no code implementations • 2 Sep 2021 • Gurmeet Manku, James Lee-Thorp, Bhargav Kanagal, Joshua Ainslie, Jingchen Feng, Zach Pearson, Ebenezer Anjorin, Sudeep Gandhe, Ilya Eckstein, Jim Rosswog, Sumit Sanghai, Michael Pohl, Larry Adams, D. Sivakumar
The dialog understanding system consists of a deep-learned Contextual Language Understanding module, which interprets user utterances, and a primarily rules-based Dialog-State Tracker (DST), which updates the dialog state and formulates search requests intended for the fulfillment engine.
no code implementations • NAACL 2021 • Yury Zemlyanskiy, Joshua Ainslie, Michiel de Jong, Philip Pham, Ilya Eckstein, Fei Sha
Knowledge-intensive tasks such as question answering often require assimilating information from different sections of large inputs such as books or article collections.
14 code implementations • NAACL 2022 • James Lee-Thorp, Joshua Ainslie, Ilya Eckstein, Santiago Ontanon
At longer input lengths, our FNet model is significantly faster: when compared to the "efficient" Transformers on the Long Range Arena benchmark, FNet matches the accuracy of the most accurate models, while outpacing the fastest models across all sequence lengths on GPUs (and across relatively shorter lengths on TPUs).
Ranked #5 on Paraphrase Identification on Quora Question Pairs
no code implementations • EACL 2021 • Yury Zemlyanskiy, Sudeep Gandhe, Ruining He, Bhargav Kanagal, Anirudh Ravula, Juraj Gottweis, Fei Sha, Ilya Eckstein
This enables a new class of powerful, high-capacity representations that can ultimately distill much of the useful information about an entity from multiple text sources, without any human supervision.