An Empirical Evaluation of a System for Text Knowledge Acquisition

We introduce a formal model and a corresponding system architecture for the acquisition of new concepts from real-world natural language texts. Our approach is centered around the linguistic and conceptual “quality” of various forms of evidence underlying the generation and refinement of concept hypotheses. Based on a terminological (meta)reasoning platform, hypotheses are continuously annotated by a stream of linguistic and conceptual evidence, preferentially ranked and, finally, selected according to their overall credibility. We discuss the results of an empirical evaluation study, concentrating on the system's learning rate and learning accuracy.

[1]  Brian R. Gaines,et al.  KITTEN: Knowledge Initiation and Transfer Tools for Experts and Novices , 1987, Int. J. Man Mach. Stud..

[2]  Fernando Gomez,et al.  The recognition and classification of concepts in understanding scientific texts , 1989, J. Exp. Theor. Artif. Intell..

[3]  Peter M. Wiemer-Hastings,et al.  Implications of an automatic lexical acquisition system , 1995, Learning for Natural Language Processing.

[4]  Udo Hahn,et al.  Terminological Meta-Reasoning by Reification and Multiple Contexts , 1995, EPIA.

[5]  Udo Hahn,et al.  Concurrent, object-oriented natural language parsing: the ParseTalk model , 1994, Int. J. Hum. Comput. Stud..

[6]  Udo Hahn,et al.  A Quality-Based Terminological Reasoning Model for Text Knowledge Acquisition , 1996, EKAW.

[7]  Raymond J. Mooney.  Integrated Learning of Words and Their Underlying Concepts , 1987 .

[8]  Douglas E. Appelt,et al.  FASTUS: A Finite-state Processor for Information Extraction from Real-world Text , 1993, IJCAI.

[9]  James J. Cimino,et al.  Review: Beyond the Superhighway: Exploiting the Internet with Medical Informatics , 1997, J. Am. Medical Informatics Assoc..

[10]  Ritu Agarwal,et al.  Knowledge extraction using content analysis , 1991 .

[11]  Bernard Moulin,et al.  Designing deontic knowledge bases from regulation texts , 1990, Knowl. Based Syst..

[12]  U Hahn,et al.  Automatic knowledge acquisition from medical texts. , 1996, Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium.

[13]  Udo Hahn,et al.  A Terminological Qualification Calculus for Preferential Reasoning under Uncertainty , 1996, KI.

[14]  Stan Szpakowicz,et al.  Semi-Automatic Acquisition of Conceptual Structure from Technical Texts , 1990, Int. J. Man Mach. Stud..

[15]  Udo Hahn,et al.  Learning from texts - a terminological metareasoning perspective , 1995, Learning for Natural Language Processing.

[16]  Franz Schmalhofer,et al.  Case-oriented knowledge acquisition from texts , 1990 .

[17]  Ulrich Reimer.  Automatic Acquisition of Terminological Knowledge from Texts , 1990, ECAI.

[18]  P. Schönemann.  On artificial intelligence , 1985, Behavioral and Brain Sciences.

[19]  David Fisher,et al.  CRYSTAL: Inducing a Conceptual Dictionary , 1995, IJCAI.

[20]  Brian R. Gaines,et al.  Current Trends in Knowledge Acquisition , 1990 .

[21]  Stan Matwin,et al.  A Logic-Based Knowledge Source System for Natural Language Document , 1985, Data Knowl. Eng..

[22]  Inger Lytje.  Knowledge Acquisition from Text , 1994 .

[23]  Lisa F. Rau,et al.  Information extraction and text summarization using linguistic knowledge acquisition , 1989, Inf. Process. Manag..

[24]  R. M. Kaplan,et al.  Knowledge-based acquisition of causal relationships in text , 1991 .

[25]  Ellen Riloff,et al.  Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing , 1996, Lecture Notes in Computer Science.

[26]  Bernhard Nebel,et al.  Reasoning and Revision in Hybrid Representation Systems , 1990, Lecture Notes in Computer Science.

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