Michal Novák

office
425
email
mnovak@ufal.mff.cuni.cz
phone
+420 951 554 366
fax
+420 257 223 293
address
Malostranské náměstí 25
118 00 Praha 1
Czech Republic

Main Research Interests

  • coreference / anaphora resolution
  • machine translation
  • machine learning

Projects

Current

  • GAUK 3389/2015 - Cross-lingual approaches to coreference resolution
  • QTLeap - Quality Translation by Deep Language Engineering Approaches

Former

  • EuroMatrix+
  • GAUK 4226/2011 – Utilization of coreference in machine translation
  • Khresmoi – Medical information retrieval (working on Machine Translation)

Curriculum Vitae

  • 2010 Mgr. (Master's degree) in Computational Linguistics, Faculty of Mathematics and Physics, Charles University in Prague.
  • 2008 Bc. (Bachelor's degree) in Computer Science, Faculty of Mathematics and Physics, Charles University in Prague.

Selected Bibliography

  1. Keith Brendan Hall, Václav Novák (2010): Corrective Dependency Parsing. In: Trends in Parsing Technology: Dependency Parsing, Domain Adaptation, and Deep Parsing, pp. 151-168, Springer Science+Business Media B.V., Dordrecht, Netherlands, ISBN 978-90-481-9351-6 (url, biblio, obd)
  2. Ondřej Bojar, David Mareček, Václav Novák, Martin Popel, Jan Ptáček, Jan Rouš, Zdeněk Žabokrtský (2009): English-Czech MT in 2008. In: Proceedings of the Fourth Workshop on Statistical Machine Translation, pp. 125-129, Association for Computational Linguistics, Athina, Greece (pdf, biblio, batt1.pdf, bibtex)
  3. Giang Linh Nguy, Václav Novák, Zdeněk Žabokrtský (2009): Comparison of Classification and Ranking Approaches to Pronominal Anaphora Resolution in Czech. In: Proceedings of the SIGDIAL 2009 Conference, pp. 276-285, The Association for Computational Linguistics, London, UK, ISBN 978-1-932432-64-0 (pdf, biblio, batt1.pdf, bibtex)
  4. Václav Novák, Sven Hartrumpf, Keith Brendan Hall (2009): Large-scale Semantic Networks: Annotation and Evaluation. In: Proceedings of the NAACL HLT Workshop on Semantic Evaluations: Recent Achievements and Future Directions, pp. 37-45, Association for Computational Linguistics , Boulder, CO, USA, ISBN 978-1-932432-31-2 (biblio, batt1.pdf, bibtex)
  5. Václav Novák, Magda Ševčíková (2009): Unsupervised Detection of Annotation Inconsistencies Using Apriori Algorithm. In: Proceedings of the Third Linguistic Annotation Workshop (LAW III) , pp. 138-141, Association for Computational Linguistics, Suntec, Singapore, ISBN 978-1-932432-52-7 (biblio, batt1.pdf, bibtex)
  6. David Mareček, Zdeněk Žabokrtský, Václav Novák (2008): Automatic Alignment of Czech and English Deep Syntactic Dependency Trees. In: Proceedings of the Twelfth EAMT Conference, pp. 102-111, HITEC e.V., Hamburg, Germany, ISBN 978-3-00-025770-4 (pdf, biblio, batt1.pdf, obd, bibtex)
  7. Václav Novák (2008): Semantic Network Manual Annotation and its Evaluation: Extract of Ph.D. Thesis. In: The Prague Bulletin of Mathematical Linguistics, ISSN 0032-6585, 90, pp. 69-82 (biblio, bibtex)
  8. Václav Novák (2008): Semantic Network Manual Annotation and its Evaluation (PhD thesis). Institute of Formal and Applied Linguistics, Charles University, Prague, Czech Republic (pdf, biblio, batt1.pdf, bibtex)
  9. Václav Novák, Keith Brendan Hall (2008): Inter-sentential Coreferences in Semantic Networks: An Evaluation of Manual Annotation. In: Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC 2008), pp. 2746-2751, European Language Resources Association, Marrakech, Morocco, ISBN 2-9517408-4-0 (pdf, biblio, batt1.pdf, bibtex)
  10. Václav Novák (2007): Cedit - Semantic Networks Manual Annotation Tool. In: Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), pp. 11-12, Association for Computational Linguistics, Rochester, NY, USA, ISBN 1-932432-94-9 (url, biblio, bibtex)
  11. Václav Novák (2007): Large Semantic Network Manual Annotation. In: Proceedings of the Seventh International Workshop on Computational Semantics IWCS-7, pp. 355-358, Universiteit van Tilburg, Tilburg, The Netherlands, ISBN 90-74029-31-0 (biblio, bibtex)
  12. Václav Novák, Zdeněk Žabokrtský (2007): Feature Engineering in Maximum Spanning Tree Dependency Parser. In: Proceedings of the 10th International Conference on Text, Speech and Dialogue, Lecture Notes in Computer Science, ISSN 0302-9743, vol. 4629, no. XVII, pp. 92-98, Springer, Berlin / Heidelberg, ISBN 978-3-540-74627-0 (url, biblio, batt1.pdf, bibtex)
  13. Václav Novák (2006): On Distance between Deep Syntax and Semantic Representation. In: Proceedings of Frontiers in Linguistically Annotated Corpora, pp. 78-85, The Association for Computational Linguistics, Sydney, Australia, ISBN 1-932432-78-7 (biblio, bibtex)
  14. Václav Novák, Jan Hajič (2006): Perspectives of Turning Prague Dependency Treebank into a Knowledge Base. In: Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC 2006) , pp. 439-442, ELRA, Genova, Italy, ISBN 2-9517408-2-4 (biblio, batt1.pdf, bibtex)
  15. Keith Brendan Hall, Václav Novák (2005): Corrective Modeling for Non-Projective Dependency Parsing. In: Proceedings of the Ninth International Workshop on Parsing Technologies (IWPT), pp. 42-52, Association for Computational Linguistics, Vancouver, BC, Canada, ISBN 1-932432-58-2 (biblio, batt1.ps, bibtex)
  16. Kiril Ribarov, Jiří Bubník, Jiří Čelák, Vojtěch Janota, Alexandr Kara, Václav Novák, Tomáš Vondra (2004): ACT - Computer Processing of Written Cultural Heritage Sources. In: Proceedings of INFORUM 2004 Conference, Praha (biblio, bibtex)
  17. Kiril Ribarov, Jiří Bubník, Jiří Čelák, Vojtěch Janota, Alexandr Kara, Václav Novák, Tomáš Vondra (2004): The Annotation Corpora of Text (ACT) Tool. In: Scripta & e-Scripta, ISSN 1312-238X, 2, pp. 49-78 (biblio, bibtex)