Tom Kocmi

Publication Activity (10 Years)

Years Active: 2016-2024
Publications (10 Years): 68

Top Topics

Transfer Learning

Machine Translation

Top Venues

Publications

Tianyi Tang, Hongyuan Lu, Yuchen Jiang, Haoyang Huang, Dongdong Zhang, Wayne Xin Zhao, Tom Kocmi, Furu Wei
Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References. NAACL-HLT (2024)
Qingyu Lu, Baopu Qiu, Liang Ding, Kanjian Zhang, Tom Kocmi, Dacheng Tao
Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models. ACL (Findings) (2024)
Tom Kocmi, Vilém Zouhar, Christian Federmann, Matt Post
Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies. ACL (1) (2024)
Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ondrej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Marzena Karpinska, Philipp Koehn, Benjamin Marie, Kenton Murray, Masaaki Nagata, Martin Popel, Maja Popovic, Mariya Shmatova, Steinþór Steingrímsson, Vilém Zouhar
Preliminary WMT24 Ranking of General MT Systems and LLMs. CoRR (2024)
Nikita Moghe, Arnisa Fazla, Chantal Amrhein, Tom Kocmi, Mark Steedman, Alexandra Birch, Rico Sennrich, Liane Guillou
Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets. CoRR (2024)
Tom Kocmi, Vilém Zouhar, Eleftherios Avramidis, Roman Grundkiewicz, Marzena Karpinska, Maja Popovic, Mrinmaya Sachan, Mariya Shmatova
Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation. CoRR (2024)
Vilém Zouhar, Tom Kocmi, Mrinmaya Sachan
AI-Assisted Human Evaluation of Machine Translation. CoRR (2024)
Tom Kocmi, Vilém Zouhar, Christian Federmann, Matt Post
Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies. CoRR (2024)
Tom Kocmi, Christian Federmann
Large Language Models Are State-of-the-Art Evaluators of Translation Quality. EAMT (2023)
Kirill Semenov, Vilém Zouhar, Tom Kocmi, Dongdong Zhang, Wangchunshu Zhou, Yuchen Eleanor Jiang
Findings of the WMT 2023 Shared Task on Machine Translation with Terminologies. WMT (2023)
Vikas Raunak, Tom Kocmi, Matt Post
SLIDE: Reference-free Evaluation for Machine Translation using a Sliding Document Window. CoRR (2023)
Tirthankar Ghosal, Ondrej Bojar, Marie Hledíková, Tom Kocmi, Anna Nedoluzhko
Overview of the Second Shared Task on Automatic Minuting (AutoMin) at INLG 2023. INLG (Generation Challenges) (2023)
Markus Freitag, Nitika Mathur, Chi-kiu Lo, Eleftherios Avramidis, Ricardo Rei, Brian Thompson, Tom Kocmi, Frédéric Blain, Daniel Deutsch, Craig Stewart, Chrysoula Zerva, Sheila Castilho, Alon Lavie, George F. Foster
Results of WMT23 Metrics Shared Task: Metrics Might Be Guilty but References Are Not Innocent. WMT (2023)
Vilém Zouhar, Shehzaad Dhuliawala, Wangchunshu Zhou, Nico Daheim, Tom Kocmi, Yuchen Eleanor Jiang, Mrinmaya Sachan
Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference. EACL (2023)
Tom Kocmi, Christian Federmann
Large Language Models Are State-of-the-Art Evaluators of Translation Quality. CoRR (2023)
Vilém Zouhar, Shehzaad Dhuliawala, Wangchunshu Zhou, Nico Daheim, Tom Kocmi, Yuchen Eleanor Jiang, Mrinmaya Sachan
Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference. CoRR (2023)
Tom Kocmi, Christian Federmann
GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4. WMT (2023)
Tom Kocmi, Christian Federmann
GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4. CoRR (2023)
Muhammad N. ElNokrashy, Tom Kocmi
eBLEU: Unexpectedly Good Machine Translation Evaluation Using Simple Word Embeddings. WMT (2023)
Vikas Raunak, Tom Kocmi, Matt Post
Evaluating Metrics for Document-context Evaluation in Machine Translation. WMT (2023)
Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ondrej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Philipp Koehn, Benjamin Marie, Christof Monz, Makoto Morishita, Kenton Murray, Makoto Nagata, Toshiaki Nakazawa, Martin Popel, Maja Popovic, Mariya Shmatova
Findings of the 2023 Conference on Machine Translation (WMT23): LLMs Are Here but Not Quite There Yet. WMT (2023)
Thamme Gowda, Tom Kocmi, Marcin Junczys-Dowmunt
Cometoid: Distilling Strong Reference-based Machine Translation Metrics into Even Stronger Quality Estimation Metrics. WMT (2023)
Tom Kocmi, Hitokazu Matsushita, Christian Federmann
MS-COMET: More and Better Human Judgements Improve Metric Performance. WMT (2022)
Johnny Tian-Zheng Wei, Tom Kocmi, Christian Federmann
Searching for a Higher Power in the Human Evaluation of MT. WMT (2022)
Tom Kocmi, Dominik Machácek, Ondrej Bojar
The Reality of Multi-Lingual Machine Translation. CoRR (2022)
Markus Freitag, Ricardo Rei, Nitika Mathur, Chi-kiu Lo, Craig Stewart, Eleftherios Avramidis, Tom Kocmi, George F. Foster, Alon Lavie, André F. T. Martins
Results of WMT22 Metrics Shared Task: Stop Using BLEU - Neural Metrics Are Better and More Robust. WMT (2022)
Tom Kocmi, Rachel Bawden, Ondrej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Thamme Gowda, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Rebecca Knowles, Philipp Koehn, Christof Monz, Makoto Morishita, Masaaki Nagata, Toshiaki Nakazawa, Michal Novák, Martin Popel, Maja Popovic
Findings of the 2022 Conference on Machine Translation (WMT22). WMT (2022)
Johnny Tian-Zheng Wei, Tom Kocmi, Christian Federmann
Searching for a higher power in the human evaluation of MT. CoRR (2022)
Tom Kocmi, Christian Federmann, Roman Grundkiewicz, Marcin Junczys-Dowmunt, Hitokazu Matsushita, Arul Menezes
To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation. WMT@EMNLP (2021)
Farhad Akhbardeh, Arkady Arkhangorodsky, Magdalena Biesialska, Ondrej Bojar, Rajen Chatterjee, Vishrav Chaudhary, Marta R. Costa-jussà, Cristina España-Bonet, Angela Fan, Christian Federmann, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Leonie Harter, Kenneth Heafield, Christopher Homan, Matthias Huck, Kwabena Amponsah-Kaakyire, Jungo Kasai, Daniel Khashabi, Kevin Knight, Tom Kocmi, Philipp Koehn, Nicholas Lourie, Christof Monz, Makoto Morishita, Masaaki Nagata, Ajay Nagesh, Toshiaki Nakazawa, Matteo Negri, Santanu Pal, Allahsera Auguste Tapo, Marco Turchi, Valentin Vydrin, Marcos Zampieri
Findings of the 2021 Conference on Machine Translation (WMT21). WMT@EMNLP (2021)
Rudolf Rosa, Tomás Musil, Ondrej Dusek, Dominik Jurko, Patrícia Schmidtová, David Marecek, Ondrej Bojar, Tom Kocmi, Daniel Hrbek, David Kosták, Martina Kinská, Marie Nováková, Josef Dolezal, Klára Vosecká, Tomás Studeník, Petr Zabka
THEaiTRE 1.0: Interactive Generation of Theatre Play Scripts. Text2Story@ECIR (2021)
Roman Grundkiewicz, Marcin Junczys-Dowmunt, Christian Federmann, Tom Kocmi
On User Interfaces for Large-Scale Document-Level Human Evaluation of Machine Translation Outputs. CoRR (2021)
Rudolf Rosa, Tomás Musil, Ondrej Dusek, Dominik Jurko, Patrícia Schmidtová, David Marecek, Ondrej Bojar, Tom Kocmi, Daniel Hrbek, David Kosták, Martina Kinská, Marie Nováková, Josef Dolezal, Klára Vosecká, Tomás Studeník, Petr Zabka
When a Robot Writes a Play: Automatically Generating a Theatre Play Script. ALIFE (2021)
Tom Kocmi, Christian Federmann, Roman Grundkiewicz, Marcin Junczys-Dowmunt, Hitokazu Matsushita, Arul Menezes
To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation. CoRR (2021)
Rudolf Rosa, Tomás Musil, Ondrej Dusek, Dominik Jurko, Patrícia Schmidtová, David Marecek, Ondrej Bojar, Tom Kocmi, Daniel Hrbek, David Kosták, Martina Kinská, Marie Nováková, Josef Dolezal, Klára Vosecká, Tomás Studeník, Petr Zabka
THEaiTRE 1.0: Interactive generation of theatre play scripts. CoRR (2021)
Ivana Kvapilíková, Tom Kocmi, Ondrej Bojar
CUNI Systems for the Unsupervised and Very Low Resource Translation Task in WMT20. WMT@EMNLP (2020)
Tom Kocmi
Exploring Benefits of Transfer Learning in Neural Machine Translation. CoRR (2020)
Tom Kocmi, Martin Popel, Ondrej Bojar
Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords. CoRR (2020)
Ivana Kvapilíková, Tom Kocmi, Ondrej Bojar
CUNI Systems for the Unsupervised and Very Low Resource Translation Task in WMT20. CoRR (2020)
Rudolf Rosa, Ondrej Dusek, Tom Kocmi, David Marecek, Tomás Musil, Patrícia Schmidtová, Dominik Jurko, Ondrej Bojar, Daniel Hrbek, David Kosták, Martina Kinská, Josef Dolezal, Klára Vosecká
THEaiTRE: Artificial Intelligence to Write a Theatre Play. CoRR (2020)
Rudolf Rosa, Ondrej Dusek, Tom Kocmi, David Marecek, Tomás Musil, Patrícia Schmidtová, Dominik Jurko, Ondrej Bojar, Daniel Hrbek, David Kosták, Martina Kinská, Josef Dolezal, Klára Vosecká
THEaiTRE: Artificial Intelligence to Write a Theatre Play. AI4Narratives@IJCAI (2020)
Tom Kocmi, Tomasz Limisiewicz, Gabriel Stanovsky
Gender Coreference and Bias Evaluation at WMT 2020. WMT@EMNLP (2020)
Tom Kocmi, Ondrej Bojar
Efficiently Reusing Old Models Across Languages via Transfer Learning. EAMT (2020)
Loïc Barrault, Magdalena Biesialska, Ondrej Bojar, Marta R. Costa-jussà, Christian Federmann, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Matthias Huck, Eric Joanis, Tom Kocmi, Philipp Koehn, Chi-kiu Lo, Nikola Ljubesic, Christof Monz, Makoto Morishita, Masaaki Nagata, Toshiaki Nakazawa, Santanu Pal, Matt Post, Marcos Zampieri
Findings of the 2020 Conference on Machine Translation (WMT20). WMT@EMNLP (2020)
Tom Kocmi, Tomasz Limisiewicz, Gabriel Stanovsky
Gender Coreference and Bias Evaluation at WMT 2020. CoRR (2020)
Tom Kocmi
CUNI Submission for the Inuktitut Language in WMT News 2020. WMT@EMNLP (2020)
Tom Kocmi, Ondrej Bojar
CUNI Submission for Low-Resource Languages in WMT News 2019. WMT (2) (2019)
Tom Kocmi, Ondrej Bojar
Transfer Learning across Languages from Someone Else's NMT Model. CoRR (2019)
Tom Kocmi, Ondrej Bojar
SubGram: Extending Skip-gram Word Representation with Substrings. CoRR (2018)
Tom Kocmi, Roman Sudarikov, Ondrej Bojar
CUNI Submissions in WMT18. WMT (shared task) (2018)
Milan Straka, Nikita Mediankin, Tom Kocmi, Zdenek Zabokrtský, Vojtech Hudecek, Jan Hajic
SumeCzech: Large Czech News-Based Summarization Dataset. LREC (2018)
Tom Kocmi, Ondrej Bojar
Trivial Transfer Learning for Low-Resource Neural Machine Translation. WMT (2018)
Jindrich Helcl, Jindrich Libovický, Tom Kocmi, Tomás Musil, Ondrej Cífka, Dusan Varis, Ondrej Bojar
Neural Monkey: The Current State and Beyond. AMTA (1) (2018)
Tom Kocmi, Dusan Varis, Ondrej Bojar
CUNI Basque-to-English Submission in IWSLT18. IWSLT (2018)
Tom Kocmi, Ondrej Bojar
Trivial Transfer Learning for Low-Resource Neural Machine Translation. CoRR (2018)
Tom Kocmi, Shantipriya Parida, Ondrej Bojar
CUNI NMT System for WAT 2018 Translation Tasks. WAT@PACLIC (2018)
Tom Kocmi, Ondrej Bojar
Curriculum Learning and Minibatch Bucketing in Neural Machine Translation. RANLP (2017)
Tom Kocmi, Ondrej Bojar
An Exploration of Word Embedding Initialization in Deep-Learning Tasks. ICON (2017)
Tom Kocmi, Dusan Varis, Ondrej Bojar
CUNI NMT System for WAT 2017 Translation Tasks. WAT@IJCNLP (2017)
Tom Kocmi, Ondrej Bojar
LanideNN: Multilingual Language Identification on Text Stream. EACL (1) (2017)
Tom Kocmi, Ondrej Bojar
LanideNN: Multilingual Language Identification on Character Window. CoRR (2017)
Tom Kocmi, Ondrej Bojar
An Exploration of Word Embedding Initialization in Deep-Learning Tasks. CoRR (2017)
Ondrej Bojar, Jindrich Helcl, Tom Kocmi, Jindrich Libovický, Tomás Musil
Results of the WMT17 Neural MT Training Task. WMT (2017)
Tom Kocmi, Ondrej Bojar
Curriculum Learning and Minibatch Bucketing in Neural Machine Translation. CoRR (2017)
Roman Sudarikov, David Marecek, Tom Kocmi, Dusan Varis, Ondrej Bojar
CUNI submission in WMT17: Chimera goes neural. WMT (2017)
Ondrej Bojar, Ondrej Cífka, Jindrich Helcl, Tom Kocmi, Roman Sudarikov
UFAL Submissions to the IWSLT 2016 MT Track. IWSLT (2016)
Tom Kocmi, Ondrej Bojar
SubGram: Extending Skip-Gram Word Representation with Substrings. TSD (2016)
Ondrej Bojar, Ondrej Dusek, Tom Kocmi, Jindrich Libovický, Michal Novák, Martin Popel, Roman Sudarikov, Dusan Varis
CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered. TSD (2016)