Search Results for author:
Found 3 papers, 2 papers with code
Semantic Loss Functions for Neuro-Symbolic Structured Prediction
We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training by minimizing the network's violation of such dependencies, steering the network towards predicting distributions satisfying the underlying structure.
Efficient Generation of Structured Objects with Constrained Adversarial Networks
Generative Adversarial Networks (GANs) struggle to generate structured objects like molecules and game maps.
Concept Tagging for Natural Language Understanding: Two Decadelong Algorithm Development
The third contribution is the release of a repository of the algorithms, datasets and recipes for NLU evaluation.
Natural Language Understanding
Vocal Bursts Valence Prediction
