Automata Induction, Grammatical Inference, and Language Acquisition
The Fourteenth International Conference on Machine Learning (ICML-97)
July 12, 1997, Nashville, Tennessee
Updated Schedule, On Line Proceedings, etc. can be found here
The Automata Induction, Grammatical Inference, and Language Acquisition
Workshop will be held on Saturday, July 12, 1997 during the Fourteenth
International Conference on Machine Learning (ICML-97) which will be
co-located with the Tenth Annual Conference on Computational Learning Theory
(COLT-97) at Nashville, Tennessee from July 8 through July 12, 1997.
Additional information on ICML-97 and COLT-97 can be found
Machine learning of grammars, variously referred to as automata induction,
grammatical inference, grammar induction, and automatic language acquisition,
finds a variety of applications in syntactic pattern recognition,
adaptive intelligent agents, diagnosis, computational biology,
systems modelling, prediction, natural language acquisition,
data mining and knowledge discovery.
The workshop seeks to bring together researchers working on
different aspects of machine learning of grammars in a number
of different (and until now, relatively isolated) areas including
neural networks, pattern recognition, computational linguistics,
computational learning theory, automata theory, and language acquisition
for fruitful exchange of the relevant recent research results.
The workshop will consist of 6 invited talks offering different
perspectives on machine learning of grammars, interspersed with
short (10--15 minutes) presentations of accepted papers. The workshop
schedule will allow ample time for informal discussion.
Topics of interest
- Different models of grammar induction:
e.g., learning from examples,
learning using examples and queries,
incremental versus non-incremental learning,
distribution-free models of learning,
learning under various distributional assumptions
(e.g., simple distributions).
Theoretical results in grammar induction:
e.g., impossibility results,
characterizations of representational and search
biases of grammar induction algorithms.
Algorithms for induction of different classes of languages and
interesting subsets of the above under additional
syntactic constraints, tree and graph grammars,
picture grammars, multi-dimensional grammars,
attributed grammars, etc.
Empirical comparison of different approaches to grammar induction.
Demonstrated or potential applications of grammar induction in
natural language acquisition,
structural pattern recognition,
adaptive intelligent agents,
and other domains.
Workshop proceedings will be published in electronic form on the world-wide
web. Authors of a selected subset of accepted workshop papers might also be
invited to submit revised and expanded versions of their papers for possible
publication in a special issue of a journal or an edited collection of papers
to be published after the conference.
Dr. Pat Langley, Stanford University and Daimler-Benz Research and Technology Center, Palo Alto, California.
Dr. Laurent Miclet, IRISIA-ENSSAT, Lannion, France.
Dr. Michael Kearns, AT&T Research. Murray Hill, New Jersey.
Dr. Jordan Pollack, Computer Science Department, Center for Complex Systems, Brandeis University,
Dr. Michael Brent, Departments of Cognitive Science and Computer Science, Johns Hopkins University, Baltimore, Maryland.
Dr. Kevin Lang, NEC Research Institute, Princeton, New Jersey.
List of Accepted Papers
- Concept Learning with Bounded Data Mining, by J. Case (University of Delaware, USA), S. Jain (National University of Singapore, Singapore), S. Lange (HTWK Leipzig, Germany) and T. Zeugmann (Kyushu University, Japan).
- Regular Inference as a Graph Coloring Problem, by F. Coste and J. Nicolas (IRISA-Rennes, France).
- A study of Grammatical Inference Algorithms in Automatic Music Composition and Musical Styles Recognition, by P. Cruz and E. Vidal (Universidad Politécnica de Valencia, Spain).
- Using Grammatical Inference to Improve Precision in Information Extraction, by D. Freitag (Carnegie Mellon University, USA).
- Evolving Stochastic Context-Free Grammars from Examples Using a Minimum Description Length Principle, by B. Keller and R. Lutz (University of Sussex, United Kingdom).
- A Recursive GSA Acquisition Algorithm for Image Compression, by B. Litow and O. de Vel (James Cook University, Australia).
- Efficient Search Techniques for the Inference of Minimum Sized Finite State Machines, by A. Oliveira and J. Silva (IST-INESC, Portugal).
- Learning DFA from Simple Examples, by R. Parekh and V. Honavar (Iowa State University, USA).
- The sk-strings method for inferring PFSA, by A. Raman and J. Patrick (Massey University, New Zealand).
- Fitness Landscapes in Evolutionary Automata Induction, by V. Slavov (New Bulgarian University, Bulgaria) and N. Nikolaev (American University, Bulgaria).
- Learning to Parse Natural Language Database Queries into Logical Form, by C. Thompson, R. Mooney and L. Tang (University of Texas, USA).
- Inductive Learning of Abstract Role Values Derived from a Constraint Dependency Grammar, by C. White. M. Harper, T. Lane and R. Helzerman (Purdue University, USA).
Organizing and scientific committee
Dr. Vasant Honavar
Department of Computer Science
226 Atanasoff Hall
Iowa State University
Ames, IA 50011
Dr. Pierre Dupont
Department of Computer Science
Carnegie Mellon University
5000 Forbes Ave
Pittsburgh, PA 15213
Dr. Lee Giles
NEC Research Institute
4 Independence Way
Princeton, NJ 08540