Consistency Training
Related Papers
ConNER: Consistency Training for Cross-lingual Named Entity Recognition
AbstractCross-lingual named entity recognition (NER) suffers from data scarcity in the target languages, especially under zero-shot settings. Existing translate-train or knowledge distillation methods attempt to bridge the language gap, but …...
Consistency Training with Virtual Adversarial Discrete Perturbation
AbstractConsistency training regularizes a model by enforcing predictions of original and perturbed inputs to be similar. Previous studies have proposed various augmentation methods for the perturbation but are limited in …...
Noise-injected Consistency Training and Entropy-constrained Pseudo Labeling for Semi-supervised Extractive Summarization
AbstractLabeling large amounts of extractive summarization data is often prohibitive expensive due to time, financial, and expertise constraints, which poses great challenges to incorporating summarization system in practical applications. This …...
Semi-Supervised Formality Style Transfer with Consistency Training
AbstractFormality style transfer (FST) is a task that involves paraphrasing an informal sentence into a formal one without altering its meaning. To address the data-scarcity problem of existing parallel datasets, …...
Semi-supervised Relation Extraction via Data Augmentation and Consistency-training
AbstractDue to the semantic complexity of the Relation extraction (RE) task, obtaining high-quality human labelled data is an expensive and noisy process. To improve the sample efficiency of the models, …...