I work in the intersection of natural language processing, information retrieval, and machine learning. I am interested in the automatic analysis of diverse qualities of texts, such as originality, relevance, and intent; also across languages. Among the different topics, see:
- Text intent. Determining the intent of a text in terms of its propagandistic contents. See the webiste of the Propaganda Analysis Project.
- Text veracity. Analysing whether a text snippet is worth verifying and assiting the expert in the actual verification.
- Multilingual corpora. Analysing and exploiting multilingual corpora. See the website of WikiTailor.
- Text originaility. Identifying whether a text has been produced by re-use of another one.
I am (or have been) the organiser of different shared tasks on these topics:
- CheckThat! The CLEF lab Enabling Automatic Identification and Verification of Claims in Social Media (from 2018 to 2020)
- SemEval 2020 Task 11. The SemEval task on the Detection of Propaganda Techniques in News Articles (2020)
- PAN. The CLEF shared tasks on digital text forensics and stylometry (from 2009 to 2012; and 2014)
