We combine logical and distributional representations of natural language meaning by transforming distributional similarity judgments into weighted inference rules using Markov Logic Networks (MLNs). We show that this framework supports both judging sentence similarity and recognizing textual entailment by appropriately adapting the MLN implementation of logical connectives. We also show that distributional phrase similarity, used as textual inference rules created on the fly, improves its performance.

PDF

Proceedings of the Second Joint Conference on Lexical and Computational Semantics (*Sem-2013) (2013), pp. 11--21.

@article{beltagy:starsem13, title={Montague Meets Markov: Deep Semantics with Probabilistic Logical Form}, author={I. Beltagy and Cuong Chau and Gemma Boleda and Dan Garrette and Katrin Erk and Raymond Mooney}, booktitle={Proceedings of the Second Joint Conference on Lexical and Computational Semantics (*Sem-2013)}, month={June}, address={Atlanta, GA}, pages={11--21}, url="http://www.cs.utexas.edu/users/ai-lab?beltagy:starsem13", year={2013} }

Slides (PPT)