The Mikrokosmos Project at NMSU is the first, large-scale attempt at a knowledge-based machine translation system. We have successfully implemented the first and central stage of basic Semantic-Dependency-Structure building. This involved the creation of a large, language independent ontology which interacts with the Spanish semantic lexicon. The uK analyzer extracts semantic constraints from these two sources, analyzes them using a sophisticated ontological graph search function, and determines the combination of choices that yields the best overall score. Along the way, it utilizes the computational techniques described as dependency-directed processing, best-first processing, failure recovery and ambiguity resolution to ensure efficient and robust analysis.
In the coming year, uK will implement various microtheories which will build on the basic Semantic Dependency analysis. Included in this effort will be microtheories of ellipsis, metaphor, coreference and time and aspect. uK is also seeking to expand its language coverage. We hold great interest in the languages of South-East Asia, particularly Thai. For this reason we are especially grateful for the opportunity to present our work at this year's Symposium for Natural Language Processing in Bangkok.