1.3k citations · 12.3k across the 104 of their papers we have counts for
12 papers · 2 filters
A Flexible Approach to Automated RNN Architecture Generation
Martin Schrimpf, Stephen Merity, James Bradbury +1
The process of designing neural architectures requires expert knowledge and extensive trial and error. While automated architecture search may simplify these requirements, the recu…
Improved Regularization Techniques for End-to-End Speech Recognition
Yingbo Zhou, Caiming Xiong, Richard Socher
Regularization is important for end-to-end speech models, since the models are highly flexible and easy to overfit. Data augmentation and dropout has been important for improving e…
Improving End-to-End Speech Recognition with Policy Learning
Yingbo Zhou, Caiming Xiong, Richard Socher
Connectionist temporal classification (CTC) is widely used for maximum likelihood learning in end-to-end speech recognition models. However, there is usually a disparity between th…
Learning when to skim and when to read
Alexander Rosenberg Johansen, Richard Socher
Many recent advances in deep learning for natural language processing have come at increasing computational cost, but the power of these state-of-the-art models is not needed for e…
DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
Caiming Xiong, Victor Zhong, Richard Socher
Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometim…
Non-Autoregressive Neural Machine Translation
Jiatao Gu, James Bradbury, Caiming Xiong +2
Existing approaches to neural machine translation condition each output word on previously generated outputs. We introduce a model that avoids this autoregressive property and prod…