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

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


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.
Anthology ID:
S17-1011
Volume:
Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)
Month:
August
Year:
2017
Address:
Vancouver, Canada
Venues:
SemEval | *SEM
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
97–103
Language:
URL:
https://aclanthology.org/S17-1011
DOI:
10.18653/v1/S17-1011
Bibkey:
Cite (ACL):
Francis Ferraro, Adam Poliak, Ryan Cotterell, and Benjamin Van Durme. 2017. Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles. In Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017), pages 97–103, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles (Ferraro et al., SemEval-*SEM 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/S17-1011.pdf
Code
 fmof/tensor-factorization
Data
FrameNet