Search Results for author: Martin Popel

Found 42 papers, 5 papers with code

CorefUD 1.0: Coreference Meets Universal Dependencies

no code implementations LREC 2022 Anna Nedoluzhko, Michal Novák, Martin Popel, Zdeněk Žabokrtský, Amir Zeldes, Daniel Zeman

Recent advances in standardization for annotated language resources have led to successful large scale efforts, such as the Universal Dependencies (UD) project for multilingual syntactically annotated data.

coreference-resolution named-entity-recognition +2

Do UD Trees Match Mention Spans in Coreference Annotations?

no code implementations Findings (EMNLP) 2021 Martin Popel, Zdeněk Žabokrtský, Anna Nedoluzhko, Michal Novák, Daniel Zeman

One can find dozens of data resources for various languages in which coreference - a relation between two or more expressions that refer to the same real-world entity - is manually annotated.

Domain Adaptation of Document-Level NMT in IWSLT19

no code implementations EMNLP (IWSLT) 2019 Martin Popel, Christian Federmann

We describe our four NMT systems submitted to the IWSLT19 shared task in English→Czech text-to-text translation of TED talks.

Domain Adaptation NMT +2

CUNI English-Czech and English-Polish Systems in WMT20: Robust Document-Level Training

no code implementations WMT (EMNLP) 2020 Martin Popel

We describe our two NMT systems submitted to the WMT 2020 shared task in English<->Czech and English<->Polish news translation.

NMT Sentence +1

Detecting Post-Edited References and Their Effect on Human Evaluation

no code implementations EACL (HumEval) 2021 Věra Kloudová, Ondřej Bojar, Martin Popel

This paper provides a quick overview of possible methods how to detect that reference translations were actually created by post-editing an MT system.

Evaluating Optimal Reference Translations

1 code implementation28 Nov 2023 Vilém Zouhar, Věra Kloudová, Martin Popel, Ondřej Bojar

The overall translation quality reached by current machine translation (MT) systems for high-resourced language pairs is remarkably good.

Machine Translation Translation

CUNI Systems for the WMT22 Czech-Ukrainian Translation Task

no code implementations1 Dec 2022 Martin Popel, Jindřich Libovický, Jindřich Helcl

We present Charles University submissions to the WMT22 General Translation Shared Task on Czech-Ukrainian and Ukrainian-Czech machine translation.

Machine Translation Translation

CUNI Submission in WMT22 General Task

no code implementations29 Nov 2022 Josef Jon, Martin Popel, Ondřej Bojar

We evaluate performance of MBR decoding compared to traditional mixed backtranslation training and we show a possible synergy when using both of the techniques simultaneously.

Translation

Understanding Model Robustness to User-generated Noisy Texts

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.

Grammatical Error Correction Machine Translation +5

Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords

no code implementations6 Jul 2020 Tom Kocmi, Martin Popel, Ondrej Bojar

We present a new release of the Czech-English parallel corpus CzEng 2. 0 consisting of over 2 billion words (2 "gigawords") in each language.

CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

no code implementations CONLL 2018 Daniel Zeman, Jan Haji{\v{c}}, Martin Popel, Martin Potthast, Milan Straka, Filip Ginter, Joakim Nivre, Slav Petrov

Every year, the Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets.

Dependency Parsing Morphological Analysis +1

Training Tips for the Transformer Model

4 code implementations1 Apr 2018 Martin Popel, Ondřej Bojar

This article describes our experiments in neural machine translation using the recent Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et al., 2017).

Machine Translation Sentence +1

QTLeap WSD/NED Corpora: Semantic Annotation of Parallel Corpora in Six Languages

no code implementations LREC 2016 Arantxa Otegi, Nora Aranberri, Antonio Branco, Jan Haji{\v{c}}, Martin Popel, Kiril Simov, Eneko Agirre, Petya Osenova, Rita Pereira, Jo{\~a}o Silva, Steven Neale

This work presents parallel corpora automatically annotated with several NLP tools, including lemma and part-of-speech tagging, named-entity recognition and classification, named-entity disambiguation, word-sense disambiguation, and coreference.

Cross-Lingual Transfer Entity Disambiguation +9

Cannot find the paper you are looking for? You can Submit a new open access paper.