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

arXiv: https://arxiv.org/abs/1706.09562 · HTML: https://mlsanity.com/paper/1706.09562/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2017.

## Built on by (most cited first, 1 of 1)

- [Semantically-informed Hierarchical Event Modeling](https://mlsanity.com/paper/2212.10547/) (2022)

## Abstract (arXiv)

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.
