Paper: Montague Meets Markov: Deep Semantics with Probabilistic Logical Form

ACL ID S13-1002
Title Montague Meets Markov: Deep Semantics with Probabilistic Logical Form
Venue Joint Conference on Lexical and Computational Semantics
Session
Year 2013
Authors

We combine logical and distributional rep- resentations of natural language meaning by transforming distributional similarity judg- ments into weighted inference rules using Markov Logic Networks (MLNs). We show that this framework supports both judg- ing sentence similarity and recognizing tex- tual entailment by appropriately adapting the MLN implementation of logical connectives. We also show that distributional phrase simi- larity, used as textual inference rules created on the fly, improves its performance.