155 citations · 272 across the 4 of their papers we have counts for
6 papers
Multimodal datasets: misogyny, pornography, and malignant stereotypes
Abeba Birhane, Vinay Uday Prabhu, Emmanuel Kahembwe
We have now entered the era of trillion parameter machine learning models trained on billion-sized datasets scraped from the internet. The rise of these gargantuan datasets has giv…
Lower Dimensional Kernels for Video Discriminators
Emmanuel Kahembwe, Subramanian Ramamoorthy
This work presents an analysis of the discriminators used in Generative Adversarial Networks (GANs) for Video. We show that unconstrained video discriminator architectures induce a…
Dynamic Evaluation of Transformer Language Models
Ben Krause, Emmanuel Kahembwe, Iain Murray +1
This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation. Transformers use stacked layers…
Talking to myself: self-dialogues as data for conversational agents
Joachim Fainberg, Ben Krause, Mihai Dobre +5
Conversational agents are gaining popularity with the increasing ubiquity of smart devices. However, training agents in a data driven manner is challenging due to a lack of suitabl…
Dynamic Evaluation of Neural Sequence Models
Ben Krause, Emmanuel Kahembwe, Iain Murray +1
We present methodology for using dynamic evaluation to improve neural sequence models. Models are adapted to recent history via a gradient descent based mechanism, causing them to…
Edina: Building an Open Domain Socialbot with Self-dialogues
Ben Krause, Marco Damonte, Mihai Dobre +6
We present Edina, the University of Edinburgh's social bot for the Amazon Alexa Prize competition. Edina is a conversational agent whose responses utilize data harvested from Amazo…