This talk will describe approaches to sense disambiguation in natural language parsing, machine translation and automatic (multilingual) indexing developed over many years of research and systems development at the University of Saarbruecken and discuss future directions.
The four approaches discussed differ with respect to the kind of ambiguity and the criteria for disambiguation. The first approach uses morphological and simple syntactic criteria and deals with tagging. The second approach is based on the notion of sublanguages in different domains and makes use of lexical criteria and a whole complex of criteria contained in the sublanguage notion. The third approach makes use of semantic relations and moves towards a semantic interlingua. The fourth approach, which will be the focus of the talk, goes beyond the sentence level and introduces an idea to employ thesaurus relations for lexical disambiguation.
For the colloquium series schedule, see the UMD Computational Linguistics Colloquium Series web page at http://umiacs.umd.edu/~resnik/cl_colloquium/. If you are interested in meeting with the speaker, please contact Mari Broman Olsen (molsen@umiacs.umd.edu) or Philip Resnik (resnik@umiacs.umd.edu).