54 citations · 108 across the 8 of their papers we have counts for
8 papers
Just Mix Once: Worst-group Generalization by Group Interpolation
Giorgio Giannone, Serhii Havrylov, Jordan Massiah +2
Advances in deep learning theory have revealed how average generalization relies on superficial patterns in data. The consequences are brittle models with poor performance with shi…
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations
Fangyu Liu, Yunlong Jiao, Jordan Massiah +2
In NLP, a large volume of tasks involve pairwise comparison between two sequences (e.g. sentence similarity and paraphrase identification). Predominantly, two formulations are used…
Preventing Posterior Collapse with Levenshtein Variational Autoencoder
Serhii Havrylov, Ivan Titov
Variational autoencoders (VAEs) are a standard framework for inducing latent variable models that have been shown effective in learning text representations as well as in text gene…
The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
Shangmin Guo, Yi Ren, Serhii Havrylov +3
Since first introduced, computer simulation has been an increasingly important tool in evolutionary linguistics. Recently, with the development of deep learning techniques, researc…
Obfuscation for Privacy-preserving Syntactic Parsing
Zhifeng Hu, Serhii Havrylov, Ivan Titov +1
The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce a…
Cooperative Learning of Disjoint Syntax and Semantics
Serhii Havrylov, Germán Kruszewski, Armand Joulin
There has been considerable attention devoted to models that learn to jointly infer an expression's syntactic structure and its semantics. Yet, \citet{NangiaB18} has recently shown…
Embedding Words as Distributions with a Bayesian Skip-gram Model
Arthur Bražinskas, Serhii Havrylov, Ivan Titov
We introduce a method for embedding words as probability densities in a low-dimensional space. Rather than assuming that a word embedding is fixed across the entire text collection…
Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
Serhii Havrylov, Ivan Titov
Learning to communicate through interaction, rather than relying on explicit supervision, is often considered a prerequisite for developing a general AI. We study a setting where t…