Consistency Loss
Related Papers
Local Additivity Based Data Augmentation for Semi-supervised NER
AbstractNamed Entity Recognition (NER) is one of the first stages in deep language understanding yet current NER models heavily rely on human-annotated data. In this work, to alleviate the dependence …...
Modelling Context Emotions using Multi-task Learning for Emotion Controlled Dialog Generation
AbstractA recent topic of research in natural language generation has been the development of automatic response generation modules that can automatically respond to a user’s utterance in an empathetic manner. …...
PROTAUGMENT: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning
AbstractRecent research considers few-shot intent detection as a meta-learning problem: the model is learning to learn from a consecutive set of small tasks named episodes. In this work, we propose …...
Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data
AbstractUnsupervised Data Augmentation (UDA) is a semisupervised technique that applies a consistency loss to penalize differences between a model’s predictions on (a) observed (unlabeled) examples; and (b) corresponding ‘noised’ examples …...
Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks
AbstractWhile fine-tuning pre-trained models for downstream classification is the conventional paradigm in NLP, often task-specific nuances may not get captured in the resultant models. Specifically, for tasks that take two …...