Lower Dimensional Kernels for Video Discriminators

1 code implementation • 18 Dec 2019 • Emmanuel Kahembwe, Subramanian Ramamoorthy

This work presents an analysis of the discriminators used in Generative Adversarial Networks (GANs) for Video.

Video Generation

Dynamic Evaluation of Transformer Language Models

1 code implementation • 17 Apr 2019 • Ben Krause, Emmanuel Kahembwe, Iain Murray, Steve Renals

This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation.

Language Modelling

Talking to myself: self-dialogues as data for conversational agents

1 code implementation • 18 Sep 2018 • Joachim Fainberg, Ben Krause, Mihai Dobre, Marco Damonte, Emmanuel Kahembwe, Daniel Duma, Bonnie Webber, Federico Fancellu

Conversational agents are gaining popularity with the increasing ubiquity of smart devices.

Edina: Building an Open Domain Socialbot with Self-dialogues

no code implementations • 28 Sep 2017 • Ben Krause, Marco Damonte, Mihai Dobre, Daniel Duma, Joachim Fainberg, Federico Fancellu, Emmanuel Kahembwe, Jianpeng Cheng, Bonnie Webber

We present Edina, the University of Edinburgh's social bot for the Amazon Alexa Prize competition.

Dynamic Evaluation of Neural Sequence Models

3 code implementations • ICML 2018 • Ben Krause, Emmanuel Kahembwe, Iain Murray, Steve Renals

We present methodology for using dynamic evaluation to improve neural sequence models.

Language Modelling