Papers › Low Resource Text Classification with ULMFit and Backtranslation

Low Resource Text Classification with ULMFit and Backtranslation

21 Mar 2019arXiv:1903.09244archive 2025-07-28

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 practiced because it must be performed before training and risks introducing label noise. We augment the IMDB movie reviews dataset with examples generated by two families of techniques: random token perturbations introduced by Wei and Zou [2019] and backtranslation -- translating to a second language then back to English. In low resource environments, backtranslation generates significant improvement on top of the state of-the-art ULMFit model. A ULMFit model pretrained on wikitext103 and then fine-tuned on only 50 IMDB examples and 500 synthetic examples generated by backtranslation achieves 80.6% accuracy, an 8.1% improvement over the augmentation-free baseline with only 9 minutes of additional training time. Random token perturbations do not yield any improvements but incur equivalent computational cost. The benefits of training with backtranslated examples decreases with the size of the available training data. On the full dataset, neither augmentation technique improves upon ULMFit's state of the art performance. We address this by using backtranslations as a form of test time augmentation as well as ensembling ULMFit with other models, and achieve small improvements.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

oraby8/TextDataAug mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Classification Data Augmentation General Classification Text Classification text-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AWD-LSTM Activation Regularization Discriminative Fine-Tuning DropConnect Dropout Embedding Dropout LSTM Sigmoid Activation Slanted Triangular Learning Rates Tanh Activation Temporal Activation Regularization ULMFiT Variational Dropout Weight Tying

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections