We describe a statistical technique for assigning senses to words. An instance of a word is assigned a sense by asking a question about the context in which the word appears. The question is constructed to have high mutual information with the translation of that instance in another lan- guage. When we incorporated this method of assigning senses into our statistical machine translation system, the error rate of the system decreased by thirteen percent.

The Knowledge-Based Machine Translation paradigm requires a comprehensive analysis of input texts into an unambiguous machine-tractable representation of the propositional and meta-propositional meaning of that text, for which we use a particular framework referred to as ontological semantics. The work presented here begins with a definition of a representation language for lexical semantic specification (and syntax/semantics interface) to support such an analysis, as well as a generalized algorithm for building the meaning representation from these lexical semantic specifications, utilizing the ontology and a syntactic parse as knowledge sources. The core of the algorithm is an algorithm for semantic constraint satisfaction and relaxation, involving finding the best path over the ontology between a candidate filler of a relation and semantic constraints on that relation. The ontology is viewed as a multi-dimensional graph, with distinct topologies in each dimension reflecting specific semantic relations between nodes (representing concepts) , where weights or arc distance reflects strength of semantic relatedness in context (where the path-so-far context is maintained in a state transition table).

This paper uses three of these as a springboard (or better soapbox) for presenting my views on the SapirWhorl hypothesis (that is, the various detenninisfic positions on perception, cognition, and language structure). It is hoped that this such expression will be preaching to the choir, though it is possible that it will not be. Upon the expression of those views, however, I am more at liberty to show how, on the one hand, cultural knowledge helps solve lexical problems, and on the other, how useful lexical organizations are as expressions of world knowledge because they can be exploited efficiently