Paper: Using Minimal Recursion Semantics for Entailment Recognition

ACL ID E14-3009
Title Using Minimal Recursion Semantics for Entailment Recognition
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

This paper describes work on using Mini- mal Recursion Semantics (MRS) repre- sentations for the task of recognising tex- tual entailment. I use entailment data from a SemEval-2010 shared task to de- velop and evaluate an entailment recog- nition heuristic. I compare my results to the shared task winner, and discuss dif- ferences in approaches. Finally, I run my system with multiple MRS representations per sentence, and show that this improves the recognition results for positive entail- ment sentence pairs.