My main research area is Computational Semantics, a subfield of Computational Linguistics with applications in Natural Language Processing. Computational semantics research aims at analysing the meaning of natural language, designing meaning representations, and developing mechanisms for reasoning over them. I am interested in both theoretical and application-oriented aspects of natural language semantics, and in cognitive aspects of language learning.

In my research, I want to help computers understand the meaning of words and utterances, and perform operations that we, humans, perform with language such as logical inference and translation. I want to help them recognize that one cannot run and sleep at the same time; that cats are pets but so can be iguanas (although less typical ones); that a great book is one I would recommend to a friend, and this in different languages.

I am a Senior Research Investigator in the Department of Computer and Information Science (CIS) of the School of Engineering and Applied Science at the University of Pennsylvania, and member of the UPenn NLP group. I am currently on leave from the French CNRS where I hold a tenure researcher position. I am also associated with the NLP group at the Department of Informatics in the Athens University of Economics and Business.


  • My survey paper "From Word Types to Tokens and Back: A Survey of Approaches to Word Meaning Representation and Interpretation" has been accepted for publication in Computational Linguistics Journal (MIT Press).
  • I defended my Habilitation à Diriger des Recherches (HDR) on "Word Meaning Representation and Interpretation in Vector Space" at the University Toulouse III - Paul Sabatier on Nov, 9, 2022.
  • Oct 2022: Honoured to have been elected Vice-President of SIGLEX (ACL Special Interest Group on the Lexicon).
  • I co-organized Deep Learning Inside Out (DeeLIO) 2022, the Third Workshop on Knowledge Extraction and Integration for Deep Learning Architectures with Ivan Vuliç and Eneko Agirre, at ACL 2022.
  • I gave an invited talk in the Cognitive Science Seminar Series at Queen Mary University of London on April 27, on "Tracking Contextual Language Models' Knowledge of Lexical Semantics".
  • I gave an invited talk at the Columbia University NLP Seminar in New York City in November 2021 where I talked about what language models know about lexical polysemy and intensity.
  • I gave an invited talk in the NYU NLP and Text-as-Data speaker series in November 2021 at New York University, on "Lexical Polysemy and Intensity in Contextualized Representations".
  • Senior Action Editor for Lexical Semantics at ACL Rolling Review (ARR). Senior Area Chair for Lexical Semantics at ACL 2023 and EACL 2021. Area Chair for Lexical Semantics at *SEM 2022, EMNLP 2021, ACL-IJCNLP 2021, ACL 2020, EMNLP 2020, ACL 2019, EMNLP-IJCNLP 2019, for Multilinguality at *SEM 2019. Program Chair at *SEM 2020. Area Chair for the EMNLP 2022 theme track “Open questions, major obstacles, and unresolved issues in NLP".
  • 2016-2021: PI of the MULTISEM: Advanced models for multilingual semantic processing
    project funded by the French National Research Agency (ANR) Young Researcher Program (JCJC).
  • Member of the SIGLEX (ACL Special Interest Group on the Lexicon) Advisory Board (2016—).

    Contact: marapi at seas dot upenn dot edu