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.
@article{arxiv.1706.09562,
title = {Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles},
author = {Francis Ferraro and Adam Poliak and Ryan Cotterell and Benjamin Van Durme},
journal= {arXiv preprint arXiv:1706.09562},
year = {2017}
}
Comments
Accepted at the Sixth Joint Conference on Lexical and Computational Semantics (*SEM). Association for Computational Linguistics, Vancouver, Canada. 2017