Grammatical Inference, variously refered to as automata induction, grammar induction, and automatic language acquisition, refers to the process of learning of grammars and languages from data. Machine learning of grammars 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.

Traditionally, grammatical inference has been studied by researchers in several research communities including: Information Theory, Formal Languages, Automata Theory, Language Acquisition, Computational Linguistics, Machine Learning, Pattern Recognition, Computational Learning Theory, Neural Networks, etc. Over the past few years, several conferences (e.g., the International Colloquium on Grammatical Inference, 1993, 1995, 1996, and 1998) and workshops have sought to bring together researchers working on grammatical inference in these areas. Some of this research is beginning to find significant applications in natural language interfaces to databases, bioinformatics, and related areas.

Against this background, to highlight the recent advances in this area, The Machine Learning Journal invites high quality original research contributions as well insightful survey and review articles for inclusion in this special issue on all aspects of machine learning of grammars including, but not limited to:

• 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), impossibility results, complexity results, characterizations of representational and search biases of grammar induction algorithms.
• Algorithms for induction of different classes of languages and automata: e.g., regular, context-free, and context-sensitive languages, interesting subsets of the above under additional syntactic constraints, tree and graph grammars, picture grammars, multi-dimensional grammars, attributed grammars, parameterized models, etc.
• Theoretical and experimental analysis of different approaches to grammar induction including artificial neural networks, statistical methods, symbolic methods, information-theoretic approaches, minimum description length, and complexity-theoretic approaches, heuristic methods, etc.
• Broader perspectives on grammar induction -- e.g., acquisition of grammar in conjunction with language semantics, semantic constraints on grammars, language acquisition by situated agents and robots, neural models of language, acquisition of language constructs that describe objects and events in space and time, developmental and evolutionary constraints on language acquisition, etc.
• Demonstrated or potential applications of grammar induction in natural language acquisition, bioinformatics (e.g., RNA and protein structure prediction, gene recognition) structural pattern recognition, information retrieval, information extraction, logic programming, database query processing and translation, text processing, adaptive intelligent agents, systems modelling and control, and other domains.

Instructions for Authors

The authors must follow the guidelines for preparation of manuscripts for submission to the Machine Learning Journal. These guidelines are available here

Please note that submissions should not exceed 12,000 words in length.

Authors should send 5 hardcopies of the manuscript to Karen Cullen (and one hardcopy each to Vasant Honavar and Colin de la Higuera). The author(s) should clearly indicate that the submission is for the special issue. The addresses for submission are:

Karen Cullen
101 Philip Drive
Assinippi Park
Norwell, MA 02061
U.S.A.
voice: 617-871-6300
fax: 617-871-6528
kcullen@wkap.com

Vasant Honavar
Department of Computer Science
226 Atanasoff Hall
Iowa State University
Ames, Iowa 50011-1040
U.S.A.
voice: 515-294-1098
fax: 515-294-0258
honavar@cs.iastate.edu

Colin de la Higuera
D'epartement de Mathematiques
Facult'e de Sciences et Techniques
23 rue du Docteur Paul Michelon
42023 Saint-Etienne Cedex 2
France
voice:(33) (0)4 77 48 15 83
fax: (33) (0)4 77 25 18 17
cdlh@univ-st-etienne.fr

Review Process

Each paper will be reviewed by at least 2 referees who will make their recommendations based on the originality, technical soundness, significance, and the clarity of presentation of each paper.

The reviews and final decisions will be coordinated by the special issue editors except in the case of submissions that are authored or coauthored by them or their collaborators (including recent graduate students) in which case the process will be handled by a member of the editorial board of the Machine Learning journal to avoid any potential conflict of interest.

Only manuscripts that are recommended for publication without any changes or with minor modifications will be accepted for publication in the special issue.

Publication

Authors of accepted papers will be invited to submit final drafts formatted preferably using LaTex style files provided by Kluwer. Electronic submission of the final drafts is highly recommended. Instructions for preparation of final drafts of manuscripts accepted for publication are available here

Relevant Deadlines

December 1, 1998 Deadline for receipt of manuscripts for review
April 1, 1999 Reviews and decisions mailed to authors
June 1, 1999 Final drafts of accepted manuscripts due