Martin Popel

Main Research Interests

MT (syntax-based, neural), Universal Dependencies, machine learning, parsing, language modeling, MT evaluation, treebanking

Projects

Grants: QTLeap, Manyla, Khresmoi, EuroMatrixPlus

Technical editor: The Prague Bulletin of Mathematical Linguistics and ÚFAL technical reports

Projects / Software / Data

• Udapi (NLP framework) [GitHub]
• Treex (NLP framework) [GitHub]
• TectoMT (MT system)
• Universal Dependencies, in past: HamleDT (harmonized dependency treebanks)
• MT-ComparEval a tool for comparison and evaluation of MT outputs See wmt.ufal.cz for a live demo.

Older tools/data

• Perl implementation of ComparEval and a sample HTML output
• older Perl script for BLEU confidence intervals evaluation via pairwise bootstrap resampling
• manual annotation of translation errors 250 sentences translated by TectoMT in 2009

Curriculum Vitae

• since 2009 Ph.D. student, Mathematical Linguistics, ÚFAL MFF UK.  Thesis: Machine Translation Using Syntactic Analysis
• 2007–2009 Master's degree in Mathematical Linguistics, with honours, MFF UK. Thesis: Ways to Improve the Quality of English-Czech Machine Translation
• 2003–2007 Bachelor's degree in Computer Science, MFF UK. Thesis: Animation of Algorithms from Automata Theory (in Czech)

Teaching

List of classesNPFL095 Modern Methods in Computational LinguisticsNPFL118 Natural language processing on computational cluster

Teaching

• NPFL095 Modern Methods in Computational Linguistics, see the web with schedule
• NPFL070 Language Data Resources (with Zdeněk Žabokrtský)
• NPFL118 Natural language processing on computational cluster

Selected Bibliography

2017

• Martin Popel, Zdenek Žabokrtský, Martin Vojtek: Udapi: Universal API for Universal Dependencies In Proceedings of UDW 2017, Göteborg, Sweden, May 2017, pp. 96–101 [pdf] [slides]
• Daniel Zeman, Martin Popel, Milan Straka, Jan Hajič, Joakim Nivre et al.: CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies In Proceedings of CoNLL 2017, Vancouver, Canada, August 2017, pp. 1–19 [pdf]

2016

• Roman Sudarikov, Martin Popel, Ondřej Bojar, Aljoscha Burchardt and Ondřej Klejch: Using MT-ComparEval In Proceedings of MT-Eval LREC 2016, Portorož, Slovenia, May 2016, pp. 76–82 [pdf] [slides]
• Nora Aranberri, Eleftherios Avramidis, Aljoscha Burchardt, Ondřej Klejch, Martin Popel, Maja Popović: Tools and Guidelines for Principled Machine Translation Development In Proceedings of LREC 2016, Portorož, Slovenia, May 2016, pp. 1877–1882 [pdf] [poster]
• Arantxa Otegi, Nora Aranberri, António Branco, Jan Hajič, Martin Popel, Kiril Simov, Eneko Agirre, Petya Osenova, Rita Pereira, João Silva, Steven Neale: QTLeap WSD/NED Corpora: Semantic Annotation of Parallel Corpora in Six Languages In Proceedings of LREC 2016, Portorož, Slovenia, May 2016, pp. 3023–3030 [pdf]
• Martin Popel; Roman Sudarikov, Ondřej Bojar, Rudolf Rosa, Jan Hajič: TectoMT – a deep-­linguistic core of the combined Chimera MT system In: Baltic Journal of Modern Computing, Vol. 4, No. 2, Riga, Latvia, pp. 377–377 [pdf]
• Rudolf Rosa, Roman Sudarikov, Michal Novák, Martin Popel, Ondřej Bojar: Dictionary-based Domain Adaptation of MT Systems without Retraining In Proceedings of WMT 2016, Berlin, Germany, August 2016, pp. 449–455 [pdf] [poster]
• Rosa Gaudio, Gorka Labaka, Eneko Agirre, Petya Osenova, Kiril Simov, Martin Popel, Dieke Oele, Gertjan van Noord, Luís Gomes, João António Rodrigues, Steven Neale, João Silva, Andreia Querido, Nuno Rendeiro and António Branco: SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task In Proceedings of WMT 2016, Berlin, Germany, August 2016, pp. 435–441 [pdf] [poster]
• Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Varvara Logacheva, Christof Monz, Matteo Negri, Aurelie Neveol, Mariana Neves, Martin Popel, Matt Post, Raphael Rubino, Carolina Scarton, Lucia Specia, Marco Turchi, Karin Verspoor and Marcos Zampieri: Findings of the 2016 Conference on Machine Translation In Proceedings of WMT 2016, Berlin, Germany, August 2016, pp. 131–198 [pdf] [slides]
• Ondřej Bojar, Ondřej Dušek, Tom Kocmi, Jindřich Libovický, Michal Novák, Martin Popel, Roman Sudarikov, Dušan Variš: CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered In Proceedings of TSD 2016, Brno, September 2016, pp. 231–238 [pdf-Springer]

2015

• Ondřej Dušek, Eva Fučíková, Jan Hajič, Martin Popel, Jana Šindlerová, Zdeňka Urešová: Using Parallel Texts and Lexicons for Verbal Word Sense Disambiguation In Proceedings of Depling 2015, Uppsala, Sweden, August 2015, pp. 82–90 [pdf]
• Ondřej Dušek, Luís Gomes, Michal Novák, Martin Popel, Rudolf Rosa: New Language Pairs in TectoMT Proceedings of WMT2015, Lisbon, Portugal, September 2015, pp. 98–104 [pdf] [poster]
• Ondřej Klejch, Eleftherios Avramidis, Aljoscha Burchardt, Martin Popel: MT-ComparEval: Graphical evaluation interface for Machine Translation development The Prague Bulletin of Mathematical Linguistics, No. 104, 2015, pp. 63–74 [pdf] [poster]
• Rudolf Rosa, Ondřej Dušek, Michal Novák, Martin Popel: Translation Model Interpolation for Domain Adaptation in TectoMT In Proceedings of the 1st Deep Machine Translation Workshop, Praha, Czechia, September 2015, pp. 89–96 [pdf]

2014

• Rudolf Rosa, Jan Mašek, David Mareček, Martin Popel, Daniel Zeman, Zdeněk Žabokrtský: HamleDT 2.0: Thirty Dependency Treebanks Stanfordized In Proceedings of LREC 2014, Reykjavík, Iceland, May 2014, pp. 2334–2341. [pdf]
• Aleš Tamchyna, Martin Popel, Rudolf Rosa, Ondřej Bojar: CUNI in WMT14: Chimera Still Awaits Bellerophon In Proceedings of WMT 2014, Baltimore, MD, USA, June 2014, pp. 195–200. [pdf]
• Daniel Zeman, Ondřej Dušek, David Mareček, Martin Popel, Loganathan Ramasamy, Jan Štěpánek, Zdeněk Žabokrtský, Jan Hajič: HamleDT: Harmonized Multi-Language Dependency Treebank In: Language Resources and Evaluation, Vol. 2014, Copyright © Springer Netherlands, ISSN 1574-020X, pp. 1–40. [official pdf] [self-archived pdf]
• Pavel Pecina et al.: Adaptation of machine translation for multilingual information retrieval in medical domain In: Artificial Intelligence in Medicine, Vol. 61, No. 3, Copyright © Elsevier, ISSN 0933-3657, Jul 2014, pp. 165–185. [pdf]

2013

• Martin Popel, David Mareček, Jan Štěpánek, Daniel Zeman, Zdeněk Žabokrtský: Coordination Structures in Dependency Treebanks In Proceedings of ACL 2013, Sofia, Bulgaria, August 5–7, 2013, pp. 517–527. [pdf] [poster]
• Petra Galuščáková, Martin Popel, Ondřej Bojar: PhraseFix: Statistical Post-Editing of TectoMT In Proceedings of WMT 2013, Sofia, Bulgaria, August 8–9, 2013, pp. 141–147. [pdf]
• David Mareček, Martin Popel, Loganathan Ramasamy, Jan Štěpánek, Daniel Zeman, Zdeněk Žabokrtský, Jan Hajič: Cross-language Study on Influence of Coordination Style on Dependency Parsing Performance ÚFAL Technical report, [pdf]
• Niraj Aswani et al.: Khresmoi Professional: Multilingual Semantic Search for Medical Professionals In Proceedings of the ACM SIGIR Workshop on Health Search and Discovery: Helping Users and Advancing Medicine, Microsoft Research, Cambridge, UK, 2013, pp. 31–34. [pdf]

2012

• Rudolf Rosa, Ondřej Dušek, David Mareček, Martin Popel: Using Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors In Proceedings of ACL SSST-6, Jeju, Korea, July 12, 2012, pp. 39–48. [pdf]
• Ondřej Dušek, Zdeněk Žabokrtský, Martin Popel, Martin Majliš, Michal Novák, and David Mareček: Formemes in English-Czech Deep Syntactic MT. In Proceedings of WMT 2012, Montréal, Canada, June 7–8, 2012, pp. 267–274. [pdf]
• Ondřej Bojar, Zdeněk Žabokrtský, Ondřej Dušek, Petra Galuščáková, Martin Majliš, David Mareček, Jiří Maršík, Michal Novák, Martin Popel, and Aleš Tamchyna: The Joy of Parallelism with CzEng 1.0. In Proceedings of LREC 2012, Istanbul, Turkey, May 21–27, 2012, pp. 3921–3928. [pdf]
• Daniel Zeman, David Mareček, Martin Popel, Loganathan Ramasamy, Jan Štěpánek, Zdeněk Žabokrtský, Jan Hajič: HamleDT: To Parse or Not to Parse?. In Proceedings of LREC 2012, Istanbul, Turkey, May 21–27, 2012, pp. 2735–2741. [pdf]

2011

• Ondřej Bojar, Miloš Ercegovčević, Martin Popel and Omar Zaidan: A Grain of Salt for the WMT Manual Evaluation. In Proceedings of WMT 2011, EMNLP 6th Workshop on Statistical Machine Translation, Edinburgh, UK, July 30, 2011, pp. 1–11. [pdf] presentation [pdf]
• Martin Popel, David Mareček, Nathan Green and Zdeněk Žabokrtský: Influence of Parser Choice on Dependency-Based MT. In Proceedings of WMT 2011, EMNLP 6th Workshop on Statistical Machine Translation, Edinburgh, UK, July 31, 2011, pp. 433–439. [pdf] poster [jpg]

2010

• Martin Popel, David Mareček: Perplexity of n-gram and Dependency Language Models. In Proceedings of TSD 2010, 13th International Conference on Text, Speech and Dialog, Brno, Czechia, September 8, 2010, pp. 173–180. [pdf] presentation [pdf]
• Martin Popel, Zdeněk Žabokrtský: TectoMT: Modular NLP Framework. In Proceedings of IceTAL, 7th International Conference on Natural Language Processing, Reykjavík, Iceland, August 17, 2010, pp. 293–304. [pdf] presentation [pdf]
• David Mareček, Martin Popel, Zdeněk Žabokrtský: Maximum Entropy Translation Model in Dependency-Based MT Framework. In Proceedings of the Joint 5th Workshop on Statistical Machine Translation and MetricsMATR, Uppsala, Sweden, 15–16 July 2010, pp. 201–206. [pdf] poster [pdf]
• Martin Popel: English-Czech Machine Translation Using TectoMT. In Proceedings of the 19th Annual Conference of Doctoral Students WDS 2010, Prague, Czech Republic, 1–4 June 2010, pp. 88–93. [pdf] presentation [pdf]

2009

• Martin Popel, Zdeněk Žabokrtský: Improving English-Czech Tectogrammatical MT. In The Prague Bulletin of Mathematical Linguistics No. 92, 2009, pp. 115–134. [pdf]
• Zdeněk Žabokrtský, Martin Popel: Hidden Markov Tree Model in Dependency-based Machine Translation. In Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics, Singapore, 2009, pp. 145–148 [pdf] poster [ppt]
• Ondřej Bojar, David Mareček, Václav Novák, Martin Popel, Jan Ptáček, Jan Rouš, Zdeněk Žabokrtský: English-Czech MT in 2008. In Proceedings of the Fourth Workshop on Statistical Machine Translation, Athens, Greece. Association for Computational Linguistics, 2009 [pdf]

For citations see Google Scholar, for bibtex entries see Biblio.

Students

• 2010–2011 Master student Amir Kamran (Hybrid MT Approaches for Low-Resource Languages)
• 2011–2012 Bachelor student Michal Koutný (Word prediction using language models)
• 2011–2013 Bachelor student Ondřej Klejch (Tool for comparison and evaluation of machine translation)
• 2012–2013 Bachelor student Michal Sedlák (Web Interface for the Treex Framework), see Treex::Web