Ezra Black

                  Tachnae Company, 527 Third Avenue,
                            Number 281,
                        New York, NY 10016 USA

      Email: takanoharian@yahoo.com               Phone/Fax: 1-718-549-2714
    

                           CURRICULUM VITAE

                      Professional Publications
     2002  E. Black, A. Finch. Beyond Tag Trigrams: New Local
           Features for Tagging, Proceedings, 3rd International Conference
           on Language Resources and Evaluation (LREC 2002). Las Palmas, Spain.
     2001  E. Black, A. Finch. Developing and Proving Effective Broad-Coverage
           Semantic-and-Syntactic Tagsets for Natural Language: The ATR
           Approach. Proceedings, ICCPOL 2001, Seoul.
     2001  A. Finch, E. Black. Using Compound Local Word-Tag Features in
           Tagging. Proceedings, ICCPOL 2001, Seoul.
     2000  R. Zhang, E. Black, A. Finch, Y. Sagisaka. A Parser-Aided
           Language Model With A Stack Decoder. Proceedings,
           6th International Conference on Spoken Language Processing
           (ICSLP 2000) . Beijing.
     1999  E. Black, A. Finch, R. Zhang. Applying Extrasentential Context
           To Maximum Entropy Based Tagging With A Large Semantic And
           Syntactic Tagset. Seventh Workshop on Very Large Corpora.
           Maryland, US.
     1999  R. Zhang, E. Black, A. Finch. Using Detailed Linguistic
           Structure In Language Modelling. Eurospeech 99. Budapest.
     1998  E. Black, A. Finch, H. Kashioka. Trigger-Pair Predictors
           in Parsing and Tagging. In Proceedings, ACL/COLING-98,
           Montreal.
     1998  E. Black, S. Eubank, H. Kashioka, J.Saia. Reinventing
           Part-of-Speech Tagging. Journal of Natural Language Processing
           (Japan). 5:1:3-23.
     1997  E. Black. Innovative Uses of Very Large Corpora. Invited
           Panelist. Fifth Workshop on Very Large Corpora. Beijing,
           Hong Kong.
     1997  E. Black, S. Eubank, H. Kashioka. Probabilistic Parsing of
           Unrestricted English Text, With A Highly-Detailed Grammar.
           Fifth Workshop on Very Large Corpora. Beijing, Hong Kong.
     1997  N. Campbell, T. Hebert, E. Black. 1997. Parsers, Prominence
           and Pauses. Proceedings, Eurospeech 97. Greece.
     1997  Evaluation of Broad--Coverage Natural Language
           Parsers. Chapter 13.4 of Survey of the State of the Art
           in Human Language Technology. R. Cole, J. Mariani et al.,
           Editors. Cambridge University Press.
     1997  E. Black, S. Eubank, H. Kashioka. 1997. The Non-Dictionary:
           Description and Evaluation of a Dictionaryless Semantic and
           Syntactic Tagger for Unrestricted English. In Proceedings,
           Third Annual Meeting, Association for Natural Language
           Processing, Kyoto.
     1996  E. Black, S. Eubank, H. Kashioka, R. Garside, G. Leech,
           D. Magerman. 1996. Beyond Skeleton Parsing: Producing a
           Comprehensive Large--Scale General--English Treebank With
           Full Grammatical Analysis. In Proceedings, COLING-96,
           Copenhagen.
     1994  H. Kashioka and E. Black.  Dealing With Low--Frequency
           Words In Mutual Information--Based Word Clustering.
           (In Japanese). In Proceedings, 49th Annual Meeting,
           Information Processing Society of Japan. September, 1994.
     1994  T. Tashiro, H. Kashioka, and E. Black. A Method of Restructuring
           Bracketed Corpora. (In Japanese). In Proceedings, 49th Annual
           Meeting, Information Processing Society of Japan. September, 1994.
     1994  A New Approach to Evaluating Broad-Coverage Parser/Grammars
           of English. International Conference on New Methods in Language
           Processing. Manchester, UK. September, 1994.
     1994  Evaluating Automatic Syntactic Analysis of English. Chapter 2,
           Part 3 of: Rationalist vs. Empiricist Approaches to NLP.
           S. Ananiadou and J. Tsujii, Eds. Mouton de Gruyter.
     1994  An Experiment in Customizing the Lancaster Treebank, Chapter 10
           of Oostdijk, N. and de Haan, P., Eds., Corpus-Based Research Into
           Language. Amstrdam: Rodopi Editions.
     1993  Parsing English By Computer: The State of the Art. Invited
           Presentation, Proceedings, International Symposium on Spoken
           Dialogue, Waseda University, Tokyo. (Also appears in: Proceedings,
           ATR International Workshop on Speech Translation. ATR Interpreting
           Telecommunications Research Laboratories, Kyoto)
     1993  Statistically-Driven Computer Grammars of English: The IBM/Lancaster
           Approach (Ed., with G. Leech and R. Garside, co-editors; and
           Roukos, Lafferty, Magerman co-authors.) Amsterdam: Rodopi Editions.
     1992  Towards History-Based Grammars: Using Richer Models for
           Probabilistic Parsing. DARPA Speech and Natural Language Workshop.
           (With Jelinek, Lafferty, Magerman, Mercer, Roukos.) (Also
           in: Proceedings, 31st Annual Meeting of the Association for
           Computational Linguistics, 1993.)
     1992  Decision Tree Models Applied to the Labelling of Text with
           Parts-of-Speech. DARPA Speech and Natural Language Workshop.
           (With Jelinek, Lafferty, Mercer, Roukos.)
     1992  Development, Evaluation and Results for a Broad-Coverage
           Probabilistic Grammar of English-Language Computer Manuals.
           Proceedings, 30th Annual Meeting of the Association for
           Computational Linguistics. (With Lafferty.)
     1992  Real Grammars for Real Tasks: Developing and Evaluating Large-Scale
           Grammars for Practical Applications. Proceedings, Fifth Annual CUNY
           Conference on Human Sentence Processing. CUNY Graduate Center,
           New York.
     1992  Statistical Modelling of Linguistic Information in Probabilistic
           Parsing. DARPA Speech and Natural Language Workshop. (With
           Magerman, Lafferty, Roukos.)
     1991  A Probabilistic Parsing Method for Sentence Disambiguation. Chapter
           10, Current Issues in Parsing Technology, M. Tomita (Ed.). Boston:
           Kluwer. (With: T. Fujisaki.)
     1991  Evaluating Syntactic Performance of Parser/Grammars of English.
           Proceedings, Natural language Processing Systems Workshop. UC
           Berkeley. (With: Abney, Flickinger, Gdaniec, Grishman, Harrison,
           Hindle, Ingria, Marcus, Santorini, Strzalkowski)
     1991  A Procedure for Quantitatively Comparing the Syntactic Coverage
           of English Grammars. DARPA Speech and Natural Language Workshop.
           (With: Abney, Flickinger, Gdaniec, Grishman, Harrison, Hindle,
           Ingria, Jelinek, Klavans, Liberman, Marcus, Roukos, Santorini,
          
Strzalkowski)
     1990  A Unification-Grammar-Based Approach to Statistical Modelling of
           Natural Language. Proceedings, IBM Natural Language ITL, Paris.
           (IBM Technical Report RC 15277)
     1989  A Probabilistic Parsing Method for Sentence Disambiguation.
           Proceedings, Carnegie Mellon University Parsing Workshop.
           (With T. Fujisaki, J. Cocke.)
     1988  An Experiment in Computational Determination of English Word
           Senses. IBM Journal of Research and Development. March 1988.
     1985  Theoretical Linguistics; Psycholinguistics; Artificial Intelligence.
           Three chapters of: J. Moyne, Language Understanding: Man or Machine.
           New York: Plenum.
     1983  A Stochastic Approach to Sentence Parsing. Presentation, Workshop on
           Semantics and Knowledge Representation, IBM Systems Research
           Institute, New York. (With T. Fujisaki)

 

 

                       Patents and Patent Disclosures

     2001  Trigger Pair Enhanced Natural Language Parsing Models. (Japanese
           Patent 3126952. With Finch, Kashioka.)
     2001  A Method For Morphological Analysis of English Via Computer.

           (Japanese Patent 3174526, with Eubank,Kashioka).

     2000  A Method For Parsing Japanese Text Using Decision-Tree Prediction
           (Japanese Patent 3035261, with Eubank, Kashioka).
     2000  A Method For Parsing English Text Using Decision-Tree Prediction
           (Japanese Patent 3027553, with Eubank, Kashioka).
     2000  A Method For Post-Tagging English Text With Part-Of-Speech Labels.
           (Japanese Patent 3100556, with Eubank, Kashioka).

     1999  Language Models for Speech Recognition Enhanced Via Complex
           Natural Language Triggers. (Japanese Patent 2000-250581 Pending.
           With Finch, Zhang, Sagisaka, Matsui.)
     1998  A Method For Efficient Construction of Detailed Natural Language
           Treebanks. (Japanese Patent 3050811. With Eubank, Kashioka.)
     1997  A Method For Format Conversion of Natural Language Treebanks.
           (Disclosure. With Eubank, Kashioka.)
     1992  Statistical Modelling of Linguistic Information in Probabilistic
           Parsing. (Disclosure. With Lafferty, Magerman, Roukos.)
     1991  Lexical Part-of-Speech Labelling Without A Lexicon For Use in
           Natural Language Parsing. (Disclosure. With Roukos, Mercer,
           Jelinek.)


                            Journal Editorship

     1990  North American Editor, Applied Computer Translation (Sigma, UK)


                              Education

     1987  Ph.D. (Linguistics), Graduate Center, City University of New York
     1973  MA    (French), Columbia University Teachers College
     1971  Certficat de francais, University of Geneva (Switzerland)
     1971  BA     (French), City College of New York
     1967  Science Diploma Bronx High School of Science, New York


                              Employment

     2001-present CEO, Tachnae Company, New York, NY, USA
     1993-2001    Manager, Statistical Parsing Group, Natural Language
                  Processing Department, Interpreting Telecommunications
                  Laboratory, ATR, Kyoto, Japan
     1987-1993    Research Staff Member, Continuous Speech Recognition Group,
                  Computer Science Department, IBM T.J. Watson Research Center,
                  Yorktown Heights, New York
     1983-1987    Consultant, Continuous Speech Recognition Group,
                  Computer Science Department, IBM T.J. Watson Research Center,
                  Yorktown Heights, New York

         
                           Other Employment

     1993-1994    Freelance translator (Spanish to English)
     1973-1985    Consultant and instructor, Testing and measurement (Harcourt
                  Brace Jovanovich, Arco Publishing Co., Simon and Schuster,
                  Academic Review, Inc., etc.)
     1981-1983    Adjunct Lecturer, Linguistics, Queens College, New York
     1980-1981    Adjunct Lecturer, Developmental Reading, Bronx Community
                  College, New York
     1976-1979    Trilingual curriculum writer/teacher-trainer, New York City
                  Board of Education
     1973-1976    Teacher of French, The Hoffman School, Riverdale, New York

                       Non-Academic Publications

     1984         Taking the SAT. New York: Arco.
     1983         Preparing for the Scholastic Aptitude Test (Home Computer
                  Version). New York: Harcourt Brace Jovanovich.
     1982         The Verbal and Analytic Sections of the GRE. New York:
                  Harcourt Brace Jovanovich.
     1976         The verbal and analytic sections of: Preparing for the
                  Law School Admissions Test. New York: Arco.


                               Languages

     French:   Professional-translator-grade fluency
     Spanish:  Professional-translator-grade fluency
     Japanese: Moderate fluency
     Polish:   Moderate fluency


                           References on request.