Hey there! I'm Victor.

I am on the job market for faculty roles. I anticipate graduating in June, 2023.

I am a PhD student in the Natural Language Processing group at the University of Washington. My advisor is Luke Zettlemoyer. My research is on Reading to Learn: how we can use language understanding to generalize and learn more efficiently.

Why should we read to learn? Most machine learning techniques train on vast amount of labeled data or experience for specific problems. When the problems change (e.g. dialogue on a new topic, language interface for a new database, policy for a new game), we find that the expensive solution we trained no longer generalizes to new problems. Humans generalize to new problems efficiently by reading. For instance, if we go to the store and buy a new board game, you and I can read the manual and quickly figure out how to play the game, without watching millions of games played by experts. The thesis of my research is this:

By reading language specifications that characterize key aspects of the problem, we can efficiently learn solutions that generalize to new problems.

My recent work has focused on

• learning policies that generalize to new environments by reading manuals (LDD, SILG, RTFM, Messenger)
• finding and synthesizing data and curricula to pretrain reading models to ground language (GAZP, E3, WikiSQL)

My work in reading to learn spans several application areas, including dialogue, question answering, semantic parsing, and knowledge base construction/inference. If you are looking to get in touch, please send me an email. Alternatively, you can find me on Mastodon and Twitter.

I am an active member of the NLP and ML communities. I have served on the organizing committees of the Lanuage in Reinforcement Workshop and the Interactive and Executable Semantic Parsing Workshop. I have given invited talks on my work on Reading to Learn at the Multimodal AI Workshopt, Apple, UBC, and other institutions. I review for NeurIPS (2018-present), ACL (2018-present), ICML (2019-present), ICLR (2018-present), EMNLP (2018-present), NAACL (2018-present), CoRL (2019-present), and CoNLL (2018-present).

For undergraduate students: I am happy to answer questions about my research and UW NLP. Unfortunately, I cannot collaborate on more projects at the moment.

I am honoured to be supported by the Apple Scholar in Artificial Intelligence and Machine Learning PhD Fellowship. Previously, I worked as a visiting researcher at Facebook AI Research and as a research scientist at Salesforce Research (formerly MetaMind). I have a Master's degree in computer science from Stanford, where I worked on knowledge base population at the Stanford NLP Group. My advisor at Stanford was Chris Manning. I completed my undergraduate studies in the Electrical and Computer Engineering department at the University of Toronto, where I worked on problems ranging from line outage detection in smart grids to FPGA compilation. My advisor at the University of Toronto was Zeb Tate.

Outside of research, I enjoy running, reading, and cooking. I was a trombonist for more than 10 years, most recently with the University of Toronto Skule Stage Band. I am also an amateur photographer.