Pepa Kostadinova Atanasova

• Presentation
• Research outputs
• Most downloaded

I am a postdoc researcher at the CopeNLU group NLP section. My current research focus is explainability for machine learning models, encompassing natural language explanations, post-hoc explainability methods, and adversarial attacks as well as the principled evaluation of existing explainability techniques. My work is currently centred on the application area of knowledge-intensive and complex reasoning natural language tasks, such as fact checking and question answering.

Selected publications

1. Published

   Faithfulness Tests for Natural Language Explanations

   Atanasova, Pepa Kostadinova, Camburu, O. M., Lioma, Christina, Lukasiewicz, T., Simonsen, Jakob Grue & Augenstein, Isabelle, 2023, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics (ACL), p. 283-294 12 p.

   Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

2. Published

   Accountable and Explainable Methods for Complex Reasoning over Text

   Atanasova, Pepa Kostadinova, 2022, 226 p.

   Research output: Book/Report › Ph.D. thesis › Research

3. Published

   Diagnostics-Guided Explanation Generation

   Atanasova, Pepa Kostadinova, Simonsen, Jakob Grue, Lioma, Christina & Augenstein, Isabelle, 2022, In: Proceedings of the International Joint Conference on Artificial Intelligence. 36, 10, p. 10445-10453.

   Research output: Contribution to journal › Conference article › Research

4. Published

   Fact Checking with Insufficient Evidence

   Atanasova, Pepa Kostadinova, Simonsen, Jakob Grue, Lioma, Christina & Augenstein, Isabelle, 2022, In: Transactions of the Association for Computational Linguistics. 10, p. 746-763

   Research output: Contribution to journal › Journal article › Research › peer-review

5. Published

   Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing

   Jolly, S., Atanasova, Pepa Kostadinova & Augenstein, Isabelle, 2022, In: Information (Switzerland). 13, 10, p. 1-18 500.

   Research output: Contribution to journal › Journal article › Research › peer-review

6. Published

   Multi-Hop Fact Checking of Political Claims

   Ostrowski, W., Arora, Arnav, Atanasova, Pepa Kostadinova & Augenstein, Isabelle, 2021, Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence, Vol. CoRR 2020. p. 3892-3898 (arXiv.org).

   Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

7. Published

   A Diagnostic Study of Explainability Techniques for Text Classification

   Atanasova, Pepa Kostadinova, Simonsen, Jakob Grue, Lioma, Christina & Augenstein, Isabelle, 2020, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, p. 3256-3274

   Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

8. Published

   Generating Fact Checking Explanations

   Atanasova, Pepa Kostadinova, Simonsen, Jakob Grue, Lioma, Christina & Augenstein, Isabelle, 2020, : Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, p. 7352-7364

   Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

9. Published

   Generating Label Cohesive and Well-Formed Adversarial Claims

   Atanasova, Pepa Kostadinova, Wright, Dustin & Augenstein, Isabelle, 2020, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, p. 3168-3177

   Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review