How to marry a star: probabilistic constraints for meaning in context

In this paper, we derive a notion of word meaning in context from Fillmore's 'semantics of understanding', in which a listener draws on their knowledge of both language and the world to 'envision' the situation described in an utterance. We characterize utterance understanding as a combination of cognitive semantics and Discourse Representation Theory, formalized as a situation description system:a probabilistic model which takes utterance understanding to be the mental process of describing one or more situations that would account for an observed utterance. Our model captures the interplay of local and global contexts and their joint influence upon the lexical representation of sentence constituents. We implement the system using a directed graphical model, and apply it to examples containing various contextualization phenomena.