Proceedings of the Sixth Joint Conference on Lexical and Computational Semantics (*SEM)

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

, , , and

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.


  • 812529 bytes

computational linguistics, learning, natural language processing, natural language processing, semantics

InProceedings

Association for Computational Linguistics

Downloads: 674 downloads

UMBC ebiquity