In recent years, there has been a flurry of research into empirical, c
orpus-based learning approaches to natural language processing (NLP).
Most empirical NLP work to date has focused on relatively low-level la
nguage processing such as part-of-speech lagging, text segmentation, a
nd syntactic parsing. The success of these approaches has stimulated r
esearch in using empirical learning techniques in other facets of NLP,
including semantic analysis-uncovering the meaning of an utterance. T
his article is an introduction to some of the emerging research in the
application of corpus-based learning techniques to problems in semant
ic interpretation. In particular, we focus on two important problems i
n semantic interpretation, namely, word-sense disambiguation and seman
tic parsing.