evidence/