58 citations · 133 across the 6 of their papers we have counts for
6 papers
Pre-trained Summarization Distillation
Sam Shleifer, Alexander M. Rush
Recent state-of-the-art approaches to summarization utilize large pre-trained Transformer models. Distilling these models to smaller student models has become critically important…
Incrementally Improving Graph WaveNet Performance on Traffic Prediction
Sam Shleifer, Clara McCreery, Vamsi Chitters
We present a series of modifications which improve upon Graph WaveNet's previously state-of-the-art performance on the METR-LA traffic prediction task. The goal of this task is to…
Classification as Decoder: Trading Flexibility for Control in Medical Dialogue
Sam Shleifer, Manish Chablani, Anitha Kannan +2
Generative seq2seq dialogue systems are trained to predict the next word in dialogues that have already occurred. They can learn from large unlabeled conversation datasets, build a…
Classification As Decoder: Trading Flexibility For Control In Neural Dialogue
Sam Shleifer, Manish Chablani, Namit Katariya +2
Generative seq2seq dialogue systems are trained to predict the next word in dialogues that have already occurred. They can learn from large unlabeled conversation datasets, build a…
Using Small Proxy Datasets to Accelerate Hyperparameter Search
Sam Shleifer, Eric Prokop
One of the biggest bottlenecks in a machine learning workflow is waiting for models to train. Depending on the available computing resources, it can take days to weeks to train a n…
Low Resource Text Classification with ULMFit and Backtranslation
Sam Shleifer
In computer vision, virtually every state-of-the-art deep learning system is trained with data augmentation. In text classification, however, data augmentation is less widely pract…