Matej Ulcar

21 papers B 3Misc 1Journal 13Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Mono- and cross-lingual evaluation of representation language models on less-resourced languages.
Comput. Speech Lang.
Matej Ulcar, Ales Zagar, Carlos Santos Armendariz, Andraz Repar, Senja Pollak, Matthew Purver, Marko Robnik-Sikonja
2025 J jnl
From Translation to Generative LLMs: Classification of Code-Mixed Affective Tasks.
IEEE Trans. Affect. Comput.
Anjali Yadav, Tanya Garg, Matej Klemen, Matej Ulcar, Basant Agarwal, Marko Robnik-Sikonja
2024 J jnl
Code-mixed Sentiment and Hate-speech Prediction.
CoRR
Anjali Yadav, Tanya Garg, Matej Klemen, Matej Ulcar, Basant Agarwal, Marko Robnik-Sikonja
2023 J jnl
Sequence-to-sequence pretraining for a less-resourced Slovenian language.
Frontiers Artif. Intell.
Matej Ulcar, Marko Robnik-Sikonja
2022 J jnl
Cross-lingual alignments of ELMo contextual embeddings.
Neural Comput. Appl.
Matej Ulcar, Marko Robnik-Sikonja
2022 J jnl
Sequence to sequence pretraining for a less-resourced Slovenian language.
CoRR
Matej Ulcar, Marko Robnik-Sikonja
2021 J jnl
Cross-lingual alignments of ELMo contextual embeddings.
CoRR
Matej Ulcar, Marko Robnik-Sikonja
2021 — conf
EMBEDDIA Tools, Datasets and Challenges: Resources and Hackathon Contributions.
EACL (Hackashop)
Senja Pollak, Marko Robnik-Sikonja, Matthew Purver, Michele Boggia, Ravi Shekhar, Marko Pranjic, Salla Salmela, Ivar Krustok, Tarmo Paju, Carl-Gustav Linden, Leo Leppänen, Elaine Zosa, Matej Ulcar, Linda Freienthal, Silver Traat, Luis Adrián Cabrera-Diego, Matej Martinc, Nada Lavrac, Blaz Skrlj, Martin Znidarsic, Andraz Pelicon, Boshko Koloski, Vid Podpecan, Janez Kranjc, Shane Sheehan, Emanuela Boros, José G. Moreno, Antoine Doucet, Hannu Toivonen
2021 — conf
EMBEDDIA hackathon report: Automatic sentiment and viewpoint analysis of Slovenian news corpus on the topic of LGBTIQ+.
EACL (Hackashop)
Matej Martinc, Nina Perger, Andraz Pelicon, Matej Ulcar, Andreja Vezovnik, Senja Pollak
2021 J jnl
Evaluation of contextual embeddings on less-resourced languages.
CoRR
Matej Ulcar, Ales Zagar, Carlos Santos Armendariz, Andraz Repar, Senja Pollak, Matthew Purver, Marko Robnik-Sikonja
2021 Misc conf
Training Dataset and Dictionary Sizes Matter in BERT Models: The Case of Baltic Languages.
AIST
Matej Ulcar, Marko Robnik-Sikonja
2021 J jnl
Training dataset and dictionary sizes matter in BERT models: the case of Baltic languages.
CoRR
Matej Ulcar, Marko Robnik-Sikonja
2020 B conf
CoSimLex: A Resource for Evaluating Graded Word Similarity in Context.
LREC
Carlos Santos Armendariz, Matthew Purver, Matej Ulcar, Senja Pollak, Nikola Ljubesic, Mark Granroth-Wilding
2020 — conf
FinEst BERT and CroSloEngual BERT - Less Is More in Multilingual Models.
TDS
Matej Ulcar, Marko Robnik-Sikonja
2020 J jnl
FinEst BERT and CroSloEngual BERT: less is more in multilingual models.
CoRR
Matej Ulcar, Marko Robnik-Sikonja
2020 B conf
High Quality ELMo Embeddings for Seven Less-Resourced Languages.
LREC
Matej Ulcar, Marko Robnik-Sikonja
2020 B conf
Multilingual Culture-Independent Word Analogy Datasets.
LREC
Matej Ulcar, Kristiina Vaik, Jessica Lindström, Milda Dailidenaite, Marko Robnik-Sikonja
2020 — conf
SemEval-2020 Task 3: Graded Word Similarity in Context.
SemEval@COLING
Carlos Santos Armendariz, Matthew Purver, Senja Pollak, Nikola Ljubesic, Matej Ulcar, Ivan Vulic, Mohammad Taher Pilehvar
2019 J jnl
CoSimLex: A Resource for Evaluating Graded Word Similarity in Context.
CoRR
Carlos Santos Armendariz, Matthew Purver, Matej Ulcar, Senja Pollak, Nikola Ljubesic, Marko Robnik-Sikonja, Mark Granroth-Wilding, Kristiina Vaik
2019 J jnl
High Quality ELMo Embeddings for Seven Less-Resourced Languages.
CoRR
Matej Ulcar, Marko Robnik-Sikonja
2019 J jnl
Multilingual Culture-Independent Word Analogy Datasets.
CoRR
Matej Ulcar, Marko Robnik-Sikonja