Yikang Shen
transformer
language models
constituency parsing
unsupervised parsing
masked language modeling
unsupervised dependency parsing
visual reasoning; symbolic representations; multi-modal vision
3
presentations
3
number of views
SHORT BIO
Yikang Shen is a senior Ph.D. student in the Mila lab at the University of Montreal and recipient of the ICLR 2019 best paper award. His research focuses on the key mechanisms that allow deep learning methods to understand the latent structure of human language and model its compositional phenomenons. The goal is to improve the robustness, interpretability, and systematic generalization of NLP models. He is also interested in hierarchical reinforcement learning. He did several internships at Microsoft Research and Google AI.
Presentations
Visual Chain-of-Thought Prompting for Knowledge-Based Visual Reasoning
Zhenfang Chen and 6 other authors
Unsupervised Dependency Graph Network
Yikang Shen and 5 other authors
Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle
Yikang Shen and 4 other authors