--- title: "Christina Lioma — author profile and papers" description: "Christina Lioma, University of Copenhagen: 3 papers on Elamur Research (2019–2020), h-index 23 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/christina-lioma/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/christina-lioma/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Christina Lioma # Christina Lioma Christina Lioma works in natural language processing, with a focus on automated fact checking and the interpretability of text classifiers. Lioma's papers here ask two related questions. The first is how claims made in public can be checked against real-world evidence. The second is how the decisions of neural models can be made understandable to the people who use them. The methods include building datasets from journalistic fact checking sources, multi-task learning, and transformer-based models for classification and sentence selection. The most cited of these papers, [MultiFC](https://md.research.elamur.ai/free/en/papers/augenstein-2019-multifc-real-world-multi-domain/), assembles genuine claims from fact checking websites together with their verdicts, metadata and search-engine evidence. Since each site uses its own label scheme, it treats every source as a separate domain and frames veracity prediction as a multi-task problem. [A Diagnostic Study of Explainability Techniques for Text Classification](https://md.research.elamur.ai/free/en/papers/atanasova-2020-diagnostic-study-explainability-techniques-text/) defines a set of properties, each with an automatic measure, for comparing gradient-, perturbation- and simplification-based saliency methods. [Generating Fact Checking Explanations](https://md.research.elamur.ai/free/en/papers/atanasova-2020-generating-fact-checking-explanations/) turns the manual task of justifying a verdict into extractive summarisation, selecting sentences from PolitiFact reports that approximate the journalists' own explanations. The papers here date from 2019 and 2020. The later ones shift from predicting whether claims are true toward explaining model outputs, a line that connects fact checking with [Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/). Lioma is based at the [University of Copenhagen](https://md.research.elamur.ai/free/en/universities/university-of-copenhagen/). Earlier bylines list the [University of Stuttgart](https://md.research.elamur.ai/free/en/universities/university-of-stuttgart/), [KU Leuven](https://md.research.elamur.ai/free/en/universities/ku-leuven/) and the [University of Glasgow](https://md.research.elamur.ai/free/en/universities/university-of-glasgow/). Frequent co-authors include [Isabelle Augenstein](https://md.research.elamur.ai/free/en/authors/isabelle-augenstein/), [Pepa Atanasova](https://md.research.elamur.ai/free/en/authors/pepa-atanasova/) and [Jakob Grue Simonsen](https://md.research.elamur.ai/free/en/authors/jakob-grue-simonsen/). Christina Lioma has 3 papers in our library, in 2019–2020, most of them on [Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/); often with [Isabelle Augenstein](https://md.research.elamur.ai/free/en/authors/isabelle-augenstein/), [Jakob Grue Simonsen](https://md.research.elamur.ai/free/en/authors/jakob-grue-simonsen/), [Pepa Atanasova](https://md.research.elamur.ai/free/en/authors/pepa-atanasova/). 3 papers in our library · 2019–2020 [OpenAlex](https://openalex.org/A5045425016) · [ORCID](https://orcid.org/0000-0003-2600-2701) · [Wikidata](https://www.wikidata.org/wiki/Q28865052) · [**h-index 23**](https://openalex.org/authors/A5045425016) · [199 works](https://openalex.org/works?filter=author.id:A5045425016) · [2,849 citations](https://openalex.org/works?filter=author.id:A5045425016&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/christina-lioma/#papers) · [🔗 422 citations in our library](https://md.research.elamur.ai/free/en/authors/christina-lioma/cited-by/) · [4 more in our library without a page yet](#also) · [⭐ Paper Star rank #2260](https://md.research.elamur.ai/free/en/paper-stars/page/23/#star-2260) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Christina+Lioma) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Christina+Lioma) · [dblp](https://dblp.org/search?q=Christina+Lioma) · [ACL Anthology](https://aclanthology.org/search/?q=Christina+Lioma) ## Affiliations [🎓**University of Copenhagen** Copenhagen · Denmark 2012–2026 · 127 papersEmployment*current*](https://md.research.elamur.ai/free/en/universities/university-of-copenhagen/) · [🎓**University of Glasgow** Glasgow · United Kingdom 2005–2007 · 9 papersEducation](https://md.research.elamur.ai/free/en/universities/university-of-glasgow/) · [🎓**University of Stuttgart** Stuttgart · Germany 2010–2011 · 8 papersEmployment 2010–2011](https://md.research.elamur.ai/free/en/universities/university-of-stuttgart/) · [🎓**KU Leuven** Leuven · Belgium 2008–2017 · 7 papersEmployment 2008–2009](https://md.research.elamur.ai/free/en/universities/ku-leuven/) · [🎓**Technical University of Denmark** Kongens Lyngby · Denmark 2013 · 2 papers](https://md.research.elamur.ai/free/en/universities/technical-university-of-denmark/) · [🎓**University of Konstanz** Konstanz · Germany 2009–2010Employment 2009–2010](https://md.research.elamur.ai/free/en/universities/university-of-konstanz/) · [🎓**University of Manchester** Manchester · United Kingdom Education](https://md.research.elamur.ai/free/en/universities/university-of-manchester/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Topics [Interpretability (1)](https://md.research.elamur.ai/free/en/topics/interpretability/) ## Works by year ### 2020s [**2020** 2 papers](https://md.research.elamur.ai/free/en/authors/christina-lioma/year/2020/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/augenstein-2019-multifc-real-world-multi-domain/) ## Papers The most cited first (OpenAlex and our library). 1. **[MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims](https://md.research.elamur.ai/free/en/papers/augenstein-2019-multifc-real-world-multi-domain/)** *(2019 · 318 citations)* Automatic fact checking has mostly relied on either small collections of real claims or large but synthetic resources such as FEVER, whose claims are rewritten Wikipedia sentences without real-world context. 2. **[A Diagnostic Study of Explainability Techniques for Text Classification](https://md.research.elamur.ai/free/en/papers/atanasova-2020-diagnostic-study-explainability-techniques-text/)** *(2020 · 273 citations)* Post-hoc explainability methods assign saliency scores to input words, but they often disagree with one another, and practitioners have little guidance on which method suits a given task and model. 3. **[Generating Fact Checking Explanations](https://md.research.elamur.ai/free/en/papers/atanasova-2020-generating-fact-checking-explanations/)** *(2020 · 219 citations)* Most automated fact checking research predicts whether a claim is true. The hardest step for human fact checkers, writing a justification for the verdict, has stayed manual. Atanasova et al. present the first study of producing such veracity explanations automatically. They frame it as extractive summarisation. Given… ## Also in our library 4 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 3 co-authors with a page, the most papers together first. - [Isabelle Augenstein](https://md.research.elamur.ai/free/en/authors/isabelle-augenstein/) ×3 - [Jakob Grue Simonsen](https://md.research.elamur.ai/free/en/authors/jakob-grue-simonsen/) ×3 - [Pepa Atanasova](https://md.research.elamur.ai/free/en/authors/pepa-atanasova/) ×2 ## Cited by Papers of our library cite their works 422 times (of the 140,884 papers whose bibliographies we read); [22 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/christina-lioma/cited-by/).