Skip to main content
Log in

Habilitation Abstract: Towards Explainable Fact Checking

  • Dissertation and Habilitation Abstracts
  • Published:
KI - Künstliche Intelligenz Aims and scope Submit manuscript

Abstract

With the substantial rise in the amount of mis- and disinformation online, fact checking has become an important task to automate. This article is a summary of a habilitation (doctor scientiarum) thesis submitted to the University of Copenhagen, which was sucessfully defended in December 2021 (Augenstein in Towards Explainable Fact Checking. Dr. Scient. thesis, University of Copenhagen, Faculty of Science, 2021). The dissertation addresses several fundamental research gaps within automatic fact checking. The contributions are organised along three verticles: (1) the fact-checking subtask they address; (2) methods which only require small amounts of manually labelled data; (3) methods for explainable fact checking, addressing the problem of opaqueness in the decision-making of black-box fact checking models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1

Similar content being viewed by others

References

  1. Atanasova P, Simonsen JG, Lioma C, Augenstein I (2020) A diagnostic study of explainability techniques for text classification. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). https://www.aclweb.org/anthology/2020.emnlp-main.263. Accessed 1 May 2022

  2. Atanasova P, Simonsen JG, Lioma C, Augenstein I (2020) Generating fact checking explanations. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). https://www.aclweb.org/anthology/2020.acl-main.656. Accessed 1 May 2022

  3. Atanasova P, Wright D, Augenstein I (2020) Generating label cohesive and well-formed adversarial claims. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). https://www.aclweb.org/anthology/2020.emnlp-main.256. Accessed 1 May 2022

  4. Augenstein I (2021) Towards Explainable Fact Checking. Dr. Scient. thesis, University of Copenhagen, Faculty of Science. https://arxiv.org/abs/2108.10274. Accessed 1 May 2022

  5. Augenstein I, Lioma C, Wang D, Chaves Lima L, Hansen C, Hansen C, Simonsen JG (2019) MultiFC: a real-world multi-domain dataset for evidence-based fact checking of claims. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hong Kong, China. https://www.aclweb.org/anthology/D19-1475. Accessed 1 May 2022

  6. Augenstein I, Rocktäschel T, Vlachos A, Bontcheva K (2016) Stance detection with bidirectional conditional encoding. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP). Austin, Texas. https://www.aclweb.org/anthology/D16-1084. Accessed 1 May 2022

  7. Augenstein I, Ruder S, Søgaard A (2018) Multi-task learning of pairwise sequence classification tasks over disparate label spaces. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Volume 1 (Long Papers). New Orleans, Louisiana. https://www.aclweb.org/anthology/N18-1172. Accessed 1 May 2022

  8. Bjerva J, Kouw W, Augenstein I (2020) Back to the future – temporal adaptation of text representations. In: Proceedings of the AAAI Conference on Artificial Intelligence. https://ojs.aaai.org/index.php/AAAI/article/view/6240. Accessed 1 May 2022

  9. Wright D, Augenstein I (2020) Claim check-worthiness detection as positive unlabelled learning. Findings of the association for computational linguistics: EMNLP. Association for Computational Linguistics, Stroudsburg, pp 476–488. https://doi.org/10.18653/v1/2020.findings-emnlp.43

    Chapter  Google Scholar 

  10. Wright D, Augenstein I ((2020) Transformer based multi-source domain adaptation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Online. https://www.aclweb.org/anthology/2020.emnlp-main.639

  11. Zubiaga A, Kochkina E, Liakata M, Procter R, Lukasik M, Bontcheva K, Cohn T, Augenstein I (2018) Discourse-aware rumour stance classification in social media using sequential classifiers. Inf Process Manag 54(2):273–290. Accessed 1 May 2022

    Article  Google Scholar 

Download references

Acknowledgements

The research described in the thesis was partially funded by several grants from the European Commission: the PHEME FP7 project (grant No. 611233), the Marie Skłodowska-Curie project under grant agreement No 801199, ERC Starting Grant Number 313695 and QUARTZ (721321, EU H2020 MSCA-ITN).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Isabelle Augenstein.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Augenstein, I. Habilitation Abstract: Towards Explainable Fact Checking. Künstl Intell 36, 255–258 (2022). https://doi.org/10.1007/s13218-022-00774-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13218-022-00774-6

Keywords

Navigation