We represent natural language semantics by combining logical and distributional information in probabilistic logic. We use Markov Logic Networks (MLN) for the RTE task, and Probabilistic Soft Logic (PSL) for the STS task. The system is evaluated on the SICK dataset. Our best system achieves 73% accuracy on the RTE task, and a Pearson's correlation of 0.71 on the STS task.

PDF

In The 8th Workshop on Semantic Evaluation (SemEval-2014), pp. 796--801, Dublin, Ireland, August 2014.

@inproceedings{beltagy:semeval14, title={UTexas: Natural Language Semantics using Distributional Semantics and Probabilistic Logic}, author={I. Beltagy and Stephen Roller and Gemma Boleda and and Katrin Erk and Raymond J. Mooney}, booktitle={The 8th Workshop on Semantic Evaluation (SemEval-2014)}, month={August}, address={Dublin, Ireland}, pages={796--801}, url="http://www.cs.utexas.edu/users/ai-labpub-view.php?PubID=127458", year={2014} }