1 code implementation • 3 Jun 2023 • Jana Straková, Eva Fučíková, Jan Hajič, Zdeňka Urešová
We have also carefully examined the correlation of the automatic scores with the human annotation.
1 code implementation • CRAC (ACL) 2022 • Milan Straka, Jana Straková
We describe the winning submission to the CRAC 2022 Shared Task on Multilingual Coreference Resolution.
no code implementations • 14 Jan 2022 • Jakub Náplava, Milan Straka, Jana Straková, Alexandr Rosen
We introduce a large and diverse Czech corpus annotated for grammatical error correction (GEC) with the aim to contribute to the still scarce data resources in this domain for languages other than English.
1 code implementation • WNUT (ACL) 2021 • Milan Straka, Jakub Náplava, Jana Straková
We propose a character-based nonautoregressive GEC approach, with automatically generated character transformations.
1 code implementation • WNUT (ACL) 2021 • Jakub Náplava, Martin Popel, Milan Straka, Jana Straková
We also compare two approaches to address the performance drop: a) training the NLP models with noised data generated by our framework; and b) reducing the input noise with external system for natural language correction.
no code implementations • 24 May 2021 • Milan Straka, Jakub Náplava, Jana Straková, David Samuel
We present RobeCzech, a monolingual RoBERTa language representation model trained on Czech data.
Ranked #1 on Semantic Parsing on PTG (czech, MRP 2020)
1 code implementation • 24 May 2021 • Jakub Náplava, Milan Straka, Jana Straková
We propose a new architecture for diacritics restoration based on contextualized embeddings, namely BERT, and we evaluate it on 12 languages with diacritics.
no code implementations • LREC 2020 • Milan Straka, Jana Straková
We present our contribution to the EvaLatin shared task, which is the first evaluation campaign devoted to the evaluation of NLP tools for Latin.
1 code implementation • 24 Oct 2019 • Milan Straka, Jana Straková
We present a system description of our contribution to the CoNLL 2019 shared task, Cross-Framework Meaning Representation Parsing (MRP 2019).
no code implementations • 8 Sep 2019 • Milan Straka, Jana Straková, Jan Hajič
We evaluate two meth ods for precomputing such embeddings, BERT and Flair, on four Czech text processing tasks: part-of-speech (POS) tagging, lemmatization, dependency pars ing and named entity recognition (NER).
no code implementations • 20 Aug 2019 • Milan Straka, Jana Straková, Jan Hajič
We present an extensive evaluation of three recently proposed methods for contextualized embeddings on 89 corpora in 54 languages of the Universal Dependencies 2. 3 in three tasks: POS tagging, lemmatization, and dependency parsing.
Ranked #1 on Dependency Parsing on Universal Dependencies
no code implementations • WS 2019 • Milan Straka, Jana Straková, Jan Hajič
In the morphological analysis, our system placed tightly second: our morphological analysis accuracy was 93. 19, the winning system's 93. 23.
1 code implementation • ACL 2019 • Jana Straková, Milan Straka, Jan Hajič
We propose two neural network architectures for nested named entity recognition (NER), a setting in which named entities may overlap and also be labeled with more than one label.
Ranked #3 on Nested Mention Recognition on ACE 2005