Open Paleoslavic data sets and corpora as a catalyst for reproducible and extensible research
Conference talk, XVIIth International Congress of Slavists, Paris, France
[Joint work with Olga Lyashevskaya and Hanne Eckhoff]
Talks and presentations
Updated on 18-8-2025
Early Slavic participle clauses and their typological parallels
Conference talk, International Conference on Historical Linguistics, Santiago, Chile
Using AI forecast of satellite imagery to improve solar generation forecasts
Conference talk, EGU General Assembly, Vienna, Austria
[Joint work with Fulton, J., Efremova, N., Simpson, N., Fenton, I., Corcoran, E., Robinson, J., Asthana, M., Yatsyshin, P.]
GramTypix: a Python pipeline for subtoken-based language typology and probabilistic semantic mapping from parallel corpora
Conference talk, Digital Humanities Conference (DH2024), Arlington, Virginia
Part of the DH Inside Out workshop organized by the DH Tech special interest group. Download the abstract.
Mapping ‘when’-clauses in Latin American and Caribbean languages: an experiment in subtoken-based typology
Conference talk, Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP), Mexico City (Mexico)
Language typologies using parallel text data and geo-statistics
Invited talk, Linguistic Data Subcommunity, Office for Statistics Regulation (UK Statistics Authority), Remote
Temporal clauses in Old Church Slavonic and Ancient Greek: typological differences emerged from massively parallel corpora
Conference talk, 56th Annual Meeting of the Societas Linguistica Europaea (SLE), Athens (Greece)
[Joint work with Dag Haug]
Metadata enrichment in the living with machines project: User-focused collaborative database development in a digital humanities context
Poster session, ADHO Digital Humanities Conference (DH2023), Graz (Austria)
[Joint work with Kalle Westerling, David Beavan, Kaspar Beelen, Mariona Coll Ardanuy, Timothy Hobson, Christina Last, Griffith Reese, and Like Hare]
Diachronic and diatopic word embeddings from British historical newspapers
Poster session, 12th AIUCD (Convegno dell’Associazione per l’Informatica Umanistica e la Cultura Digitale)., Siena (Italy)
[Joint work with Barbara McGillivray]
T*xt as data: A sneak peek into the possibilities unleashed by computational methods
Invited talk, Creative & Heritage Innovation Challenge Workshop, Oxford (UK)
The Language of Mechanisation (Circle-U prize)
Plenary talk, Conference on interdisciplinary and transdisciplinary research for sustainable development, UCLouvain, Louvain-la-neuve (Belgium)
Machines in the media: semantic change in the lexicon of mechanization in 19th-century British newspapers
Conference talk, The 2nd International Workshop on Natural Language Processing for Digital Humanities (NLP4DH), Taipei, Taiwan
[Joint paper with Barbara McGillivray]
Evaluating Language Models for Ancient Greek: Design, Challenges, and Future Directions
Conference talk, International Conference on Historical Linguistics 2022 (ICHL25)", University of Oxford (UK)
[Joint paper with Barbara McGillivray, Malvina Nissim, Saskia Peels-Matthey & Silvia Stopponi]
Deep impact: A study on the impact of data papers and datasets in the humanities and social sciences
Plenary talk, SciDataCon, Seoul, Korea
[Joint paper with Marton Ribary, Mandy Wigdorowitz, Eleonora Zordan, and Barbara McGillivray]
Historic machines from ‘prams’ to ’Parliament’: new avenues for collaborative linguistic research
Conference talk, DH Benelux 2022: RE-MIX. Creation and alteration in DH, University of Luxembourg
[Joint paper with Mia Ridge, Giorgia Tolfo, Kalle Westerling and Barbara McGillivray] Download the abstract.
Open data and data publishing in the humanities and social sciences
Discussion group, Humanities and Data Science Discussion Group, The Alan Turing Institute (London, UK)
Le Journal of Open Humanities Data (JOHD): enjeux et défis dans la publication de data papers pour les sciences humaines
Round table, DHNord2021 "Le data paper: une nouvelle forme de publication scienti que en SHS", Held online
[Joint paper with Paola Marongiu, Marton Ribary and Barbara McGillivray]
Tackling lack of linguistic data with HTR: A specialized model for the transcription of Serbian Church Slavonic manuscripts
Conference talk, El’ Manuscript Conference 2021, Freiburg, DE (held online)
Same question, different annotation depths: early Slavonic dative absolute in deeply versus shallowly annotated treebanks
Conference talk, Grammar & Corpora International Conference, Kraków (Poland)
Exploiting Cross-Dialectal Gold Syntax for Low-Resource Historical Languages: Towards a Generic Parser for Pre-Modern Slavic
Conference talk, Computational Humanities Research Workshop, Amsterdam (The Netherlands)
The associated article was published in the CHR proceedings. Download the paper.
Participial free adjuncts in early Slavic treebanks: The discourse properties of the dative absolute
Conference talk, Slavic Linguistics Society (SLS) Conference, Bloomington, IN, USA (held virtually)
Challenges in historical corpus analyses of discourse relations: a case study in Old Church Slavonic
Conference talk, Corpora & Discourse International Conference, University of Sussex (UK)