Probabilistic Soft Logic (PSL) is a recently developed framework for probabilistic logic. We use PSL to combine logical and distributional representations of natural-language meaning, where distributional information is represented in the form of weighted inference rules. We apply this framework to the task of Semantic Textual Similarity (STS) (i.e. judging the semantic similarity of natural-language sentences), and show that PSL gives improved results compared to a previous approach based on Markov Logic Networks (MLNs) and a purely distributional approach.

PDF

In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL-14), pp. 1210--1219, Baltimore, MD 2014.

@inproceedings{beltagy:acl14, title={Probabilistic Soft Logic for Semantic Textual Similarity}, author={I. Beltagy and Katrin Erk and Raymond J. Mooney}, booktitle={Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL-14)}, address={Baltimore, MD}, pages={1210--1219}, url="http://www.cs.utexas.edu/users/ai-labpub-view.php?PubID=127438", year={2014} }

Poster