Publications

Journal/Book || Information Extraction || Machine Learning || Machine Translation

Journal Papers/Book Chapters

Information Extraction for Enhanced Access to Disease Outbreak Reports
Ralph Grishman, Silja Huttunen, and Roman Yangarber
In Journal of Biomedical Informatics, 35(4) pp. 236-246, C. Friedman, ed. (2003)

Acquisition of Domain Knowledge
Roman Yangarber
In Extraction in the Web Era (M.T. Pazienza, ed.), Lecture Notes in Computer Science, Vol. 2700 Springer-Verlag Heidelberg, pp. 1-28 (2002) Rome, Italy [Invited paper]


Machine Learning

Bootstrapped Learning of Semantic Classes from Positive and Negative Examples    (ps.gz, pdf)
Winston Lin, Roman Yangarber and Ralph Grishman
In Proceedings of the 20th International Conference on Machine Learning: ICML 2003 Workshop on The Continuum from Labeled to Unlabeled Data in Machine Learning and Data Mining (2003) Washington, D.C.

Counter-Training in Discovery of Semantic Patterns    (ps.gz, pdf)
Roman Yangarber
In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics: ACL-2003 (2003) Sapporo, Japan

Unsupervised Learning of Generalized Names    (ps.gz, pdf)
Roman Yangarber, Winston Lin and Ralph Grishman
In Proceedings of the 19th International Conference on Computational Linguistics: COLING-2002 (2002) Taipei, Taiwan

Automatic Acquisition of Domain Knowledge for Information Extraction    (ps.gz)
Roman Yangarber, Ralph Grishman, Pasi Tapanainen and Silja Huttunen
In Proceedings of the 18th International Conference on Computational Linguistics: COLING-2000 (2000) Saarbrücken, Germany

Machine Learning of Extraction Patterns from Un-annotated Corpora    (pdf)
Roman Yangarber and Ralph Grishman
In Proceedings of the 14th European Conference on Artificial Intelligence: ECAI-2000 Workshop on Machine Learning for Information Extraction (2000) Berlin, Germany

Extraction Pattern Discovery through Corpus Analysis    (doc)
Roman Yangarber and Ralph Grishman
In Proceedings of the 2nd International Conference on Language Resources and Evaluation: LREC-2000 Workshop: Information Extraction meets Corpus Linguistics (2000) Athens, Greece

Unsupervised Discovery of Scenario-Level Patterns for Information Extraction    (ps.gz)
Roman Yangarber, Ralph Grishman, Pasi Tapanainen and Silja Huttunen
In Proceedings of Conference on Applied Natural Language Processing ANLP-NAACL 2000 pp. 282-289, (2000) Seattle, WA


Information Extraction

User-Oriented Evaluation in Information Extraction   
Roman Yangarber.  (2004)  
Workshop on User-Oriented Evaluation of Knowledge Discovery Systems, at the 4th International Conference on Language Resources and Evaluation (LREC 2004) Lisbon, Portugal

Complexity of Event Structure in IE Scenarios    (ps, pdf)
Silja Huttunen, Roman Yangarber, Ralph Grishman
In Proceedings of the 19th International Conference on Computational Linguistics: COLING-2002 (2002) Taipei, Taiwan

Diversity of Scenarios in Information Extraction    (ps)
Silja Huttunen, Roman Yangarber and Ralph Grishman
In Proceedings of the 3rd International Conference on Language Resources and Evaluation LREC-2002 (2002) Las Palmas de Gran Canaria, Spain

Real-Time Event Extraction for Infectious Disease Outbreaks    (pdf)
Ralph Grishman, Silja Huttunen and Roman Yangarber
In Proceedings of the 3rd Annual Human Language Technology Conference HLT-2002 (2002) San Diego, CA

Issues in Corpus-Trained Information Extraction    (doc)
Ralph Grishman and Roman Yangarber
In Proceedings of International Symposium: Toward the Realization of Spontaneous Speech Engineering, pp. 107-112, (2000) Tokyo, Japan

Transforming Examples into Patterns for Information Extraction    (ps.gz)
Roman Yangarber and Ralph Grishman
In Proceedings of TIPSTER Text Program Phase III, Morgan Kaufmann (1998) Baltimore, MD

Japanese IE System and Customization Tool    (ps.gz)
Chikashi Nobata, Satoshi Sekine and Roman Yangarber
In Proceedings of TIPSTER Text Program Phase III, Morgan Kaufmann (1998) Baltimore, MD

Using NOMLEX to Produce Nominalization Patterns for Information Extraction    (ps.gz)
Adam Meyers, Catherine Macleod, Roman Yangarber, Ralph Grishman, Leslie Barrett, Ruth Reeves
In Proceedings of COLING-ACL-98 Workshop on Computational Treatment of Nominals, (1998) Montreal, Canada

NYU: Description of the Proteus/PET System as Used for MUC-7 ST    (ps.gz)
Roman Yangarber and Ralph Grishman
In Proceedings of the 7th Message Understanding Conference: MUC-7 (1998) Washington, DC

Customization of Information Extraction Systems    (ps.gz)
Roman Yangarber and Ralph Grishman
In Proceedings of International Workshop on Lexically-Driven Information Extraction, invited talk, pp. 1-11, (1997) Frascati, Italy


Machine Translation

Deriving Transfer Rules from Dominance-Preserving Alignments    (ps.gz)
Adam Meyers, Roman Yangarber, Ralph Grishman, Catherine Macleod, Antonio Moreno-Sandoval
In Proceedings of COLING-ACL-98 (1998) Montreal, Canada

Alignment of Shared Forests for Bilingual Corpora    (ps.gz)
Adam Meyers, Roman Yangarber, Ralph Grishman
In Proceedings of the 16th International Conference on Computational Linguistics: COLING-96 pp. 460-465 (1996) Copenhagen, Denmark