Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data
This addresses the challenge of obtaining labeled data for discriminative models by improving weak supervision techniques, though it is incremental as it builds on existing generative model approaches.
The paper tackles the problem of weak supervision sources performing inconsistently across latent subsets in training data by introducing Socratic learning, which uses discriminative model feedback to identify these subsets and augment generative models, resulting in up to 56.06% error reduction in relation extraction tasks.
A challenge in training discriminative models like neural networks is obtaining enough labeled training data. Recent approaches use generative models to combine weak supervision sources, like user-defined heuristics or knowledge bases, to label training data. Prior work has explored learning accuracies for these sources even without ground truth labels, but they assume that a single accuracy parameter is sufficient to model the behavior of these sources over the entire training set. In particular, they fail to model latent subsets in the training data in which the supervision sources perform differently than on average. We present Socratic learning, a paradigm that uses feedback from a corresponding discriminative model to automatically identify these subsets and augments the structure of the generative model accordingly. Experimentally, we show that without any ground truth labels, the augmented generative model reduces error by up to 56.06% for a relation extraction task compared to a state-of-the-art weak supervision technique that utilizes generative models.