Resume of Daniel Zeman
Personal and family data
Born: December 21, 1971, Praha (Czechoslovakia)
Married: April 16, 1999, Praha (Czechia)
Sex: Male
Citizenship: Czech
Affiliation
ÚFAL MFF UK
(Institute of Formal and Applied Linguistics,
Faculty of Mathematics and Physics, Charles University), Malostranské
náměstí 25, Praha 1, CZ-11800
Education
- 2005, Univerzita Karlova (Charles University), Praha
- Obtained the RNDr. title.
- 13.1.2005, Univerzita Karlova (Charles University), Praha
- Obtained Ph.D. in mathematical linguistics
- 1999, May-July: University of Pennsylvania, Philadelphia (Pennsylvania, USA)
- visiting scholar at the Institute
for Research in Cognitive Science. Invited by
Aravind Joshi
to work together with
Anoop Sarkar
on automatic acquiring of subcategorization frames from the Prague Dependency
Treebank.
- 1998, July-August: Johns Hopkins University, Baltimore (Maryland, USA)
- participation in the summer workshop
Core NLP Technology Applicable
to Multiple Languages at the Center for Language and Speech Processing.
- 1997 to 2005: Univerzita Karlova (Charles University), Praha
- Graduate student of mathematical linguistics at the Faculty of Mathematics
and Physics. The PhD thesis topic: Parsing with a Statistical Dependency Model. Special interest in syntax.
- 1990 to 1997: Univerzita Karlova, Praha
- undergraduate study of Computer
Science at the Faculty of Mathematics and Physics.
Regular study finished with the fifth year on October 10,
1995. Thesis and final examination in the field of Computational and
Formal Linguistics. The exam was passed in June 1997. Obtained the title
"magistr" ("Mgr.", an equivalent to MSc.).
- 1986 to 1990: Akademické gymnázium (The Academical Grammar School), Praha
- regular study with specialization in programming. In 1990 finished
with the leaving examination in Mathematics, Programming, Czech and
German Languages.
Teaching experience
- 2001-2002: Programování (Programming), workshop leader,
Faculty of Mathematics and Physics, Charles University.
- 2000-2005: Počítače a přirozený jazyk (Computers and Natural Language), lecturer,
faculty of Nuclear Sciences and Physical Engineering, Czech Technical University.
- 1999-2005: Počítačové zpracování
češtiny (Automatic Processing of Czech); since winter 2003/2004 Počítačové zpracování přirozeného jazyka (Automatic Processing of Natural Language), lecturer and workshop
leader, Faculty of Mathematics and Physics, Charles University.
Professional positions
- 2006: University of Maryland, College Park.
- Awarded Fulbright-Masaryk Fellowship (January to July), postdoc (July to December). I worked with Philip Resnik at the University of Maryland,
Institute for Advanced Computer Studies,
Computational Linguistics & Information Processing.
- since 2000: Univerzita Karlova, Praha
- Researcher, Center for Computational Linguistics, since 2004 Institute of Formal and Applied Linguistics.
Research interests: statistical parsing of Czech, dependency modeling.
- 1995 to 1999: Olt s.r.o., Praha
- after finishing the regular MSc. study at Charles University, I
started
my cooperation with the Prague software firm Olt s.r.o. I have been
developing parts of their programs for Windows NT, e.g. a built-in text
editor (in C++).
- 1994: SSaG s.r.o., Praha
- during the study, from April to November 1994 I worked as programmer.
Awards
Publications and talks
I do not update this section regularly. An up-to-date list of publications can be found here.
- 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))
Cited in:
- Václav Klimeš: Analytical and Tectogrammatical Analysis of a Natural Language (Ph.D. thesis).
Univerzita Karlova, Praha, 2006.
- 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 (210 KB),
XML Docbook (205 KB),
PDF (492 KB))
Cited in:
- Barbora Vidová Hladká, Ondřej Bojar, Jan Hajič, Jiří Hana, Jaroslava Hlaváčová, Jiří Mírovský, Jan Votrubec:
Průvodce Českým akademickým korpusem 1.0. Univerzita Karlova, Praha, 2006.
- 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)
Cited in:
- Václav Klimeš: Analytical and Tectogrammatical Analysis of a Natural Language (Ph.D. thesis).
Univerzita Karlova, Praha, 2006.
- Keith Hall, Václav Novák: Corrective Modeling for Non-Projective Dependency Parsing. In: Proceedings of the Ninth International Workshop on Parsing Technologies (IWPT-05), pp. 42-52. The Association for Computational Linguistics, Vancouver, British Columbia, 2005.
- 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))
Cited in:
- Keith Hall, Václav Novák: Corrective Modeling for Non-Projective Dependency Parsing. In: Proceedings of the Ninth International Workshop on Parsing Technologies (IWPT-05), pp. 42-52. The Association for Computational Linguistics, Vancouver, British Columbia, 2005.
- 2002, October:
Daniel Zeman:
How to Decrease Performance of a Statistical Parser.
In: Prague Bulletin of Mathematical Linguistics, volume 78, pages 53-62.
Univerzita Karlova, Praha, 2002.
(HTML (190 KB),
RTF (301 KB),
PostScript (1 MB))
- 2002, August, Coling:
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)
Cited in:
- Ondřej Bojar: Automatizovaná extrakce lexikálně syntaktických údajů z korpusu (master thesis). Univerzita Karlova, Praha, 2002.
- Péter Dienes: Statistical parsing with non-local
dependencies (PhD Dissertation). Saarbrücken Dissertations
in Computational Linguistics and Language Technology,
vol. 20. Universität des Saarlandes, Saarbrücken, 2005.
- 2001, October 19: talk and paper at the
International Workshop on Parsing Technologies (IWPT) 2001, Beijing.
Title: How Much Will a RE-based Preprocessor Help a Statistical Parser?
Cited in:
- Václav Klimeš: Analytical and Tectogrammatical Analysis of a Natural Language (Ph.D. thesis).
Univerzita Karlova, Praha, 2006.
- Ondřej Bojar: Automatizovaná extrakce lexikálně syntaktických údajů z korpusu (master thesis).
Univerzita Karlova, Praha, 2002.
- 2001: Parsing with Regular Expressions: A Minute to Learn, a Lifetime to Master.
In: Prague Bulletin of Mathematical Linguistics, volume 75, pages 29-37. Univerzita Karlova, Praha 2001.
Cited in:
- Ondřej Bojar: Automatizovaná extrakce lexikálně syntaktických údajů z korpusu (master thesis). Univerzita Karlova, Praha, 2002.
- 2000, August 1: talk and paper at the conference
Coling 2000, Saarbrücken. Title:
Automatic Extraction of Subcategorization Frames for Czech
(co-author: Anoop Sarkar; a modified version of the Athens paper).
Cited in:
- Anna Korhonen: Using Semantically Motivated Estimates to Help Subcategorization Acquisition. In: Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora. Hong Kong, China, 2000.
- Anna Korhonen, Genevieve Gorrell, Diana McCarthy: Statistical Filtering and Subcategorization Frame Acquisition. In: Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora. Hong Kong, China, 2000.
- Katia-Lîda Kermanidou, Manolis Maragoudakîs, Nikos Fakôtakîs, Geôrgios Kokkinakîs: Influence of Conditional Independence Assumption on Verb Subcategorization Detection. In: Václav Matoušek et al. (eds.): "Proceedings of TSD 2001" , Springer LNAI 2166, pp. 62-69. Železná Ruda, Czechia, 2001.
- Anna Korhonen: Subcategorization Acquisition (PhD thesis). Cambridge University, Cambridge, England, 2002.
- 2000, May 31: talk and paper at the conference
LREC 2000, Athîna.
Title:
Learning Verb Subcategorization from Corpora: Counting Frame
Subsets (co-author: Anoop Sarkar).
- 1999, July 29: talk at IRCS, Philadelphia (Pennsylvania, USA). Title:
Learning Verb Subcategorization from Corpora.
- 1998, September: poster presentation at the conference
"Text, Speech
and Dialogue", Brno (Czechia). Title: Parsing Czech with Statistics.
- 1998: 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 (Maryland, USA).
Cited in:
- Michael Collins: Head-Driven Statistical Models for Natural Language
Parsing (PhD Dissertation). University of Pennsylvania, Philadelphia,
1999.
- Barbora Hladká: Czech Language Tagging (PhD Dissertation).
Univerzita Karlova, Praha, 2000.
- Tomáš Holan: Nástroje pro vývoj závislostních analyzátorů přirozených jazyků s volným slovosledem (disertační práce).
Univerzita Karlova, Praha, 2001.
- Vladislav Kuboň: Problems of Robust Parsing of Czech (PhD Dissertation).
Univerzita Karlova, Praha, 2001.
- 1998: A Statistical Approach to Parsing of Czech. In: Prague Bulletin of
Mathematical Linguistics, volume 69, pages 29-37. Univerzita Karlova,
Praha (Czechia).
Cited in:
- Barbora Hladká: Czech Language Tagging (PhD Dissertation).
Univerzita Karlova, Praha, 2000.
- Péter Dienes: Statistical parsing with non-local
dependencies (PhD Dissertation). Saarbrücken Dissertations
in Computational Linguistics and Language Technology,
vol. 20. Universität des Saarlandes, Saarbrücken, 2005.
- 1998, June: talk at the conference "Week of Doctoral Students", Praha
(Czechia). Title: Parsing Natural Languages: Statistical Methods.
- 1997: Pravdepodobnostni model vyznamovych zapisu vet. (In Czech - master
degree thesis.) Matematicko-fyzikalni fakulta, Univerzita Karlova, Praha
(Czechia).
Cited in:
- Markéta Straňáková: Homonymie předložkových skupin v češtině a možnost jejich automatického zpracování (PhD thesis). Univerzita Karlova, Praha, 2001.
- Ondřej Bojar: Automatizovaná extrakce lexikálně syntaktických údajů z korpusu (master thesis). Univerzita Karlova, Praha, 2002.
Reviews
- Reviewer
COLING-ACL 2006 (section Parsing),
Macquarie University, Sydney, Australia.
- Reviewer (section Parsing),
COLING 2002,
Academia Sinica, Taibei, Taiwan.
- Reviewer,
ACL 2002,
University of Pennsylvania, Philadelphia, Pennsylvania.
- Reviewer,
ACL 1999,
University of Maryland, College Park, Maryland.
- Reviewer,
EACL 1999,
Universitetet i Bergen, Bergen, Norway.
Languages
German, English, Russian (sufficient knowledge for communication,
although not fluent). Spanish (basic knowledge). Of course, fluent in
Czech and able to understand Slovak (well) and Polish (a little).
Programming environments
- Programming languages:
- Perl, C++, Visual Basic
- Operating systems:
- Windows, Linux
Other interests
travel, alpine tourism, canoeing; languages, computers
References
Doc. Jan Hajič
Ústav formální a aplikované lingvistiky
Matematicko-fyzikální fakulta
Univerzita Karlova
Malostranské náměstí 25
CZ-11800 Praha
Czechia
tel. +420-221-914-257
hajic -at- ufal -dot- mff -dot- cuni -dot- cz
Prof. Frederick Jelinek
Center for Language and Speech Processing
Johns Hopkins University
Barton Hall
3400 North Charles Street
Baltimore, MD 21218
USA
tel. +1-410-516-7730
jelinek -at- jhu -dot- edu
Prof. Philip Resnik
Institute for Advanced Computer Studies
University of Maryland
3143 A. V. Williams Building
College Park, MD 20742
USA
tel. +1-301-405-6760
resnik -at- umiacs -dot- umd -dot- edu