23 citations · 23 across the 1 of their papers we have counts for
5 papers
Optimal Subarchitecture Extraction For BERT
Adrian de Wynter, Daniel J. Perry
We extract an optimal subset of architectural parameters for the BERT architecture from Devlin et al. (2018) by applying recent breakthroughs in algorithms for neural architecture…
Mischief: A Simple Black-Box Attack Against Transformer Architectures
Adrian de Wynter
We introduce Mischief, a simple and lightweight method to produce a class of human-readable, realistic adversarial examples for language models. We perform exhaustive experimentati…
An Approximation Algorithm for Optimal Subarchitecture Extraction
Adrian de Wynter
We consider the problem of finding the set of architectural parameters for a chosen deep neural network which is optimal under three metrics: parameter size, inference speed, and e…
On the Bounds of Function Approximations
Adrian de Wynter
Within machine learning, the subfield of Neural Architecture Search (NAS) has recently garnered research attention due to its ability to improve upon human-designed models. However…
Leveraging External Knowledge for Out-Of-Vocabulary Entity Labeling
Adrian de Wynter, Lambert Mathias
Dealing with previously unseen slots is a challenging problem in a real-world multi-domain dialogue state tracking task. Other approaches rely on predefined mappings to generate ca…