Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles

2017-06-29SEMEVAL 2017Code Available0· sign in to hype

Francis Ferraro, Adam Poliak, Ryan Cotterell, Benjamin Van Durme

Code Available — Be the first to reproduce this paper.

Code

github.com/fmof/tensor-factorization
OfficialIn papernone★ 0

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.

Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles

Code

Abstract

Reproductions