Forskningsresultat per år
Forskningsresultat per år
Personlig profil
Information om forskning och undervisning
I work as a post-doc researcher at the Department of Digital Humanities at the University of Helsinki. My main research interests are resource building and NLP for low-resource languages, as well as corpus-based studies in dependency syntax.
Utbildning / akademisk kvalifikation
Linguistics and NLP, PhD, Université Toulouse Jean Jaurès
2014 → 2018
Tilldelningsdatum: 20 juni 2018
Lexicography and NLP, M.Sc., Université de Lille 3
2012 → 2013
Vetenskapsgrenar
- 6121 Språkvetenskaper
- 113 Data- och informationsvetenskap
Internationellt och inhemskt samarbete
Publikationer och projekt inom de senaste fem åren.
-
A Gold Standard with Silver Linings: Scaling Up Annotation for Distinguishing Bosnian, Croatian, Montenegrin and Serbian
Miletić, A. & Miletić, F., 2024, Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024. Balloccu, S., Belz, A., Huidrom, R., Reiter, E., Sedoc, J. & Thomson, C. (red.). Paris: European Language Resources Association (ELRA), s. 36-46 11 s. (International conference on computational linguistics)(LREC proceedings).Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Konferensbidrag › Vetenskaplig › Peer review
Öppen tillgångFil -
Automated Extraction and Analysis of Sentences under Production: A Theoretical Framework and Its Evaluation
Ulasik, M. A. & Miletić, A., 22 feb. 2024, I: Languages . 9, 3, 33 s., 71.Forskningsoutput: Tidskriftsbidrag › Artikel › Vetenskaplig › Peer review
Öppen tillgång -
Explainability of machine learning approaches in forensic linguistics: a case study in geolinguistic authorship profiling
Roemling, D., Scherrer, Y. & Miletic Haddad, A., juli 2024, Proceedings of the 1st International Conference on NLP & AI for Cyber Security. s. 10-16 7 s.Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Konferensbidrag › Vetenskaplig › Peer review
Öppen tillgångFil -
Loflòc: A Morphological Lexicon for Occitan using Universal Dependencies
Vergez-Couret, M., Bras, M., Miletić, A. & Poujade, C., 2024, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S. & Xue, N. (red.). Paris: European Language Resources Association (ELRA), s. 10716-10724 9 s. (International conference on computational linguistics )(LREC proceedings ).Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Konferensbidrag › Vetenskaplig › Peer review
Öppen tillgångFil -
VarDial Evaluation Campaign 2024: Commonsense Reasoning in Dialects and Multi-Label Similar Language Identification
Chifu, A.-G., Glavaš, G., Ionescu, R. T., Ljubešić, N., Miletic Haddad, A., Miletić, F., Scherrer, Y. & Vulić, I., 1 juni 2024, Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024). Scherrer, Y., Jauhiainen, T., Ljubešić, N., Zampieri, M., Nakov, P. & Tiedemann, J. (red.). Kerrville: The Association for Computational Linguistics, s. 1-15 15 s.Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Konferensbidrag › Vetenskaplig › Peer review
Öppen tillgångFil
Projekter
- 1 Aktiv
-
CorCoDial: CorCoDial - Corpus-based computational dialectology: exploiting machine translation techniques to extract, visualize and interpret dialectal patterns
Scherrer, Y. (Projektledare), Tiedemann, J. (Projektledare), Kuparinen, O. V. (deltagare), Mickus, T. (deltagare), Miletic Haddad, A. (deltagare), Psaltaki, E. (deltagare), Roemling, D. (deltagare), Siewert, J. (deltagare) & Siewert, J. (deltagare)
Suomen Akatemia Projektilaskutus
01/09/2021 → 31/08/2025
Projekt: Finlands Akademi: Akademiprojektsbidrag
Forskningsdatauppsättningar
-
OcWikiAnnot: Annotated Wikipedia Corpus of Occitan
Miletic Haddad, A. (Skapad av), Zenodo, 20 apr. 2023
DOI: 10.5281/zenodo.7777340, https://doi.org/10.5281/zenodo.7777340
Datauppsättning
-
OcWikiDisc: a Corpus of Wikipedia Talk Pages in Occitan
Miletic Haddad, A. (Skapad av) & Scherrer, Y. (Skapad av), Zenodo, 14 sep. 2022
DOI: 10.5281/zenodo.7079580, https://doi.org/10.5281/zenodo.7079580
Datauppsättning
Aktiviteter
- 6 !!Oral presentation
-
Model Interpretability as Error Analysis for Variation Research
Roemling, D. (!!Speaker), Scherrer, Y. (!!Speaker), Miletic Haddad, A. (!!Speaker) & Siewert, J. (!!Speaker)
11 sep. 2024Aktivitet: Typer för tal eller presentation › !!Oral presentation
Fil -
Extracting dialect-specific features from dialect classifiers
Scherrer, Y. (!!Speaker), Aepli, N. (!!Speaker), Roemling, D. (!!Speaker) & Miletic Haddad, A. (!!Speaker)
10 juli 2024Aktivitet: Typer för tal eller presentation › !!Oral presentation
Fil -
Distinguishing Between Bosnian, Croatian, Montenegrin and Serbian: What Indicators Do Speakers Rely On?
Miletic Haddad, A. (!!Speaker)
10 juli 2024Aktivitet: Typer för tal eller presentation › !!Oral presentation
Fil -
Occitan in Wikipedia Discussions: Initial Findings
Miletic Haddad, A. (!!Speaker) & Scherrer, Y. (!!Speaker)
6 okt. 2022Aktivitet: Typer för tal eller presentation › !!Oral presentation
Fil -
Occitan in Wikipedia discussions: Corpus extraction, language identification and user practices
Miletic Haddad, A. (!!Speaker)
24 nov. 2022Aktivitet: Typer för tal eller presentation › !!Oral presentation