Bio (detailed CV)
I am currently a research scientist at Facebook AI Research (FAIR). Previously, I was an instructor at Princeton University and the Institute for Advanced Study. In 2017, I completed a PhD in computer science at Stanford where I worked on machine learning and natural language processing co-advised by Chris Manning and Percy Liang. Before that I got a BASc at University of Toronto and worked on capsules with Geoffrey Hinton.
The best way to contact me is email: sidawxyz [at] gmail.com
Language to code: Coder-reviewer, LEVER, DS-1000, InCoder, aggregating execution. Before LLMs, I worked on training more grounded models and bridging the formal programming language and informal natural language: learning language games interactively from human feedback, and naturalizing a programming language.
Translation: My paper accessing higher dimensions is the most direct method to achieve unsupervised word translation with improved robustness / data efficiency. On the other hand, using pretrained model for bitext construction and improve word translation.
Others: Fast dropout, which helped to understand dropout and anticipated variational dropout. Baselines and bigrams (NBSVM): showing (again) the power of bag of bigrams over neural networks despite their use of word order, which is adopted by the popular fastText. Capsules and transforming autoencoders, which are early works in self-supervised learning.
Area chair for Neurips, ICLR, ICML
Reviewer for TACL, ARR, Neurips, ICLR, EMNLP, JMLR, ICML
- Spring 2018: COS495 Natural language processing
- Fall 2015: Head TA for CS224 Natural language processing
- Winter 2013: TA for CS229T Statistical machine learning