Institute of Formal and Applied Linguistics
@ufal.mff.cuni.cz
Computational linguistics • Natural language processing • Formal linguistics • Machine translation | at Faculty of Mathematics and Physics, Charles University
🌍 Towards Adding Arabic to CorefUD
Dima Taji and Dan Zeman
aclanthology.org/2025.crac-1.6
Expanding the CorefUD universal coreference dataset to Arabic - taking important steps toward truly multilingual coreference resolution resources and better Arabic NLP.
Dima Taji and Dan Zeman
aclanthology.org/2025.crac-1.6
Expanding the CorefUD universal coreference dataset to Arabic - taking important steps toward truly multilingual coreference resolution resources and better Arabic NLP.
November 11, 2025 at 2:37 PM
🌍 Towards Adding Arabic to CorefUD
Dima Taji and Dan Zeman
aclanthology.org/2025.crac-1.6
Expanding the CorefUD universal coreference dataset to Arabic - taking important steps toward truly multilingual coreference resolution resources and better Arabic NLP.
Dima Taji and Dan Zeman
aclanthology.org/2025.crac-1.6
Expanding the CorefUD universal coreference dataset to Arabic - taking important steps toward truly multilingual coreference resolution resources and better Arabic NLP.
EMNLP 2025 is over... and Milan Straka is bringing home an award! 🏆
CorPipe triumphed in the prestigious CRAC25 Shared Task, focusing on multilingual coreference resolution.
Did Milan just CRACk it? We certainly think so! 😉
🔗 Find out more at arxiv.org/abs/2509.17858
#EMNLP2025 #CorPipe #CRAC25
CorPipe triumphed in the prestigious CRAC25 Shared Task, focusing on multilingual coreference resolution.
Did Milan just CRACk it? We certainly think so! 😉
🔗 Find out more at arxiv.org/abs/2509.17858
#EMNLP2025 #CorPipe #CRAC25
November 11, 2025 at 1:49 PM
EMNLP 2025 is over... and Milan Straka is bringing home an award! 🏆
CorPipe triumphed in the prestigious CRAC25 Shared Task, focusing on multilingual coreference resolution.
Did Milan just CRACk it? We certainly think so! 😉
🔗 Find out more at arxiv.org/abs/2509.17858
#EMNLP2025 #CorPipe #CRAC25
CorPipe triumphed in the prestigious CRAC25 Shared Task, focusing on multilingual coreference resolution.
Did Milan just CRACk it? We certainly think so! 😉
🔗 Find out more at arxiv.org/abs/2509.17858
#EMNLP2025 #CorPipe #CRAC25
The EU's 🇪🇺 HPLT project, coordinated by @ufal.mff.cuni.cz is at #EMNLP2025! It has supported it as a silver sponsor, disseminating HPLT results from our booth and through several papers. We'll continue to shape the future of multilingual datasets and models here and in @openeurollm.bsky.social!
November 7, 2025 at 9:03 PM
The EU's 🇪🇺 HPLT project, coordinated by @ufal.mff.cuni.cz is at #EMNLP2025! It has supported it as a silver sponsor, disseminating HPLT results from our booth and through several papers. We'll continue to shape the future of multilingual datasets and models here and in @openeurollm.bsky.social!
📚 SRS-Stories: Vocabulary-constrained multilingual story generation for language learning
Wiktor Kamzela, Mateusz Lango & @toonietuesday.bsky.social
aclanthology.org/2025.emnlp-i...
LLM stories teach vocab while reviewing learned words via Spaced Repetition-more grammatical than standard generation
Wiktor Kamzela, Mateusz Lango & @toonietuesday.bsky.social
aclanthology.org/2025.emnlp-i...
LLM stories teach vocab while reviewing learned words via Spaced Repetition-more grammatical than standard generation
November 7, 2025 at 8:54 PM
📚 SRS-Stories: Vocabulary-constrained multilingual story generation for language learning
Wiktor Kamzela, Mateusz Lango & @toonietuesday.bsky.social
aclanthology.org/2025.emnlp-i...
LLM stories teach vocab while reviewing learned words via Spaced Repetition-more grammatical than standard generation
Wiktor Kamzela, Mateusz Lango & @toonietuesday.bsky.social
aclanthology.org/2025.emnlp-i...
LLM stories teach vocab while reviewing learned words via Spaced Repetition-more grammatical than standard generation
Excited to share our work at #EMNLP2025! Our team is presenting 12 papers across the main conference and workshops, covering multilingual NLG, LLM agents, coreference resolution, and machine translation.
A thread with highlights 🧵👇
A thread with highlights 🧵👇
November 7, 2025 at 8:54 PM
Excited to share our work at #EMNLP2025! Our team is presenting 12 papers across the main conference and workshops, covering multilingual NLG, LLM agents, coreference resolution, and machine translation.
A thread with highlights 🧵👇
A thread with highlights 🧵👇
Zveme na dnešní přednášku Jazykovědného sdružení, kterou od 17:30 přednese prof. PhDr. Eva Hajičová, DrSc.
🔗 Můžete přijít osobně nebo sledovat na zoomu: lnkd.in/eQeST-uG
Téma přednášky: Aktuální členění v době paralelních korpusů
📸 Foto: Vladimír Šigut, UK
🔗 Můžete přijít osobně nebo sledovat na zoomu: lnkd.in/eQeST-uG
Téma přednášky: Aktuální členění v době paralelních korpusů
📸 Foto: Vladimír Šigut, UK
October 23, 2025 at 9:02 AM
Zveme na dnešní přednášku Jazykovědného sdružení, kterou od 17:30 přednese prof. PhDr. Eva Hajičová, DrSc.
🔗 Můžete přijít osobně nebo sledovat na zoomu: lnkd.in/eQeST-uG
Téma přednášky: Aktuální členění v době paralelních korpusů
📸 Foto: Vladimír Šigut, UK
🔗 Můžete přijít osobně nebo sledovat na zoomu: lnkd.in/eQeST-uG
Téma přednášky: Aktuální členění v době paralelních korpusů
📸 Foto: Vladimír Šigut, UK
🚀 PROJECT LAUNCH: Infoveillance is Live! Our AI tool monitors digital media to detect misinformation and enhance public trust/literacy. Fighting infodemics & polarization.
[https://ufal.mff.cuni.cz/grants/infoveillance]
#Infoveillance #AI #Misinformation #PublicTrust #UFAL
[https://ufal.mff.cuni.cz/grants/infoveillance]
#Infoveillance #AI #Misinformation #PublicTrust #UFAL
October 2, 2025 at 11:46 AM
🚀 PROJECT LAUNCH: Infoveillance is Live! Our AI tool monitors digital media to detect misinformation and enhance public trust/literacy. Fighting infodemics & polarization.
[https://ufal.mff.cuni.cz/grants/infoveillance]
#Infoveillance #AI #Misinformation #PublicTrust #UFAL
[https://ufal.mff.cuni.cz/grants/infoveillance]
#Infoveillance #AI #Misinformation #PublicTrust #UFAL
Šest kolegů vedlo pro DGT (Evropské ředitelství pro překlady) třídenní letní školu v Lucemburku. Učili 40+ pracovníků DGT nejnovější metody strojové podpory překladu a zajištění kvality. Cíl? Zefektivnit překlad legislativy EU do všech členských jazyků!
#DGT #UFAL #StrojovyPreklad #AI #EUTools
#DGT #UFAL #StrojovyPreklad #AI #EUTools
September 29, 2025 at 9:31 AM
Šest kolegů vedlo pro DGT (Evropské ředitelství pro překlady) třídenní letní školu v Lucemburku. Učili 40+ pracovníků DGT nejnovější metody strojové podpory překladu a zajištění kvality. Cíl? Zefektivnit překlad legislativy EU do všech členských jazyků!
#DGT #UFAL #StrojovyPreklad #AI #EUTools
#DGT #UFAL #StrojovyPreklad #AI #EUTools
@Dan Zeman has been invited as a keynote speaker at the ICLC 11 conference! iclc11.ff.cuni.cz/keynote-spea...
#UFAL #ICLC11 #UniversalDependencies #CharlesUniversity #Prague
#UFAL #ICLC11 #UniversalDependencies #CharlesUniversity #Prague
September 24, 2025 at 7:48 AM
@Dan Zeman has been invited as a keynote speaker at the ICLC 11 conference! iclc11.ff.cuni.cz/keynote-spea...
#UFAL #ICLC11 #UniversalDependencies #CharlesUniversity #Prague
#UFAL #ICLC11 #UniversalDependencies #CharlesUniversity #Prague
Nahlédněte na kick‐off meeting projektu ✨HumanAId: AI zaměřená na člověka pro udržitelnou a adaptabilní společnost✨.
Projekt se silnou účastí: vede ho FFUK ve spolupráci s MFF UK, FSV UK, PF UP v Olomouci, FÚ AV ČR, prg.ai a Kampusem Hybernská.
#prgAI #HumanAId #OPJAK
1/2
Projekt se silnou účastí: vede ho FFUK ve spolupráci s MFF UK, FSV UK, PF UP v Olomouci, FÚ AV ČR, prg.ai a Kampusem Hybernská.
#prgAI #HumanAId #OPJAK
1/2
September 23, 2025 at 2:58 PM
And another successfully defended thesis: 👉Dr.👈 Kira Droganova defended her thesis: Dependency Parsing beyond Simple Trees, which focused on enriching syntactic parsing with deeper semantic layers to better capture meaning across languages. Congratulations 🥳
September 23, 2025 at 11:07 AM
And another successfully defended thesis: 👉Dr.👈 Kira Droganova defended her thesis: Dependency Parsing beyond Simple Trees, which focused on enriching syntactic parsing with deeper semantic layers to better capture meaning across languages. Congratulations 🥳
🎉 Congratulations to 👉Dr.👈 Tomáš Musil on successfully defending his PhD thesis! 🍻 His talk explored #LLMs, theories of meaning, and their role in LLM #interpretability, highlighting unsupervised discovery of binary semantic features via ICA and the word intruder test.
September 22, 2025 at 10:09 AM
🎉 Congratulations to 👉Dr.👈 Tomáš Musil on successfully defending his PhD thesis! 🍻 His talk explored #LLMs, theories of meaning, and their role in LLM #interpretability, highlighting unsupervised discovery of binary semantic features via ICA and the word intruder test.
Workshop "Regulace, AI a advokacie – zákulisí legislativy a advokátních inovací" představil OpenEuroLLM jako naději pro evropskou digitální suverenitu a nutnost pro konkurenceschopnost Evropy. Jan Hajič zdůraznil, že Česko se snaží o snižování byrokracie v oblasti AI.
#AI #AIregulation #FutureOfLaw
#AI #AIregulation #FutureOfLaw
September 19, 2025 at 2:45 PM
Workshop "Regulace, AI a advokacie – zákulisí legislativy a advokátních inovací" představil OpenEuroLLM jako naději pro evropskou digitální suverenitu a nutnost pro konkurenceschopnost Evropy. Jan Hajič zdůraznil, že Česko se snaží o snižování byrokracie v oblasti AI.
#AI #AIregulation #FutureOfLaw
#AI #AIregulation #FutureOfLaw
Researchers' Night with @informatfyz.cuni.cz!
You can come to a live podcast recording and try out a real-time automatic interpreting system ELITR. The event is on September 26th.
🔗 czechia.representation.ec.europa.eu/evropsky-den...
#ELITR #AI #Interpreting #MachineTranslation #LanguageTech
You can come to a live podcast recording and try out a real-time automatic interpreting system ELITR. The event is on September 26th.
🔗 czechia.representation.ec.europa.eu/evropsky-den...
#ELITR #AI #Interpreting #MachineTranslation #LanguageTech
September 18, 2025 at 10:19 AM
Researchers' Night with @informatfyz.cuni.cz!
You can come to a live podcast recording and try out a real-time automatic interpreting system ELITR. The event is on September 26th.
🔗 czechia.representation.ec.europa.eu/evropsky-den...
#ELITR #AI #Interpreting #MachineTranslation #LanguageTech
You can come to a live podcast recording and try out a real-time automatic interpreting system ELITR. The event is on September 26th.
🔗 czechia.representation.ec.europa.eu/evropsky-den...
#ELITR #AI #Interpreting #MachineTranslation #LanguageTech
Gold Data and Multiple Understanding of Discourse Relations
by Š. Zikánová, A. Nedoluzhko, J. Mírovský & E. Hajičová
TL;DR: Investigate how annotators interpret discourse relations differently, revealing important insights about subjectivity in linguistic annotation and its impact on NLP systems.
by Š. Zikánová, A. Nedoluzhko, J. Mírovský & E. Hajičová
TL;DR: Investigate how annotators interpret discourse relations differently, revealing important insights about subjectivity in linguistic annotation and its impact on NLP systems.
September 1, 2025 at 2:29 PM
Gold Data and Multiple Understanding of Discourse Relations
by Š. Zikánová, A. Nedoluzhko, J. Mírovský & E. Hajičová
TL;DR: Investigate how annotators interpret discourse relations differently, revealing important insights about subjectivity in linguistic annotation and its impact on NLP systems.
by Š. Zikánová, A. Nedoluzhko, J. Mírovský & E. Hajičová
TL;DR: Investigate how annotators interpret discourse relations differently, revealing important insights about subjectivity in linguistic annotation and its impact on NLP systems.
Morphological Segmentation with Neural Networks: Performance Effects of Architecture, Data Size, and Cross-Lingual Transfer in Seven Languages
by M. Olbrich & Z. Zabokrtsky
TL;DR: Analyzed neural architectures, data size, and cross-lingual transfer for morphological segmentation for 7 languages.
by M. Olbrich & Z. Zabokrtsky
TL;DR: Analyzed neural architectures, data size, and cross-lingual transfer for morphological segmentation for 7 languages.
September 1, 2025 at 2:29 PM
Morphological Segmentation with Neural Networks: Performance Effects of Architecture, Data Size, and Cross-Lingual Transfer in Seven Languages
by M. Olbrich & Z. Zabokrtsky
TL;DR: Analyzed neural architectures, data size, and cross-lingual transfer for morphological segmentation for 7 languages.
by M. Olbrich & Z. Zabokrtsky
TL;DR: Analyzed neural architectures, data size, and cross-lingual transfer for morphological segmentation for 7 languages.
Flexing in 73 Languages: A Single Small Model for Multilingual Inflection
by Tomáš Sourada & Jana Straková
TL;DR: Compact neural model successfully handles morphological inflection across 73 diverse languages, proving that small can be mighty in multilingual NLP.
by Tomáš Sourada & Jana Straková
TL;DR: Compact neural model successfully handles morphological inflection across 73 diverse languages, proving that small can be mighty in multilingual NLP.
September 1, 2025 at 2:29 PM
Flexing in 73 Languages: A Single Small Model for Multilingual Inflection
by Tomáš Sourada & Jana Straková
TL;DR: Compact neural model successfully handles morphological inflection across 73 diverse languages, proving that small can be mighty in multilingual NLP.
by Tomáš Sourada & Jana Straková
TL;DR: Compact neural model successfully handles morphological inflection across 73 diverse languages, proving that small can be mighty in multilingual NLP.
Refining Czech GEC: Insights from a Multi-Experiment Approach
by P. Pechman, @straka-milan.bsky.social , @janastrakova.bsky.social , J. Náplava
TL;DR: Better Czech grammatical error correction systems + insights for better automated writing assistance in Czech arxiv.org/abs/2506.22402
by P. Pechman, @straka-milan.bsky.social , @janastrakova.bsky.social , J. Náplava
TL;DR: Better Czech grammatical error correction systems + insights for better automated writing assistance in Czech arxiv.org/abs/2506.22402
September 1, 2025 at 2:29 PM
Refining Czech GEC: Insights from a Multi-Experiment Approach
by P. Pechman, @straka-milan.bsky.social , @janastrakova.bsky.social , J. Náplava
TL;DR: Better Czech grammatical error correction systems + insights for better automated writing assistance in Czech arxiv.org/abs/2506.22402
by P. Pechman, @straka-milan.bsky.social , @janastrakova.bsky.social , J. Náplava
TL;DR: Better Czech grammatical error correction systems + insights for better automated writing assistance in Czech arxiv.org/abs/2506.22402
Investigating the Effect of Parallel Data in the Cross-Lingual Transfer for Vision-Language Encoders
by @andrei-a-manea.bsky.social & @jlibovicky.bsky.social
TL;DR: Explore how parallel datasets improve cross-lingual transfer in vision-language models. arxiv.org/abs/2504.21681
by @andrei-a-manea.bsky.social & @jlibovicky.bsky.social
TL;DR: Explore how parallel datasets improve cross-lingual transfer in vision-language models. arxiv.org/abs/2504.21681
September 1, 2025 at 2:29 PM
Investigating the Effect of Parallel Data in the Cross-Lingual Transfer for Vision-Language Encoders
by @andrei-a-manea.bsky.social & @jlibovicky.bsky.social
TL;DR: Explore how parallel datasets improve cross-lingual transfer in vision-language models. arxiv.org/abs/2504.21681
by @andrei-a-manea.bsky.social & @jlibovicky.bsky.social
TL;DR: Explore how parallel datasets improve cross-lingual transfer in vision-language models. arxiv.org/abs/2504.21681
ParCzech 3.0: A Large Czech Speech Corpus with Rich Metadata
by M. Kopp, V. Stankov, J. O. Krůza, . Straňák & . Bojar
TL;DR: Czech parliamentary speeches from 2013-2021 with rich metadata incl. speaker identities, political affiliations, and automatic linguistic annotations in TEI format.
by M. Kopp, V. Stankov, J. O. Krůza, . Straňák & . Bojar
TL;DR: Czech parliamentary speeches from 2013-2021 with rich metadata incl. speaker identities, political affiliations, and automatic linguistic annotations in TEI format.
September 1, 2025 at 2:29 PM
ParCzech 3.0: A Large Czech Speech Corpus with Rich Metadata
by M. Kopp, V. Stankov, J. O. Krůza, . Straňák & . Bojar
TL;DR: Czech parliamentary speeches from 2013-2021 with rich metadata incl. speaker identities, political affiliations, and automatic linguistic annotations in TEI format.
by M. Kopp, V. Stankov, J. O. Krůza, . Straňák & . Bojar
TL;DR: Czech parliamentary speeches from 2013-2021 with rich metadata incl. speaker identities, political affiliations, and automatic linguistic annotations in TEI format.
Automated Speaking Assessment for L2 Learners of Czech by Peter Polák, Michal Novák, Kateřina Rysová, Magdaléna Rysová & Ondřej Bojar
TL;DR: An automated system to evaluate the Czech speaking skills of second language learners, making language assessment more accessible and consistent.
TL;DR: An automated system to evaluate the Czech speaking skills of second language learners, making language assessment more accessible and consistent.
September 1, 2025 at 2:29 PM
Automated Speaking Assessment for L2 Learners of Czech by Peter Polák, Michal Novák, Kateřina Rysová, Magdaléna Rysová & Ondřej Bojar
TL;DR: An automated system to evaluate the Czech speaking skills of second language learners, making language assessment more accessible and consistent.
TL;DR: An automated system to evaluate the Czech speaking skills of second language learners, making language assessment more accessible and consistent.
Great week at #TSD2025 in Erlangen! Our @ufal-cuni.bsky.social team presented 7 papers covering various topics from Czech speech assessment to multilingual morphology. Thanks to all attendees who engaged with our work! 🧵👇
#NLP #ComputationalLinguistics #CzechNLP #MachineLearning
#NLP #ComputationalLinguistics #CzechNLP #MachineLearning
September 1, 2025 at 2:29 PM
Great week at #TSD2025 in Erlangen! Our @ufal-cuni.bsky.social team presented 7 papers covering various topics from Czech speech assessment to multilingual morphology. Thanks to all attendees who engaged with our work! 🧵👇
#NLP #ComputationalLinguistics #CzechNLP #MachineLearning
#NLP #ComputationalLinguistics #CzechNLP #MachineLearning
Our team of 10 is at #MTMarathon2025 in Helsinki 🇫🇮, a week-long meeting of machine translation researchers, developers.
✅ Posters presented
✅ Now working on cool collaborative projects with researchers from around the world.
#MachineTranslation #NLP
✅ Posters presented
✅ Now working on cool collaborative projects with researchers from around the world.
#MachineTranslation #NLP
August 26, 2025 at 8:05 AM
Our team of 10 is at #MTMarathon2025 in Helsinki 🇫🇮, a week-long meeting of machine translation researchers, developers.
✅ Posters presented
✅ Now working on cool collaborative projects with researchers from around the world.
#MachineTranslation #NLP
✅ Posters presented
✅ Now working on cool collaborative projects with researchers from around the world.
#MachineTranslation #NLP
We are hosting a summer school „Data Literacy with R for Students of Humanities“ at Malá Strana, August 4-15. ufal.mff.cuni.cz/events/summe...
#DataLiteracy #Humanities #Matfyz #UFAL #CharlesUniversity
#DataLiteracy #Humanities #Matfyz #UFAL #CharlesUniversity
August 7, 2025 at 1:11 PM
We are hosting a summer school „Data Literacy with R for Students of Humanities“ at Malá Strana, August 4-15. ufal.mff.cuni.cz/events/summe...
#DataLiteracy #Humanities #Matfyz #UFAL #CharlesUniversity
#DataLiteracy #Humanities #Matfyz #UFAL #CharlesUniversity
Atyaephyra at SemEval-2025 Task 4: Low-Rank Negative Preference Optimization
arxiv.org/abs/2503.13690
by Jan Bronec and @jindrahelcl.bsky.social
Negative preference optimization with LoRA for LLM unlearning, using efficient regularization to exceed SemEval 2025 baseline performance.
arxiv.org/abs/2503.13690
by Jan Bronec and @jindrahelcl.bsky.social
Negative preference optimization with LoRA for LLM unlearning, using efficient regularization to exceed SemEval 2025 baseline performance.
August 1, 2025 at 1:37 PM
Atyaephyra at SemEval-2025 Task 4: Low-Rank Negative Preference Optimization
arxiv.org/abs/2503.13690
by Jan Bronec and @jindrahelcl.bsky.social
Negative preference optimization with LoRA for LLM unlearning, using efficient regularization to exceed SemEval 2025 baseline performance.
arxiv.org/abs/2503.13690
by Jan Bronec and @jindrahelcl.bsky.social
Negative preference optimization with LoRA for LLM unlearning, using efficient regularization to exceed SemEval 2025 baseline performance.