Paper: Identifying semantic relations in a specialized corpus through distributional analysis of a cooccurrence tensor

ACL ID S14-1007
Title Identifying semantic relations in a specialized corpus through distributional analysis of a cooccurrence tensor
Venue Joint Conference on Lexical and Computational Semantics
Session
Year 2014
Authors

We describe a method of encoding cooc- currence information in a three-way tensor from which HAL-style word space mod- els can be derived. We use these models to identify semantic relations in a specialized corpus. Results suggest that the tensor- based methods we propose are more ro- bust than the basic HAL model in some respects.