Expert profile: Marsal Gavalda

[ ID = 0262 ] Marsal Gavalda 
Name Gavalda, Marsal
Job Title Senior Research Scientist 
Organisation Interactive Systems 
Postal Code  
Country United States 
Email marsal_(on)_taronja.com [@ replaced for spam protection]
Organisation URL  
Personal URL  
Specialism Speechtechnology:
Artificial Neural Networks
Chinese NLP Processing
Computational Lexicography
Computational Linguistics
Computational Morphology
Developer Tools
Dynamic Lexicon Building
Hidden Markov Models
Human Voice Understanding
Information Services by Telephone using Speech Technologies
Language Learning
Language Modeling
Language Processing
Machine Learning Algorithms
Machine Translation
Multimodal Human-Machine Communication
Natural Language Semantics
Neural Networks
Oral Dialogue
Robust Parsing and Understanding
Robust Speech Recognition
Search Strategies
Shallow Parsing
Software Architecture for Language Engineering
Speech Applications
Speech Processing
Speech Recognition
Speech Technologies
Speech-to-Speech Translation
Spoken Dialogue and Robust Speech Understanding
Spoken Dialogue Systems
Spoken Language Resources and Evaluation
Spoken Translation
Spontaneous Speech
Statistical Language Modeling and Analysis
Universal Authoring
Web Applications
Word meaning 
PhotographDescription or CV
Description: PhD in Language and Information Technologies from Carnegie
   Mellon University. Interests include robust parsing, grammar
   acquisition, natural language understanding; conversational systems,
   machine translation; artificial intelligence, computer science,
   linguistics, cognitive science.

                               Marsal Gavalda

                           140 Hoyt St. Apt. 5-D

                             Stamford, CT 06905




   1996-2000: Ph.D. in Language and Information Technologies from the
   Language Technologies Institute, School of Computer Science, Carnegie
   Mellon University, Pittsburgh, Pennsylvania.

   Thesis: "Growing Semantic Grammars." Successfully demonstrated robust
   parsing of natural language and interactive grammar acquisition for
   the rapid deployment of conversational systems via the design and
   implementation of the GSG system. When GSG does not understand what
   the user says, it makes educated guesses, poses confirmation and
   clarification questions, and acquires the meaning of new words and
   constructions by formulating and generalizing rules and merging them
   with the existing grammar. GSG incorporates external knowledge sources
   (semantic grammar, part-of-speech tagger, syntactic grammar,
   end-application constraints), constructs internal knowledge sources
   (ontology, parsebank, hypotactical and paratactical models) and
   combines learning strategies (all-top parsing, anchor mother
   prediction, daughter argument selection, vertical and horizontal
   generalization) into a coherent, mixed-initiative conversation with
   the end-user, as an epiphenomenon of which the original semantic
   grammar, written in a standard formalism such as JSGF, is judiciously
   and seamlessly extended.

   1994-1996: Master of Science in Computational Linguistics from the
   Philosophy Department at Carnegie Mellon University.

   Courses: Natural Language Processing, Syntax, Semantics, Artificial
   Intelligence, Speech Recognition, Logic and Computability, etc.

   1993-1994: European Union Erasmus Scholarship at the Universitaet
   Karlsruhe, Karlsruhe, Germany.

   Courses: Machine Learning, Neural Networks, Knowledge Representation,
   Robotics, Philosophy and Computer Science Working Group, etc.

   1989-1994: Bachelor of Science in Computer Science at the Universitat
   Politecnica de Catalunya, Barcelona, Catalonia, Spain.

   Courses: Algebra, Analysis, Statistics, Physics, Operations Research,
   Computer Architecture, Computer Networks, Operating Systems,
   Programming Languages, Algorithms, Compiler Construction, Information
   Theory, Computer Graphics, Numerical Calculus, etc.

   1985-1989: Secondary School Degree with Honors, Institut de
   Batxillerat Maragall, Barcelona, Catalonia, Spain.

   1977-1985: Primary School Degree with Honors, Escola Orlandai,
   Barcelona, Catalonia, Spain.


   Chairman, Barcelona Language Technologies Advisory Committee since
   July 2000.

   Director, Course on Language Technologies at the Universitat
   Internacional Menendez Pelayo, Barcelona, Catalonia, Spain, July 2000.

   Member of the ACL-1999 Review Committee (thematic session on Robust
   Sentence Level Interpretation).

   Member of the ACL-1999 Student Session Program Committee.

   Teaching assistant at Carnegie Mellon for the graduate course "Speech
   Recognition and Understanding" for the Fall 1998 semester; subsequent
   yearly invitation to lecture on NLP.

   Member of the COLING/ACL-1999 Review Committee (multimodal NLP area).

   Advisor to senior honors thesis "Resolving Sentence Ambiguitiy through
   Speech Act Prediction" by Michele Lyn Banko, May 1998 - May 1999.

   Invited lecturer at the Hong Kong University of Science and
   Technology, Hong Kong, December 1997.

   Student member of the Language Technologies Institute Admissions
   Committee from January 1997 to January 1999.

   Co-organizer of the Language Technologies Institute Seminar Series
   from August 1996 to August 1998.

   Invited lecturer at the Universitat de Girona, Girona, Catalonia,
   Spain, June 1996.

   Work Experience

   Interactive Systems: Senior Research Scientist at Interactive Systems,
   Inc. in Pittsburgh, Pennsylvania,

   from October 1998 to present. Designed and developed SOUP, a
   stochastic, chart-based, top-down parser, especially engineered for
   real-time analysis of spoken language with very large, multi-domain
   semantic grammars. SOUP achieves flexibility by encoding context-free
   grammars written in a standard formalism, such as JSGF, as
   probabilistic recursive transition networks that can be dynamically
   modified, and robustness by allowing the skipping of input words at
   any position and producing ranked interpretations that may consist of
   multiple parse trees.

   Patent pending (filed January 2000): "Method and System for Robust
   Parsing of Natural Language."

   Microsoft: Software Design Engineer in the Natural Language Group,
   Microsoft Corporation in Redmond, Washington, from May to August, 1997
   (summer internship).

   Developed the language-identification algorithm that was shipped in
   Microsoft WORD-2000.


   Computer environments: UNIX (SUN-Solaris, HP-UX, DEC OSF/1, Linux);
   Windows-NT/2000; World Wide Web server administration.

   Computer languages: C/C++, Java, Python, Perl; VoiceXML, HTML, CGI,
   Tcl/Tk; Lisp, Prolog, Miranda, ML; LaTeX.

   Natural languages: Catalan (native), Spanish (native), English
   (near-native), German (near-native), Chinese (advanced), Japanese



   M. Gavalda. "Introduccio a les tecnologies de la llengua" in "Quark",
   19. Barcelona, Catalonia, Spain (to appear).

   M. Gavalda. "Growing Semantic Grammars." Ph.D. dissertation. Carnegie
   Mellon University. Pittsburgh, Pennsylvania. August 2000.

   M. Gavalda. "Epiphenomenal Grammar Acquisition with GSG" in
   "Proceedings of the Workshop on Conversational Systems of the 6th
   Conference on Applied Natural Language Processing and the 1st
   Conference of the North American Chapter of the Association for
   Computational Linguistics (ANLP/NAACL-2000)", Seattle, Washington, May

   M. Gavalda. "SOUP: A Parser for Real-world Spontaneous Speech" in
   "Proceedings of the 6th International Workshop on Parsing Technologies
   (IWPT-2000)", Trento, Italy, February 2000.

   L. Levin, A. Lavie, M. Woszczya, D. Gates, M. Gavalda, D. Koll and A.
   Waibel. "The JANUS-III Translation System: Speech-to-Speech
   Translation in Multiple Domains" in"Machine Translation," Kluwer
   Academic Publishers (to appear).

   W. Minker, M. Gavalda and A. Waibel. "Hidden Understanding Models for
   Machine Translation" in "European Speech Communication Association
   Tutorial and Research Workshop on Interactive Dialogue in Multi-Modal
   Systems (ESCA-1999)," Kloster Irsee, Germany, June 1999.

   W. Minker, M. Gavalda and A. Waibel. "Stochastically-Based Semantic
   Analysis for Machine Translation" in "Computer Speech and Language,"
   13(2), April 1999, pp. 177-194, Academic Press.

   M. Woszczyna, M. Broadhead, D. Gates, M. Gavalda, A. Lavie, L. Levin
   and A. Waibel. "A Modular Approach to Spoken Language Translation for
   Large Domain" in "Proceedings of the 3rd Conference of the Association
   for Machine Translation in the Americas (AMTA-1998)," Langhorne,
   Pennsylvania, October 1998.

   M. Gavalda. "Interactive Grammar Repair" in "Proceedings of the
   Workshop on Automated Acquisition of Syntax and Parsing of the 10th
   European Summer School in Logic, Language and Information
   (ESSLLI-1998)," Saarbruecken, Germany, August 1998.

   M. Gavalda and A. Waibel. "Growing Semantic Grammars" in "Proceedings
   of the 17th International Conference on Computational Linguistics and
   the 36th Annual Meeting of the Association for Computational
   Linguistics (COLING/ACL-1998)," Montreal, Quebec, Canada, August 1998.

   A. Lavie, A. Waibel, L. Levin, M. Finke, D. Gates, M. Gavalda, T.
   Zeppenfeld and P. Zhan. "JANUS-III: Speech-to-Speech Translation in
   Multiple Languages" in "Proceedings of the 22nd IEEE International
   Conference on Acoustics, Speech, and Signal Processing (ICASSP-1997),"
   Munich, Germany, April 1997.

   M. Gavalda, K. Zechner, G. Aist. "High Performance Segmentation of
   Spontaneous Speech Using Part of Speech and Trigger Word Information"
   in "Proceedings of the 5th Conference on Applied Natural Language
   Processing (ANLP-1997), Washington, D.C., April 1997.

   D. Gates, A. Lavie, L. Levin, A. Waibel, M. Gavalda, L. Mayfield, M.
   Woszczyna and P. Zhan. "End-to-End Evaluation in JANUS" in E. Maier,
   M. Mast and S. Luperfoy (eds.) "Dialogue Processing in Spoken Language
   Systems. Selected Papers. Lecture Notes in Computer Science/Lecture
   Notes in Artificial Intelligence," 1236; pp. 195-206. Berlin,
   Heidelberg, New York: Springer Verlag, 1997.

   P. Zhan, K. Ries, M. Gavalda, D. Gates, A. Lavie and A. Waibel.
   "JANUS-II: Towards Spontaneous Spanish Speech Recognition" in
   "Proceedings of the 4th International Conference on Spoken Language
   Processing (ICSLP-1996)," Philadelphia, Pennsylvania, October 1996.

   A. Lavie, A. Waibel, D. Gates, M. Gavalda, T. Zeppenfeld, P. Zhan and
   O. Glickman. "Translation of Conversational Speech with JANUS-II" in
   "Proceedings of ICSLP-1996."

   A. Lavie, L. Levin, Y. Qu, A. Waibel, D. Gates, M. Gavalda, L.
   Mayfield and M. Taboada. "Dialogue Processing in a Conversational
   Speech Translation System" in "Proceedings of ICSLP-1996."

   A. Lavie, D. Gates, M. Gavalda, L. Mayfield, A. Waibel and L. Levin.
   "Multi-lingual Translation of Spontaneously Spoken Language in a
   Limited Domain" in "Proceedings of the 16th International Conference
   on Computational Linguistics (COLING-1996)," Copenhagen, Denmark,
   August 1996.

   A. Waibel, M. Finke, D. Gates, M. Gavalda, T. Kemp, A. Lavie, L.
   Levin, M. Maier, L. Mayfield, A. McNair, I. Rogina, K. Shima, T.
   Sloboda, M. Woszczyna, T. Zeppenfeld and P. Zhan. "JANUS-II:
   Translation of Spontaneous Conversational Speech" in "Proceedings of
   the 21st IEEE International Conference on Acoustics, Speech, and
   Signal Processing (ICASSP-1996), Atlanta, Georgia, May 1996.

   L. Mayfield, M. Gavalda, Y-H. Seo, B. Suhm, W. Ward and A. Waibel.
   "Parsing Real Input in JANUS: a Concept-Based Approach" in
   "Proceedings of the 6th International Conference on Theoretical and
   Methodological Issues in Machine Translation (TMI-1995)," Leuven,
   Belgium, July 1995.

   L. Mayfield, M. Gavalda, W. Ward and A. Waibel. "Concept-Based Speech
   Translation" in "Proceedings of the 20th IEEE International Conference
   on Acoustics, Speech, and Signal Processing (ICASSP-1995)," Detroit,
   Michigan, May 1995.


   M. Gavalda. "El genoll del temps" in "Cavall Fort," 740, Barcelona,
   Catalonia, Spain, May 1993.

   M. Gavalda. "Diari-S" in "Mecanoscrit," Edicions Pleniluni, Barcelona,
   Catalonia, Spain, 1990.


   Professional: Robust parsing, grammar acquisition, natural language
   understanding; conversational systems, machine translation; artificial
   intelligence, computer science, linguistics, cognitive science.

   Personal: Long-distance motorcycling, camping; opera, literature,
   photography, Chinese calligraphy; basketball, table tennis.

Update your profile Last update: 2002-04-05 12:00:00   Visits since 28-08-2008: 4575


Browse and Search the Directories of Language and Speech Technology (LST) Experts and Organisations
The Directories
Some statistics
Browse in alphabetical order Browse in alphabetical order (in frame) Browse by country Browse by ID number Add your profile Select directory to search Search directories for keywords and phrases (use ~ for space within keys; most word-initial regular expressions can be used; no slashes or backslashes)
Directory of Experts in LST browse browse browse browse add expert

Directory of LST R&D Organisations browse browse browse browse add organisation

Directory of Call and Contact Centers, now including translation and localisation browse browse browse browse


[print/pda] [no frame] [navigation table] [navigation frame]     Page generated 17-01-2014 by Steven Krauwer Disclaimer / Contact ELSNET