A Method for Automatically Building and Evaluating Dictionary Resources
Smaranda Muresan (Department of Computer Science, Columbia University, 1214 Amsterdam Av., Mail code 0401 New York, NY 10027 USA )
Judith Klavans (Center for Research on Information Access, Columbia University)
WO3: Acquisition Of Lexical Information
This paper describes a method toward automatically building dictionaries from text. We present DEFINDER, a rule-based system for extraction of definitions from on-line consumer-oriented medical articles. We provide an extensive evaluation on three dimensions: i) performance of the definition extraction technique in terms of precision and recall, ii) quality of the built dictionary as judged both by specialists and lay users, iii) coverage of existing on-line dictionaries. The corpus we used for the study is publicly available. A major contribution of the paper is the range of quantitative and qualitative evaluation methods.
Automatic dictionary construction, Quantitative evaluation, User-Based qualitative evaluation, Text mining, Consumer-Oriented medical corpus