Taido Purason

17 papers C 2Journal 7Unranked 8
YearRankTypeTitle / Venue / Authors
2026 J jnl
EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training.
CoRR
Aleksei Dorkin, Taido Purason, Emil Kalbaliyev, Hele-Andra Kuulmets, Marii Ojastu, Mark Fisel, Tanel Alumäe, Eleri Aedmaa, Krister Kruusmaa, Kairit Sirts
2026 — conf
Teaching Old Tokenizers New Words: Efficient Tokenizer Adaptation for Pretrained Models.
EACL (Findings)
Taido Purason, Pavel Chizhov, Ivan P. Yamshchikov, Mark Fishel
2025 — conf
How Well do LLMs know Finno-Ugric Languages? A Systematic Assessment.
NoDaLiDa/Baltic-HLT
Hele-Andra Kuulmets, Taido Purason, Mark Fishel
2025 — conf
LLMs for Extremely Low-Resource Finno-Ugric Languages.
NAACL (Findings)
Taido Purason, Hele-Andra Kuulmets, Mark Fishel
2025 J jnl
Prune or Retrain: Optimizing the Vocabulary of Multilingual Models for Estonian.
CoRR
Aleksei Dorkin, Taido Purason, Kairit Sirts
2025 J jnl
Teaching Old Tokenizers New Words: Efficient Tokenizer Adaptation for Pre-trained Models.
CoRR
Taido Purason, Pavel Chizhov, Ivan P. Yamshchikov, Mark Fishel
2024 J jnl
LLMs for Extremely Low-Resource Finno-Ugric Languages.
CoRR
Taido Purason, Hele-Andra Kuulmets, Mark Fishel
2024 — conf
Multilinguality or Back-translation? A Case Study with Estonian.
LREC/COLING
Elizaveta Korotkova, Taido Purason, Agnes Luhtaru, Mark Fishel
2024 — conf
SMUGRI-MT - Machine Translation System for Low-Resource Finno-Ugric Languages.
EAMT (2)
Taido Purason, Aleksei Ivanov, Lisa Yankovskaya, Mark Fishel
2024 — conf
Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer.
NAACL-HLT (Findings)
Hele-Andra Kuulmets, Taido Purason, Agnes Luhtaru, Mark Fishel
2024 J jnl
Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer.
CoRR
Hele-Andra Kuulmets, Taido Purason, Agnes Luhtaru, Mark Fishel
2024 — conf
To Err Is Human, but Llamas Can Learn It Too.
EMNLP (Findings)
Agnes Luhtaru, Taido Purason, Martin Vainikko, Maksym Del, Mark Fishel
2024 J jnl
To Err Is Human, but Llamas Can Learn It Too.
CoRR
Agnes Luhtaru, Taido Purason, Martin Vainikko, Maksym Del, Mark Fishel
2022 C conf
MTee: Open Machine Translation Platform for Estonian Government.
EAMT
Toms Bergmanis, Marcis Pinnis, Roberts Rozis, Janis Slapins, Valters Sics, Berta Bernane, Guntars Puzulis, Endijs Titomers, Andre Tättar, Taido Purason, Hele-Andra Kuulmets, Agnes Luhtaru, Liisa Rätsep, Maali Tars, Annika Laumets-Tättar, Mark Fishel
2022 C conf
Multilingual Neural Machine Translation With the Right Amount of Sharing.
EAMT
Taido Purason, Andre Tättar
2022 J jnl
Open and Competitive Multilingual Neural Machine Translation in Production.
Balt. J. Mod. Comput.
Andre Tättar, Taido Purason, Hele-Andra Kuulmets, Agnes Luhtaru, Liisa Rätsep, Maali Tars, Marcis Pinnis, Toms Bergmanis, Mark Fishel
2022 — conf
Teaching Unseen Low-resource Languages to Large Translation Models.
WMT
Maali Tars, Taido Purason, Andre Tättar