no code implementations • 10 May 2013 • James Foulds, Levi Boyles, Christopher DuBois, Padhraic Smyth, Max Welling
We propose a stochastic algorithm for collapsed variational Bayesian inference for LDA, which is simpler and more efficient than the state of the art method.
no code implementations • NAACL 2021 • Shayne Longpre, Yi Lu, Christopher DuBois
In the context of question answering, we investigate competing hypotheses for the existence of MPPIs, including poor posterior calibration of neural models, lack of pretraining, and "dataset bias" (where a model learns to attend to spurious, non-generalizable cues in the training data).
no code implementations • Findings of the Association for Computational Linguistics 2020 • Shayne Longpre, Yu Wang, Christopher DuBois
Task-agnostic forms of data augmentation have proven widely effective in computer vision, even on pretrained models.
no code implementations • NAACL (MIA) 2022 • Ivan Montero, Shayne Longpre, Ni Lao, Andrew J. Frank, Christopher DuBois
Existing methods for open-retrieval question answering in lower resource languages (LRLs) lag significantly behind English.