Artyom Gadetsky

Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces

2021 · arXiv (Cornell University)

Structured latent variables allow incorporating meaningful prior knowledge into deep learning models. However, learning with such variables remains challenging because of their discrete nature. Nowadays, the standard learning approach is to define a latent variable …

Conditional Generators of Words Definitions

2018

We explore recently introduced definition modeling technique that provided the tool for evaluation of different distributed vector representations of words through modeling dictionary definitions of words. In this work, we study the problem of word …