Text World and Word Embedding Lower Bounds

In the first half of this episode, Kyle speaks with Marc-Alexandre Côté and Wendy Tay about Text World. Text World is an engine that simulates text adventure games. Developers are encouraged to try out their reinforcement learning skills building agents that can programmatically interact with the generated text adventure games.

Guests

Marc-Alexandre Côté: Marc-Alexandre Côté is a Principal Researcher at Microsoft Research – Montréal. Since joining Microsoft in 2017, his research focuses on reinforcement learning and natural language understanding. Specifically, he is leading the Microsoft TextWorld project which aims at developing new RL agents capable of navigating and interacting with text environments (e.g. text-based adventure games). Such agents should possess skills like reading and understanding natural language text, information/knowledge-gathering, planning, dealing with combinatorially large action-space. Marc-Alexandre Côté was a member of the organizing committee for the Wordplay: When Language Meets Games workshops at NeurIPS 2018 and 2020, and NACCL 2022. He also served as a program committee member for NeurIPS, ICLR, and ICML.

Wendy Tay: Wendy Tay is a Program Manager at Microsoft Research Montreal lab based out of Montreal, QC, Canada. She works with researchers, applied researchers, and engineers on research projects and products using the natural language deep learning. She leads ideation, product design, and innovation transfers for technologies coming out of the lab. Before joining Microsoft Research in 2017, Wendy was part of Azure Identity, where she drove telemetry and developer engagement efforts on the Microsoft Graph team (developer APIs). She has an interest in artificial intelligence, new product development, ethical considerations of technology, and UX design. Prior to joining Microsoft, Wendy was a Technology Associate at Thomson Reuters. Wendy graduated from the University of Michigan with her Ph.D. in chemical biology in 2014.

Kevin Patel: Natural-language-processing researcher whose doctoral work focused on word embeddings, including theoretical questions about the dimensionality needed to represent semantic relationships.