Semantic lexicon acquisition for learning natural language interfaces
Cynthia A. Thompson, Raymond J. Mooney · 1998
This paper describes a system, Wolfie (WOrd Learning From Interpreted Examples), that acquires a semantic lexicon from a corpus of sentences paired with representations of their meaning. The lexicon learned consists of words paired with meaning representations. Wolfie is part of an integrated system that learns to parse novel sentences into semantic representations, such as logical database queries. Experimental results are presented demonstrating Wolfie's ability to learn useful lexicons for a database interface in four different natural languages. The lexicons learned by Wolfie are compared to those acquired by a comparable system developed by Siskind (1996). 1 Introduction & Overview The application of learning methods to natural-language processing (NLP) is a growing area. Using machine learning to help automate the construction of NLP systems can eliminate much of the difficulty of building such systems by hand. The semantic lexicon, or the mapping from words to meanings, is one...