1.3k citations · 12.3k across the 104 of their papers we have counts for
8 papers · 1 filter
A Way out of the Odyssey: Analyzing and Combining Recent Insights for LSTMs
Shayne Longpre, Sabeek Pradhan, Caiming Xiong +1
LSTMs have become a basic building block for many deep NLP models. In recent years, many improvements and variations have been proposed for deep sequence models in general, and LST…
Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
Jiasen Lu, Caiming Xiong, Devi Parikh +1
Attention-based neural encoder-decoder frameworks have been widely adopted for image captioning. Most methods force visual attention to be active for every generated word. However,…
Quasi-Recurrent Neural Networks
James Bradbury, Stephen Merity, Caiming Xiong +1
Recurrent neural networks are a powerful tool for modeling sequential data, but the dependence of each timestep's computation on the previous timestep's output limits parallelism a…
Dynamic Coattention Networks For Question Answering
Caiming Xiong, Victor Zhong, Richard Socher
Several deep learning models have been proposed for question answering. However, due to their single-pass nature, they have no way to recover from local maxima corresponding to inc…
A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
Kazuma Hashimoto, Caiming Xiong, Yoshimasa Tsuruoka +1
Transfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks. Ideally, the linguistic levels of morphology, syntax a…
Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
Hakan Inan, Khashayar Khosravi, Richard Socher
Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional clas…