Paper: haLF: Comparing a Pure CDSM Approach with a Standard Machine Learning System for RTE

ACL ID S14-2049
Title haLF: Comparing a Pure CDSM Approach with a Standard Machine Learning System for RTE
Venue Joint Conference on Lexical and Computational Semantics
Session
Year 2014
Authors

In this paper, we describe our sub- mission to the Shared Task #1. We tried to follow the underlying idea of the task, that is, evaluating the gap of full-fledged recognizing textual en- tailment systems with respect to com- positional distributional semantic mod- els (CDSMs) applied to this task. We thus submitted two runs: 1) a sys- tem obtained with a machine learning approach based on the feature spaces of rules with variables and 2) a sys- tem completely based on a CDSM that mixes structural and syntactic infor- mation by using distributed tree ker- nels. Our analysis shows that, under the same conditions, the fully CDSM system is still far from being competi- tive with more complex methods.