Publikační databáze ÚFAL

Publikace

• Bushra Jawaid, Daniel Zeman: Word-Order Issues in English-to-Urdu Statistical Machine Translation. In: The Prague Bulletin of Mathematical Linguistics, No. 95, Copyright © Univerzita Karlova, Praha, Czechia, ISSN 0032-6585, pp. 87-106, Apr 2011
  (PDF (1127 KB), Biblio)
• Eduard Bejček, Pavel Straňák, Daniel Zeman: Influence of Treebank Design on Representation of Multiword Expressions. In: Alexander Gelbukh (ed.): CICLing 2011: Computational Linguistics and Intelligent Text Processing. 12th International Conference, CICLing 2011, Tokyo, Japan, February 20-26, 2011. Proceedings, Copyright © Springer, Berlin / Heidelberg, Germany, ISBN 978-3-642-19399-6, ISSN 0302-9743, pp. 1-14, 2011
  (PDF (323 KB), Biblio)
• Daniel Zeman: Morphological Stickers for Annotation of Check. In: Jarmila Panevová, Barbora Vidová Hladká (eds.): Padesát je málo. Komorně laděný sborník u příležitosti 50. narozenin profesora Jana Hajiče, Univerzita Karlova v Praze, Praha, Czechia, pp. 65-70, 2010
  (PDF (156 KB), Biblio)
• Daniel Zeman: Using TectoMT as a Preprocessing Tool for Phrase-Based Statistical Machine Translation. In: Lecture Notes in Computer Science, Vol. 6231, Text, Speech and Dialogue. 13th International Conference, TSD 2010, Brno, Czech Republic, September 6-10, 2010. Proceedings, Copyright © Springer, Masarykova univerzita, Berlin / Heidelberg, ISBN 978-3-642-15759-2, ISSN 0302-9743, pp. 216-223, 2010
  (PDF (96 KB), Biblio)
• Daniel Zeman: Hierarchical Phrase-Based MT at the Charles University for the WMT 2010 Shared Task. In: Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, Copyright © Association for Computational Linguistics, Uppsala Universitet, Uppsala, Sweden, ISBN 978-1-932432-71-8, pp. 212-215, 2010
  (PDF (127 KB), Biblio)
• Ondřej Bojar, Pavel Straňák, Daniel Zeman: Data Issues in English-to-Hindi Machine Translation. In: Proceedings of the 7th International Conference on Language Resources and Evaluation (LREC 2010), Valletta, Malta, 2010
  (PDF (587 KB), Biblio)
• Daniel Zeman: Hard Problems of Tagset Conversion. In: Proceedings of the Second International Conference on Global Interoperability for Language Resources (ICGL-2010), ISBN 978-962-442-323-5, pp. 181-185, City University of Hong Kong, Hong Kong, China, 2010
  (PDF (178 KB), Biblio)
• Daniel Zeman: Maximum Spanning Malt: Hiring World's Leading Dependency Parsers to Plant Indian Trees. In: Proceedings of the 7th International Conference On Natural Language Processing (ICON-2009), International Institute of Information Technologies, Hyderabad, India, 2009
  (PDF (186 KB), Biblio)
• Ondřej Bojar, Pavel Straňák, Daniel Zeman, Gaurav Jain, Michal Hrušecký, Michal Richter, Jan Hajič: English-Hindi Translation - Obtaining Mediocre Results with Bad Data and Fancy Models. In: Proceedings of the 7th International Conference On Natural Language Processing (ICON-2009), International Institute of Information Technologies, Hyderabad, India, 2009
  (PDF (177 KB), Biblio)
• Daniel Zeman: Using Unsupervised Paradigm Acquisition for Prefixes (revised version). In: Lecture Notes in Computer Science, Vol. 5706, Evaluating Systems for Multilingual and Multimodal Information Access - 9th Workshop of the Cross-Language Evaluation Forum, Copyright © Springer Verlag, Berlin / Heidelberg, ISBN 978-3-642-04446-5, ISSN 0302-9743, pp. 983-990, 2009
  (RTF (261 KB), PDF (90 KB), Biblio)
• Daniel Zeman: A Simple Generative Pipeline Approach to Dependency Parsing and Semantic Role Labeling. In: Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL): Shared Task, Association for Computational Linguistics, Boulder, CO, USA, ISBN 978-1-932432-29-9, pp. 120-125, 2009
  (RTF (552 KB), PDF (129 KB), Biblio)
• Ondřej Bojar, Pavel Straňák, Daniel Zeman: English-Hindi Translation in 21 Days. In: Proceedings of ICON 2008 NLP Tools Contest. Puné, Indie, 2008.
  (PDF (128 KB))
• Daniel Zeman: Using Unsupervised Paradigm Acquisition for Prefixes. In: Working Notes for the Cross Language Evaluation Forum (CLEF) 2008 Workshop. Århus, Dánsko, 2008.
  (HTML (180 KB), RTF (288 KB), PDF (182 KB))
• Daniel Zeman: Unsupervised Acquiring of Morphological Paradigms from Tokenized Text (Revised version of the paper from the CLEF Working Notes). In: Carol Peters et al. (eds.): 8th Workshop of the Cross-Language Evaluation Forum, CLEF 2007, Budapest, Hungary, September 2007. Springer Lecture Notes in Computer Science (LNCS 5152), ISSN 0302-9743, pp. 892-899. Springer-Verlag, Berlin / Heidelberg, Germany. To appear in 2008.
  (HTML (75 KB), RTF (207 KB), PDF (117 KB))
• Daniel Zeman: Reusable Tagset Conversion Using Tagset Drivers. In: Proceedings of the Language Resources and Evaluation Conference, LREC 2008. CD full edition + printed Conference Abstracts (ISBN 2-9517408-4-0). Marrákeš, Maroko, 2008.
  (HTML (135 KB), RTF (315 KB), PDF (110 KB))
• Daniel Zeman, Philip Resnik: Cross-Language Parser Adaptation between Related Languages. In: Proceedings of IJCNLP 2008 Workshop on NLP for Less Privileged Languages. Hajdarábádu, Indie, 2008.
  (HTML (186 KB), RTF (561 KB), PDF (201 KB))
• Daniel Zeman: Unsupervised Acquiring of Morphological Paradigms from Tokenized Text. In: Working Notes for the Cross Language Evaluation Forum (CLEF) 2007 Workshop. Budapest, Maďarsko, 2007.
  (HTML (149 KB), RTF (264 KB), PDF (126 KB))
• Daniel Zeman, Zdeněk Žabokrtský: Improving Parsing Accuracy by Combining Diverse Dependency Parsers. In: Proceedings of the International Workshop on Parsing Technologies (IWPT 2005). Simon Fraser University, Vancouver, British Columbia, 2005.
  (HTML (297 KB), RTF (489 KB), PDF (143 KB))
• Jiří Hana, Daniel Zeman: Manual for Morphological Annotation, Revision for the Prague Dependency Treebank 2.0. ÚFAL Technical Report No. 2005-27, 42 pages. Univerzita Karlova, Praha, 2005.
  (HTML (207 KB), XML Docbook (201 KB), PDF (334 KB))
• Daniel Zeman: Neprojektivity v Pražském závislostním korpusu (PDT). CKL/ÚFAL Technical Report No. 2004-22, 35 pages. Univerzita Karlova, Praha, 2004.
  (HTML (442 KB), RTF (721 KB), PDF (302 KB))
• Daniel Zeman: Parsing with a Statistical Dependency Model (PhD thesis). Univerzita Karlova, Praha, 2004.
  (available here)
• Eva Hajičová, Jiří Havelka, Petr Sgall, Kateřina Veselá, Daniel Zeman: Issues of Projectivity in the Prague Dependency Treebank. In: Prague Bulletin of Mathematical Linguistics, volume 81, pages 5-22. ISSN 0032-6585. Univerzita Karlova, Praha, 2004.
  (PDF (190 KB))
• Daniel Zeman: How to Decrease Performance of a Statistical Parser. In: Prague Bulletin of Mathematical Linguistics, volume 78, pages 53-62. ISSN 0032-6585. Univerzita Karlova, Praha, 2002.
  (HTML (190 KB), RTF (301 KB), PostScript (1 MB))
• Daniel Zeman: Can Subcategorization Help a Statistical Dependency Parser? In: Proceedings of the 19th International Conference on Computational Linguistics (Coling 2002). Zhongyang Yanjiuyuan (Academia Sinica), Taibei, Tchaj-wan, 2002.
  (HTML, RTF, PostScript)
• Daniel Zeman: How Much Will a RE-based Preprocessor Help a Statistical Parser? In: Proceedings of the Seventh International Workshop on Parsing Technologies (IWPT 2001), Tsinghua University Press, ISBN 7-302-04925-4. Beijing Daxue, Beijing, Čína, 2001.
  (HTML, RTF, PostScript)
• Daniel Zeman: Parsing with Regular Expressions: A Minute to Learn, a Lifetime to Master. In: Prague Bulletin of Mathematical Linguistics, volume 75, pages 29-37. ISSN 0032-6585. Univerzita Karlova, Praha 2001.
  (HTML, RTF, PostScript)
• Anoop Sarkar, Daniel Zeman: Automatic Extraction of Subcategorization Frames for Czech. In: Proceedings of the 18th International Conference on Computational Linguistics (Coling 2000), Universität des Saarlandes, Saarbrücken, Německo, 2000.
  (PostScript, Latex)
• Daniel Zeman, Anoop Sarkar: Learning Verb Subcategorization from Corpora: Counting Frame Subsets. In: Proceedings of the Second International Conference on Language Resources and Evaluation (LREC 2000). ELRA, Athîna, Řecko, 2000.
  (PDF, PostScript, Microsoft Word 97)
• Jan Hajič, Eric Brill, Michael Collins, Barbora Hladká, Douglas Jones, Cynthia Kuo, Lance Ramshaw, Oren Schwartz, Christoph Tillmann, Daniel Zeman: Core Natural Language Processing Technology Applicable to Multiple Languages. The Workshop 98 Final Report. At: http://www.clsp.jhu.edu/ws98/projects/nlp/report/. Center for Language and Speech Processing, Johns Hopkins University, Baltimore 1998.
  (HTML, zazipované RTF, zazipovaný Postscript)
  Zkrácená verze také v: Prague Bulletin of Mathematical Linguistics, volume 70, pages 73-82. ISSN 0032-6585.
• Daniel Zeman: A Statistical Approach to Parsing of Czech. In: Prague Bulletin of Mathematical Linguistics, volume 69, pages 29-37. ISSN 0032-6585. Univerzita Karlova, Praha 1998.
  (HTML, zazipované RTF, zazipovaný Postscript)
• Daniel Zeman: Pravděpodobnostní model významových zápisů vět (Diplomová práce). Matematicko-fyzikální fakulta Univerzity Karlovy, Praha 1997.
  (HTML, zazipované RTF)