research
∙
10/21/2022
Just Mix Once: Worst-group Generalization by Group Interpolation
Advances in deep learning theory have revealed how average generalizatio...
share
research
∙
09/27/2021
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations
In NLP, a large volume of tasks involve pairwise comparison between two ...
research
∙
04/30/2020
Preventing Posterior Collapse with Levenshtein Variational Autoencoder
Variational autoencoders (VAEs) are a standard framework for inducing la...
research
∙
10/11/2019
The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
Since first introduced, computer simulation has been an increasingly imp...
research
∙
04/21/2019
Obfuscation for Privacy-preserving Syntactic Parsing
The goal of homomorphic encryption is to encrypt data such that another ...
research
∙
02/25/2019
Cooperative Learning of Disjoint Syntax and Semantics
There has been considerable attention devoted to models that learn to jo...
research
∙
11/29/2017
Embedding Words as Distributions with a Bayesian Skip-gram Model
We introduce a method for embedding words as probability densities in a ...
research
∙
05/31/2017