Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles
arXiv:1706.09562
Abstract
We study how different frame annotations complement one another when learning continuous lexical semantics. We learn the representations from a tensorized skip-gram model that consistently encodes syntactic-semantic content better, with multiple 10% gains over baselines.
Accepted at the Sixth Joint Conference on Lexical and Computational Semantics (*SEM). Association for Computational Linguistics, Vancouver, Canada. 2017