Sort by:

• Highly Influential Citations
• Citations
• Acceleration
• Velocity
• Recency

Learn More

Dynamic Coattention Networks For Question Answering

• Caiming Xiong, Victor Zhong, Richard Socher
• ArXiv
• 2016

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 incorrect answers. To… (More)

Pointer Sentinel Mixture Models

• Stephen Merity, Caiming Xiong, James Bradbury, Richard Socher
• ArXiv
• 2016

Recent neural network sequence models with softmax classifiers have achieved their best language modeling performance only with very large hidden states and large vocabularies. Even then they… (More)

Dynamic Memory Networks for Visual and Textual Question Answering

• Caiming Xiong, Stephen Merity, Richard Socher
• ICML
• 2016

Neural network architectures with memory and attention mechanisms exhibit certain reasoning capabilities required for question answering. One such architecture, the dynamic memory network (DMN),… (More)

A Deep Reinforced Model for Abstractive Summarization

• Romain Paulus, Caiming Xiong, Richard Socher
• ArXiv
• 2017

Attentional, RNN-based encoder-decoder models for abstractive summarization have achieved good performance on short input and output sequences. However, for longer documents and summaries, these… (More)

Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

• Victor Zhong, Caiming Xiong, Richard Socher
• ArXiv
• 2017

Relational databases store a significant amount of the worlds data. However, accessing this data currently requires users to understand a query language such as SQL. We propose Seq2SQL, a deep neural… (More)

Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning

• Jiasen Lu, Caiming Xiong, Devi Parikh, Richard Socher
• IEEE Conference on Computer Vision and Pattern…
• 2017

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, the decoder likely… (More)

Streaming Hierarchical Video Segmentation

• Chenliang Xu, Caiming Xiong, Jason J. Corso
• ECCV
• 2012

The use of video segmentation as an early processing step in video analysis lags behind the use of image segmentation for image analysis, despite many available video segmentation methods. A major… (More)

Learned in Translation: Contextualized Word Vectors

• Bryan McCann, James Bradbury, Caiming Xiong, Richard Socher
• NIPS
• 2017

Computer vision has benefited from initializing multiple deep layers with weights pretrained on large supervised training sets like ImageNet. Natural language processing (NLP) typically sees… (More)

A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks

• Kazuma Hashimoto, Caiming Xiong, Yoshimasa Tsuruoka, Richard Socher
• EMNLP
• 2017

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 and semantics would… (More)

Quasi-Recurrent Neural Networks

• James Bradbury, Stephen Merity, Caiming Xiong, Richard Socher
• ArXiv
• 2016

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 and makes RNNs… (More)

• ‹
• 1
• 2
• 3
• 4
• 5
• ›