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
#NLP #ComputationalLinguistics #CzechNLP #MachineLearning
#NLP #ComputationalLinguistics #CzechNLP #MachineLearning
arxiv.org/abs/2506.22402
arxiv.org/abs/2506.22402
I’ll have two works there:
1️⃣ Refining Czech GEC: Insights from a Multi-Experiment Approach by Petr Pechman, Milan Straka, me, Jakub Náplava
2️⃣ Flexing in 73 Languages: A Single Small Model for Multilingual Inflection by Tomáš Sourada & me
I’ll have two works there:
1️⃣ Refining Czech GEC: Insights from a Multi-Experiment Approach by Petr Pechman, Milan Straka, me, Jakub Náplava
2️⃣ Flexing in 73 Languages: A Single Small Model for Multilingual Inflection by Tomáš Sourada & me
aclanthology.org/2025.acl-dem...
by @janastrakova.bsky.social and @straka-milan.bsky.social bsky.social
Open-source multilingual NER tool achieving state-of-the-art results on 21 datasets in 15 languages with a single 355M model.
aclanthology.org/2025.acl-dem...
by @janastrakova.bsky.social and @straka-milan.bsky.social bsky.social
Open-source multilingual NER tool achieving state-of-the-art results on 21 datasets in 15 languages with a single 355M model.
lindat.mff.cuni.cz/services/nam...
If you're attending ACL 2025, stop by our demo, we'd love to show you what it can do.
#ACL2025NLP #NLProc
lindat.mff.cuni.cz/services/nam...
If you're attending ACL 2025, stop by our demo, we'd love to show you what it can do.
#ACL2025NLP #NLProc
🔗 www.matfyz.cz/clanky/holky...
🖥️ @ufal-cuni.bsky.social
🎉 NameTag 3.1 achieves state of the art on 21 datasets across 15 languages.
🛞 Try the demo: lindat.mff.cuni.cz/services/nam...
🎉 NameTag 3.1 achieves state of the art on 21 datasets across 15 languages.
🛞 Try the demo: lindat.mff.cuni.cz/services/nam...