How to marry a star: Probabilistic constraints for meaning in context
- Katrin Erk (University of Texas at Austin)
- Aurelie Herbelot (University of Trento)
Abstract
We derive a notion of word meaning in context from an account of sentence comprehension, 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. We briefly sketch how to implement the system using a directed graphical model.
Keywords: meaning in context, generative models, lexical semantics, DRT
How to Cite:
Erk, K. & Herbelot, A., (2021) “How to marry a star: Probabilistic constraints for meaning in context”, Society for Computation in Linguistics 4(1), 451-453. doi: https://doi.org/10.7275/rcx1-aw95
Downloads:
Download PDF