DANIEL GILDEA
Department of Computer Science
University of Rochester
PO Box 270226
Rochester NY 14627
| PhD |
2001 |
Computer Science, University of California, Berkeley. |
| |
|
Directed by Nelson Morgan, Daniel Jurafsky, Charles Fillmore, Jerome Feldman. |
| |
|
Dissertation: Statistical Language Understanding Using Frame Semantics
|
| MS |
1999 |
Computer Science, University of California, Berkeley. |
| |
|
Thesis: Topic-Based Language Models Using EM
|
| BA |
1995 |
Double major in Linguistics and Computer Science, |
| |
|
University of California, Berkeley. |
- statistical machine translation
- natural language understanding, including syntactic parsing
and semantic interpretation
- machine learning algorithms
Current projects include syntax-based word alignment for
statistical machine translation, unsupervised acquisition of verb
alternation behavior, and automatic identification of semantic roles.
- 9/03 -
- Assistant professor,
Department of Computer Science, University of Rochester.
- 9/01 - 8/03
- Postdoctoral fellow, Institute for Research in Cognitive Science and
Department of Computer and Information Science, University of Pennsylvania.
- 8/96 - 8/01
- Research assistant, International Computer Science Institute,
Berkeley, California. Affiliated with Speech and
Artificial Intelligence groups. Projects included language modeling and
pronunciation modeling for speech recognition, natural language understanding,
and statistical parsing.
- 7/95 - 3/96
- Software engineer, PA-RISC compiler group, Hewlett-Packard Corporation.
Journal Articles
Enumeration of Factorizable Multi-Dimensional Permutations,
Hao Zhang and Daniel Gildea.
Journal of Integer Sequences, 07(5.8), 2007.
The
Proposition Bank: An Annotated Corpus of Semantic Roles,
Martha Palmer, Daniel Gildea, and Paul Kingsbury.
Computational Linguistics, 31(1):71-106, 2005.
Effects of
disfluencies, predictability, and utterance position on word form variation
in English conversation,
Alan Bell, Daniel Jurafsky, Eric Fosler-Lussier, Cynthia Girand, Michelle
Gregory, and Daniel Gildea.
Journal of the Acoustical Society of America, 113(2):1001-1024,
2003.
Automatic Labeling
of Semantic Roles,
Daniel Gildea and Daniel Jurafsky.
Computational Linguistics, 28(3):245-288, 2002.
Learning Bias and
Phonological Rule Induction,
Daniel Gildea and Daniel Jurafsky.
Computational Linguistics, 22(4):497-530, 1996.
Refereed Conference Papers
Extracting Synchronous Grammar Rules From Word-Level Alignments in Linear
Time,
Hao Zhang, Daniel Gildea, and David Chiang.
In Proceedings of the 22nd International Conference on Computational
Linguistics (COLING-08), Manchester, UK, 2008.
Efficient Multi-pass Decoding for Synchronous Context Free Grammars,
Hao Zhang and Daniel Gildea.
In Proceedings of the 46th Annual Meeting of the Association for
Computational Linguistics (ACL-08), Columbus, Ohio, 2008.
Bayesian Learning of Non-compositional Phrases with Synchronous
Parsing,
Hao Zhang, Chris Quirk, Robert C. Moore, and Daniel Gildea.
In Proceedings of the 46th Annual Meeting of the Association for
Computational Linguistics (ACL-08), Columbus, Ohio, 2008.
Optimizing Grammars for Minimum Dependency Length,
Daniel Gildea and David Temperley.
In Proceedings of the 45th Annual Conference of the Association for
Computational Linguistics (ACL-07), 2007.
Worst-Case Synchronous Grammar Rules,
Daniel Gildea and Daniel Stefankovic.
In Proceedings of the 2007 Meeting of the North American chapter of the
Association for Computational Linguistics (NAACL-07), 2007.
Source-Language Features and Maximum Correlation Training for Machine Translation
Evaluation,
Ding Liu and Daniel Gildea.
In Proceedings of the 2007 Meeting of the North American chapter of the
Association for Computational Linguistics (NAACL-07), 2007.
Efficient Search for Inversion Transduction Grammar,
Hao Zhang and Daniel Gildea.
In 2006 Conference on Empirical Methods in Natural Language Processing
(EMNLP), Sydney, 2006.
Inducing Word Alignments with Bilexical Synchronous Trees,
Hao Zhang and Daniel Gildea.
In Proceedings of the International Conference on Computational
Linguistics/Association for Computational Linguistics (COLING/ACL-06) Poster
Session, Sydney, 2006.
Factoring Synchronous Grammars by Sorting,
Daniel Gildea, Giorgio Satta, and Hao Zhang.
In Proceedings of the International Conference on Computational
Linguistics/Association for Computational Linguistics (COLING/ACL-06) Poster
Session, Sydney, 2006.
Stochastic Iterative Alignment for Machine Translation Evaluation,
Ding Liu and Daniel Gildea.
In Proceedings of the International Conference on Computational
Linguistics/Association for Computational Linguistics (COLING/ACL-06) Poster
Session, Sydney, 2006.
Synchronous Binarization for Machine Translation,
Hao Zhang, Liang Huang, Daniel Gildea, and Kevin Knight.
In Proceedings of the 2006 Meeting of the North American chapter of the
Association for Computational Linguistics (NAACL-06), pages 256-263,
2006.
Stochastic
Lexicalized Inversion Transduction Grammar for Alignment,
Hao Zhang and Daniel Gildea.
In Proceedings of the 43rd Annual Conference of the Association for
Computational Linguistics (ACL-05), 2005.
Dependencies
vs. Constituents for Tree-Based Alignment,
Daniel Gildea.
In 2004 Conference on Empirical Methods in Natural Language Processing
(EMNLP), Barcelona, 2004.
Syntax-Based Alignment: Supervised or Unsupervised?,
Hao Zhang and Daniel Gildea.
In Proceedings of the 20th International Conference on Computational
Linguistics (COLING-04), Geneva, Switzerland, August 2004.
Skeletons in
the Parser: Using a Shallow Parser to Improve Deep Parsing,
Mary Swift, James Allen, and Daniel Gildea.
In Proceedings of the 20th International Conference on Computational
Linguistics (COLING-04), pages 383-389, Geneva, Switzerland, August
2004.
A Smorgasbord of
Features for Statistical Machine Translation,
Franz Josef Och, Daniel Gildea, Sanjeev Khudanpur, Anoop Sarkar, Kenji Yamada,
Alex Fraser, Shankar Kumar, Libin Shen, David Smith, Katherine Eng, Viren
Jain, Zhen Jin, and Dragomir Radev.
In Proceedings of the 2004 Meeting of the North American chapter of the
Association for Computational Linguistics (NAACL-04), Boston, 2004.
Loosely
Tree-Based Alignment for Machine Translation,
Daniel Gildea.
In Proceedings of the 41th Annual Conference of the Association for
Computational Linguistics (ACL-03), pages 80-87, Sapporo, Japan, 2003.
Identifying
Semantic Roles Using Combinatory Categorial Grammar,
Daniel Gildea and Julia Hockenmaier.
In 2003 Conference on Empirical Methods in Natural Language Processing
(EMNLP), pages 57-64, Sapporo, Japan, 2003.
An Algorithm for Word-level Alignment of Parallel Dependency Trees,
Yuan Ding, Daniel Gildea, and Martha Palmer.
In The 9th Machine Translation Summit of the International Association for
Machine Translation, New Orleans, 2003.
The Necessity of
Syntactic Parsing for Predicate Argument Recognition,
Daniel Gildea and Martha Palmer.
In Proceedings of the 40th Annual Conference of the Association for
Computational Linguistics (ACL-02), pages 239-246, Philadelphia, PA,
2002.
Probabilistic
Models of Verb-Argument Structure,
Daniel Gildea.
In Proceedings of the 19th International Conference on Computational
Linguistics (COLING-02), pages 308-314, Taipei, 2002.
Corpus
Variation and Parser Performance,
Daniel Gildea.
In 2001 Conference on Empirical Methods in Natural Language Processing
(EMNLP), Pittsburgh, PA, 2001.
Automatic
Labeling of Semantic Roles,
Daniel Gildea and Daniel Jurafsky.
In Proceedings of the 38th Annual Conference of the Association for
Computational Linguistics (ACL-00), pages 512-520, Hong Kong, October
2000.
Topic-Based
Language Models Using EM,
Daniel Gildea and Thomas Hofmann.
In Proceedings of the 6th European Conference on Speech Communication and
Technology (EUROSPEECH-99), pages 2167-2170, Budapest, 1999.
Forms of
English function words - Effects of disfluencies, turn position, age and
sex, and predictability,
Alan Bell, Daniel Jurafsky, Eric Fosler-Lussier, Cynthia Girand, and Daniel
Gildea.
In Proceedings of the International Congress of Phonetic Sciences
(ICPhS-99), pages 395-398, San Francisco, California, 1999.
A Dynamic Model of
Aspectual Composition,
Nancy Chang, Daniel Gildea, and Srini Narayanan.
In Proceedings of the 20th Annual Conference of the Cognitive Science
Society (COGSCI-98), pages 226-231, Madison, WI, 1998.
Applications of Technology in Providing Transit Information,
Daniel Gildea and Mikael Sheikh.
In Transportation Research Record 1521, pages 71-76, Washington, DC,
1996.
Automatic
Induction of Finite State Transducers for Simple Phonological Rules,
Daniel Gildea and Daniel Jurafsky.
In Proceedings of the 33rd Annual Conference of the Association for
Computational Linguistics (ACL-95), pages 9-15, Cambridge, MA, 1995.
Refereed Workshop Papers
Improved
Tree-to-string Transducer for Machine Translation,
Ding Liu and Daniel Gildea.
In ACL Workshop on Statistical Machine Translation (ACL08-SMT),
2008.
Factorization of Synchronous Context-Free Grammars in Linear Time,
Hao Zhang and Daniel Gildea.
In NAACL Workshop on Syntax and Structure in Statistical Translation
(SSST), 2007.
Syntactic Features for Evaluation of Machine Translation,
Ding Liu and Daniel Gildea.
In ACL 2005 Workshop on Intrinsic and Extrinsic Evaluation Measures for
Machine Translation and/or Summarization, 2005.
Machine Translation as Lexicalized Parsing with Hooks,
Liang Huang, Hao Zhang, and Daniel Gildea.
In International Workshop on Parsing Technologies (IWPT05), Vancouver,
BC, 2005.
Online
Statistics for a Unification-Based Dialogue Parser,
Micha Elsner, Mary Swift, James Allen, and Daniel Gildea.
In International Workshop on Parsing Technologies (IWPT05), Vancouver,
BC, 2005.
Invited Papers
Identifying Semantic Roles in
Text,
Daniel Gildea and Daniel Jurafsky.
In Seventeenth International Joint Conference on Artificial Intelligence
(IJCAI-01), Seattle, Washington, 2001.
Appears as chapter in Exploring Artificial Intelligence in the New
Millenium, Gerhard Lakemeyer and Bernhard Nebel, eds., Morgan Kaufmann,
2003.
Technical Reports
Syntax for Statistical Machine
Translation,
Franz Josef Och, Daniel Gildea, Sanjeev Khudanpur, Anoop Sarkar, Kenji Yamada,
Alex Fraser, Shankar Kumar, Libin Shen, David Smith, Katherine Eng, Viren
Jain, Zhen Jin, and Dragomir Radev.
Technical report, Center for Language and Speech Processing, Johns Hopkins
University, Baltimore, 2003.
Summer Workshop Final Report.
Natural Language Generation in the
Context of Machine Translation,
Jan Hajic, Martin Cmejrek, Bonnie Dorr, Yuan Ding, Jason Eisner, Daniel
Gildea, Terry Koo, Kristen Parton, Gerald Penn, Dragomir Radev, and Owen
Rambow.
Technical report, Center for Language and Speech Processing, Johns Hopkins
University, Baltimore, 2002.
Summer Workshop Final Report.
Topic-Based Novelty Detection,
James Allan, Hubert Jin, Martin Rajman, Charles Wayne, Daniel Gildea, Victor
Lavrenko, Rose Hoberman, and David Caputo.
Technical report, Center for Language and Speech Processing, Johns Hopkins
University, Baltimore, 1999.
Summer Workshop Final Report.
- Spring 2005, 2006, 2007
- Graduate Machine Learning,
University of Rochester.
- Fall 2006
- Graduate seminar on
Language, Parsing, and Complexity,
University of Rochester.
- Fall 2005, 2007
- Graduate
Statistical Speech and Language Processing,
University of Rochester.
- Fall 2004
- Undergraduate Design and Analysis of Efficient Algorithms,
University of Rochester.
- Spring 2004
- Graduate seminar on
Machine Translation,
University of Rochester.
- Fall 2002
- Cotaught graduate seminar on
Information Extraction,
University of Pennsylvania.
Graduated PhD students: Shan He (now at Google)
Current PhD students at Rochester: Hao Zhang, Ding Liu, Matt Post, Saurabh Deshpande, Shaojun Zhao, Tagyoung Chung.
PhD Thesis Committees at Rochester: Chengliang Zhang, Phil Michalak, Carlos Gomez, Fabrizio Morbini, Benjamin Van Durme.
Outside PhD Thesis Committess: Marta Alegre (Technical University of Catalonia, graduated August 2004),
Edward Loper (U Pennsylvania).
Undergraduate research advising at Rochester: Micha Elsner.
Semantics for Statistical Machine Translation,
NSF Faculty Early Career Development (CAREER) Award funded 2005-2010.
Probabilistic Tree Transducers for Machine
Translation and Natural Language Processing, NSF ITR grant funded 2004-2009,
Kevin Knight (USC/ISI, PI),
Daniel Marcu (USC/ISI, co-PI),
Daniel Gildea (U of Rochester, co-PI)
Domain-Independent Semantic Interpretation, NSF ITR grant funded 2003-2007,
Daniel Jurafsky (U of Colorado, PI),
Daniel Gildea (U of Rochester, co-PI),
Wayne Ward (U of Colorado, co-PI),
Martha Palmer (U of Pennsylvania, co-PI),
Charles Fillmore (UC Berkeley, co-PI).
Editorial Board, Computational Linguistics
Reviewer, Speech Communication, ACM Transactions on Speech and Language Processing, Journal of Artificial Intelligence Research.
Area Chair, Annual Meeting of the Association for Computational Linguistics (ACL 2008)
Local Arrangements Co-chair, Annual Meeting of the North American Chapter of the
Association for Computational Linguistics (NAACL 2007)
Co-organizer, Conference on Natural Language Learning (CoNLL 2005)
Panelist, Doctoral Consortium, American Assoc. for Aritificial Intelligence (AAAI 2005, 2008)
Reviewer, Conference on Natural Language Learning (CoNLL 2008)
Program Committee, Journal of Natural Language Engineering
special issue on Parallel Texts (2004)
Reviewer, Machine Learning Journal,
Special Issue on
Learning in Speech and Language Technologies (2004)
Reviewer, Journal of Artificial Intelligence Research (2004)
Area Chair, Conference on Empirical Methods in Natural Language Processing (EMNLP 2004)
Program Committee, Seventh International Workshop on Tree Adjoining Grammars and Related Formalisms (TAG+ 2004)
Reviewer, Advances in Neural Information Processing (NIPS 2004, 2005, 2006, 2007)
Reviewer, Annual Meeting of the North American Chapter of the
Association for Computational Linguistics (NAACL 2004, 2006)
Reviewer, International Joint Conference on Natural Language Processing
(IJCNLP 2004, 2007)
Reviewer, International Conference on on Computational Linguistics
(COLING 2004)
Program Committee, International Workshop on Scalable Natural Language Understanding (ScaNaLU 2004, 2006)
Reviewer, Annual Meeting of the Association for Computational Linguistics (ACL 2000, 2003)
Program Committee, Conference on Empirical Methods in Natural Language Processing (EMNLP 2002, 2005, 2006, 2007)
Reviewer, Third International Conference on Language Resources and Evaluation (LREC 2002)
Reviewer, Journal of Machine Learning Research
special issue on Machine Learning Approaches to Shallow Parsing (2001)
Reviewer, Applied Intelligence
special issue on Neural Networks and Machine Learning for Natural Language
Processing (2000)
Reviewer, International Colloquium on Grammatical Inference (ICGI 1998, 2000)
Member, Association for Computing Machinery, Association for Computational Linguistics.
NSF
Faculty Early Career Development (CAREER) Award, 2005-2010
IRCS postdoctoral fellowship, University of Pennsylvania, 2001-2003
National Defense Science and Engineering Graduate Fellowship, 1997-2000
Finalist, National Science Foundation Graduate Fellowship, 1997
California Microelectronics Graduate Fellowship, 1996-1997
Daniel Gildea
2008-07-01