An Evaluation of a Lexicographer's Workbench Incorporating Word Sense Disambiguation

NLPsystem developers and corpus lexicographers would both bene t from a tool for nding and organizing the distinctive patterns of use of words in texts. Such a tool would be an asset for both language research and lexicon development, particularly for lexicons for Machine Translation. We have developed the waspbench, a tool that (1) presents a \word sketch", a summary of the corpus evidence for a word, to the lexicographer (2) supports the lexicographer in analysing the word into its distinct meanings and (3) uses the lexicographer's analysis as the input to a state-of-the-art word sense disambiguation (WSD) algorithm, the output of which is a \word expert" for the word which can then disambiguate new instances of the word. In this paper we describe a set of evaluation experiments, designed to establish whether waspbench can be used to save time and improve performance in the development of a lexicon for Machine Translation or other NLP application. 1 Motivations On the ...

• Type: Conference
• Year: 2003
• Where: CICLING
• Authors: Adam Kilgarriff, Rob Koeling
• Keywords: CICLING 2003, Machine Translation, Natural Language Processing, Tool, Word Sense Disambiguation