Blasting Open a Choice Space: Learning Inflectional Morphology for NLP

This article discusses the various aspects of designing a system for eliciting knowledge about language from informants. For each design aspect, various options for implementation are presented, along with their pros, cons, and repercussions for other parts of the knowledge elicitation system. A running example throughout the text is taken from the paradigmatic morphology elicitation module of a system called Boas, which elicits knowledge to support a machine translation system. The main point of the article is an argument about the necessity to analyze the design choice space for complex natural language processing (NLP) systems early, comprehensively, and overtly.

[1]  Eric Nyberg,et al.  Tooling the lexicon acquisition process for large-scale KBMT , 1994, Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94.

[2]  Sergei Nirenburg,et al.  Project Boas: "A Linguist in the Box" as a multi-purpose language resource , 1998, LREC.

[3]  M. McShane,et al.  Bootstrapping Morphological Analyzers by Combining Human Elicitation and Machine Learning , 2001, Computational Linguistics.

[4]  Jeffrey M. Bradshaw,et al.  Expertise Transfer and Complex Problems: Using AQUINAS as a Knowledge-Acquisition Workbench for Knowledge-Based Systems , 1993, Int. J. Man Mach. Stud..

[5]  Sergei Nirenburg,et al.  Lexicons in the MikroKosmos Project , 1996 .

[6]  Yolanda Gil,et al.  An integrated environment for knowledge acquisition , 2001, IUI '01.

[7]  G. Lakoff.  Women, fire, and dangerous things : what categories reveal about the mind , 1989 .

[8]  Lawrence M. Fagan,et al.  Use of a Domain Model to Drive an Interactive Knowledge-Editing Tool , 1987, Int. J. Man Mach. Stud..

[9]  Peter Brusilovsky,et al.  Adaptive educational systems on the World Wide Web , 1998 .

[10]  Sergei Nirenburg,et al.  Choices for Lexical Semantics , 2001, Comput. Intell..

[11]  Alfred Kobsa,et al.  Generic User Modeling Systems , 2001, User Modeling and User-Adapted Interaction.

[12]  G. Lakoff,et al.  Women, Fire, and Dangerous Things: What Categories Reveal about the Mind , 1988 .

[13]  Larry J. Eshelman,et al.  MOLE: A Tenacious Knowledge-Acquisition Tool , 1987, Int. J. Man Mach. Stud..

[14]  Sergei Nirenburg,et al.  The Subworld Concept Lexicon and the Lexicon Management System , 1987, Comput. Linguistics.

[15]  Sergei Nirenburg,et al.  Parameterizing and Eliciting Text Elements across Languages for Use in Natural Language Processing Systems , 2004, Machine Translation.

[16]  Marjorie McShane.  Redefining "Paradigm" for Computer-Aided Language Instruction , 2003 .

[17]  Sergei Nirenburg,et al.  The analysis lexicon and the lexicon management system , 2005, Computers and translation.

[18]  Enrico Motta,et al.  A Methodology and Tool for Knowledge Acquisition in Keats-2 , 1989 .

[19]  Brian R. Gaines,et al.  Eliciting Knowledge and Transferring It Effectively to a Knowledge-Based System , 1993, IEEE Trans. Knowl. Data Eng..

[20]  Marcelo Tallis.  A Script-Based Approach to Modifying Knowledge-Based Systems , 1998, AAAI/IAAI.

[21]  Sergei Nirenburg,et al.  Embedding Knowledge Elicitation and MT Systems within a Single Architecture , 2005, Machine Translation.

[22]  Alfred Kobsa,et al.  Towards a user-adapted information environment on the Web , 1998 .

[23]  Nigel G. Ward.  Machine Translation: Past, Present, Future , 2001 .

[24]  Enrico Motta,et al.  A Methodology and Tool for Knowledge Acquisition , 1989 .