TOD BERT
material
ID: todbert
Related Papers
Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
AbstractAs the labeling cost for different modules in task-oriented dialog (ToD) systems is expensive, a major challenge is to train different modules with the least amount of labeled data. Recently, …...
N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking
AbstractAugmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation …...