Research

Main Research Projects and Activities

• Theoretical and applicational aspects of computational linguistics (Petr Sgall, Jan Hajič, Jarmila Panevová, Eva Hajičová)
• European Research Projects
  • Khresmoi
  • FAUST
  • EuromatrixPlus
  • META-NET
  • Clarin
  • Lindat-Clarin
  • Malach
  • MosesCore
• International Teaching/Training Projects
  • Erasus Mundus Master Program in Language and Communication Technologies
  • CLARA
• Corpora and Their Annotation
  • Prague Dependency Treebank, 2.0 (Pražský závislostní korpus, 2.0 ) (Eva Hajičová)
  • Czech Academic Corpus (Barbora Hladká)
  • Prague Dependency Treebank of Spoken Language (Czech, English) - current status (v0.5)
  • Discourse Annotation in PDT (Eva Hajičová, Šárka Zikánová)
  • Prague English Dependency Treebank, 2.0
  • Prague Arabic Dependency Treebank (Otakar Smrž)
  • Prague Czech-English Dependency Treebank, version 2.0
  • CzEng 1.0 (Czech-English Parallel Corpus, version 1.0) (Ondřej Bojar, Zdeněk Žabokrtský)
  • ÚFAL Multilingual Corpora (UMC) (Ondřej Bojar)
• Valency lexicons
  • Valency Lexicon of Czech Verbs VALLEX (Markéta Lopatková, Zdeněk Žabokrtský, Václava Kettnerová)
  • Valency Lexicon PDT-VALLEX (Zdeňka Urešová)
  • Valency of Czech Nouns (Veronika Řezníčková)
  • EngVallex (Jana Šindlerová, Jan Hajič jr.)
  • SPR – Semantic Pattern Recognition (Silvie Cinková, Martin Holub)
• Machine Translation
  • EuroMatrix
  • Statistical Machine Translation, Moses (Ondřej Bojar)
  • TectoMT (Zdeněk Žabokrtský, Martin Popel)
  • Česílko (Jan Hajič, Vladislav Kuboň)
• Morphology
  • Morphological tagging (Barbora Vidová-Hladká)
• Parsing
  • Czech Language Parsing (Daniel Zeman)
• Speech recognition
  • Nino Peterek
• Statistical Dialog Systems
  • Vystadial (Filip Jurčíček)
• Machine Learning for NLP
  • Barbora Vidová-Hladká & Martin Holub
• Other
  • Mutual Information-based Classes (MMI clustering) (David Klusáček)

Other Activities

• The Prague Bulletin of Mathematical Linguistics (PBML)
• The Vilem Mathesius Centre
• Centrum vizuální historie Malach 
• Technical Reports

Important Past Activities

• 45th Meeting of the Association for Computational Linguistics (ACL 2007) (June 24-29, 2007)
• “Treebanks and Linguistic Theories” Conference (TLT 2006) (Dec 1-2, 2006)
• XVII International Congress of Linguists (CIL 17), July 24-29, 2003 (Anna Kotěšovcová)
  Report (MS Word, 35kB), Zpráva o akci (MS Word, 39kB, )
• Speaker Identification, 2002-2003 (Jan Hajič)
  post-workshop award, Baltimore 2002
• Workshop Baltimore 2002
  generation in MT; speaker recognition
• 9th ELSNET European Summer School on Language and Speech Communication, July 16-27, 2001
• Workshop Baltimore 1999
  machine translation; speech recognition
• Workshop Baltimore 1998
  syntactic parsing
• ESSLLI 1996 (Geert-Jan Kruijff, Ivana Kruijff-Korbayová)
• RUSLAN, 1987-1990
  machine translation Czech to Russian
• ASIMUT
  automatical declension of Czech words