Gabi Dobocanblog.telepat.io·Dec 5, 2024Unlocking Efficiency in Task-Oriented Dialogue Systems with Self-Training and Constrained DecodingIntroduction Task-oriented dialogue systems have become increasingly popular, thanks to advancements in natural language generation (NLG). These systems, however, often require substantial amounts of annotated data to generate coherent and contextual...Constrained Decoding
Retzam Tarleretzam.hashnode.dev·Jul 29, 2024Semi-Supervised LearningSemi-supervised learning is a branch of machine learning that uses both labelled and unlabelled data to train models. It uses both supervised and unsupervised learning methods to train AI models. We have learned in-depth about supervised and unsuperv...Self-training
