789 citations · 3.9k across the 31 of their papers we have counts for
7 papers · 1 filter
Global Capacity Measures for Deep ReLU Networks via Path Sampling
Ryan Theisen, Jason M. Klusowski, Huan Wang +3
Classical results on the statistical complexity of linear models have commonly identified the norm of the weights as a fundamental capacity measure. Generalizations of this…
CTRL: A Conditional Transformer Language Model for Controllable Generation
Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney +2
Large-scale language models show promising text generation capabilities, but users cannot easily control particular aspects of the generated text. We release CTRL, a 1.63 billion-p…
Pretrained AI Models: Performativity, Mobility, and Change
Lav R. Varshney, Nitish Shirish Keskar, Richard Socher
The paradigm of pretrained deep learning models has recently emerged in artificial intelligence practice, allowing deployment in numerous societal settings with limited computation…
Neural Text Summarization: A Critical Evaluation
Wojciech Kryściński, Nitish Shirish Keskar, Bryan McCann +2
Text summarization aims at compressing long documents into a shorter form that conveys the most important parts of the original document. Despite increased interest in the communit…
XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering
Jasdeep Singh, Bryan McCann, Nitish Shirish Keskar +2
While natural language processing systems often focus on a single language, multilingual transfer learning has the potential to improve performance, especially for low-resource lan…
Unifying Question Answering, Text Classification, and Regression via Span Extraction
Nitish Shirish Keskar, Bryan McCann, Caiming Xiong +1
Even as pre-trained language encoders such as BERT are shared across many tasks, the output layers of question answering, text classification, and regression models are significant…
Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
Victor Zhong, Caiming Xiong, Nitish Shirish Keskar +1
End-to-end neural models have made significant progress in question answering, however recent studies show that these models implicitly assume that the answer and evidence appear c…