Building accurate and efficient natural language processing (NLP) systems is an important and difficult problem. There has been increasing interest in automating this process. The lexicon, or the mapping from words to meanings, is one component that is typically difficult to update and that changes from one domain to the next. Therefore, automating the acquisition of the lexicon is an important task in automating the acquisition of NLP systems. This proposal describes a system, WOLFIE (WOrd Learning From Interpreted Examples), that learns a lexicon from input consisting of sentences paired with representations of their meanings. Preliminary experimental results show that this system can learn correct and useful mappings. The correctness is evaluated by comparing a known lexicon to one learned from the training input. The usefulness is evaluated by examining the effect of using the lexicon learned by WOLFIE to assist a parser acquisition system, where previously this lexicon had to be hand-built. Future work in the form of extensions to the algorithm, further evaluation, and possible applications is discussed.

PDF, PS

unpublished. Ph.D. proposal.

@unpublished{thompson:proposal96, title={Corpus-Based Lexical Acquisition For Semantic Parsing}, author={Cynthia Thompson}, month={February}, school={Department of Computer Sciences, University of Texas at Austin}, institution={Department of Computer Sciences, University of Texas at Austin}, pages={38 pages}, note={Ph.D. proposal}, url="http://www.cs.utexas.edu/users/ai-lab?thompson:proposal96", year={1996} }