Peng Xu
Senior Researcher
MSc Computing Science, University of Alberta
I'm a Senior Researcher at Borealis AI, Toronto. I'm broadly interested in a range of topics on machine learning and natural language processing, including semantic parsing, language modelling, generative modelling, information extraction, text generation and optimization. My research goal is to find the right way to achieve understandings between humans and machines, so that machines can learn logic and reasoning like humans and humans can trust machines to facilitate critical decision making.
Before joining Borealis AI, I was a master student of Department of Computing Science at University of Alberta, advised by Denilson Barbosa.
Research Areas
Reinforcement Learning
Natural Language Processing
Publications
June 3, 2021
Optimizing Deeper Transformers on Small Datasets
Association for Computational Linguistics (ACL), 2021
June 3, 2021
TURING: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface
Association for Computational Linguistics (ACL), 2021
July 12, 2020
On Variational Learning of Controllable Representations for Text without Supervision
International Conference on Machine Learning (ICML), 2020
June 3, 2020
Better Long-Range Dependency by Bootstrapping A Mutual Information Regularizer
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
July 28, 2019
A Cross-Domain Transferable Neural Coherence Model
Association for Computational Linguistics (ACL), 2019