Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Tom Kocmi

Tom Kocmi

Large Language Models Are State-of-the-Art Evaluators of Translation Quality

Feb 28, 2023
Tom Kocmi, Christian Federmann

Figure 1 for Large Language Models Are State-of-the-Art Evaluators of Translation Quality

Figure 2 for Large Language Models Are State-of-the-Art Evaluators of Translation Quality

Figure 3 for Large Language Models Are State-of-the-Art Evaluators of Translation Quality

Figure 4 for Large Language Models Are State-of-the-Art Evaluators of Translation Quality

* 10 pages, 8 tables, one figure

Access Paper or Ask Questions

Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference

Jan 28, 2023
Vilém Zouhar, Shehzaad Dhuliawala, Wangchunshu Zhou, Nico Daheim, Tom Kocmi, Yuchen Eleanor Jiang, Mrinmaya Sachan

Figure 1 for Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference

Figure 2 for Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference

Figure 3 for Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference

Figure 4 for Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference

* Accepted at EACL23 (main)

Access Paper or Ask Questions

The Reality of Multi-Lingual Machine Translation

Feb 25, 2022
Tom Kocmi, Dominik Macháček, Ondřej Bojar

Figure 1 for The Reality of Multi-Lingual Machine Translation

Figure 2 for The Reality of Multi-Lingual Machine Translation

Figure 3 for The Reality of Multi-Lingual Machine Translation

Figure 4 for The Reality of Multi-Lingual Machine Translation

* ISBN 978-80-88132-11-0. arXiv admin note: substantial text overlap with arXiv:2001.01622

Access Paper or Ask Questions

On User Interfaces for Large-Scale Document-Level Human Evaluation of Machine Translation Outputs

Apr 21, 2021
Roman Grundkiewicz, Marcin Junczys-Dowmunt, Christian Federmann, Tom Kocmi

Figure 1 for On User Interfaces for Large-Scale Document-Level Human Evaluation of Machine Translation Outputs

Figure 2 for On User Interfaces for Large-Scale Document-Level Human Evaluation of Machine Translation Outputs

Figure 3 for On User Interfaces for Large-Scale Document-Level Human Evaluation of Machine Translation Outputs

Figure 4 for On User Interfaces for Large-Scale Document-Level Human Evaluation of Machine Translation Outputs

* Presented at HumEval, EACL 2021

Access Paper or Ask Questions

THEaiTRE 1.0: Interactive generation of theatre play scripts

Feb 17, 2021
Rudolf Rosa, Tomáš Musil, Ondřej Dušek, Dominik Jurko, Patrícia Schmidtová, David Mareček, Ondřej Bojar, Tom Kocmi, Daniel Hrbek, David Košťák, Martina Kinská, Marie Nováková, Josef Doležal, Klára Vosecká, Tomáš Studeník, Petr Žabka

* Submitted to Text2Story workshop 2021

Access Paper or Ask Questions

Gender Coreference and Bias Evaluation at WMT 2020

Oct 12, 2020
Tom Kocmi, Tomasz Limisiewicz, Gabriel Stanovsky

Figure 1 for Gender Coreference and Bias Evaluation at WMT 2020

Figure 2 for Gender Coreference and Bias Evaluation at WMT 2020

Figure 3 for Gender Coreference and Bias Evaluation at WMT 2020

Figure 4 for Gender Coreference and Bias Evaluation at WMT 2020

* Accepted WMT20

Access Paper or Ask Questions

Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords

Jul 06, 2020
Tom Kocmi, Martin Popel, Ondrej Bojar

Figure 1 for Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords

Figure 2 for Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords

Access Paper or Ask Questions