Self-Training with Weak Supervision

TL;DR

This paper introduces ASTRA, a semi-supervised framework that combines weak supervision, self-training, and rule attention to improve text classification by leveraging all available data, including unlabeled and weakly labeled instances.

Contribution

ASTRA is a novel weak supervision approach that utilizes self-training and rule attention to effectively incorporate unlabeled data and weak rules for improved learning.

Findings

Significant performance improvements over state-of-the-art baselines.

Effective use of unlabeled data through self-training.

Robust rule aggregation via rule attention network.

Abstract

State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such settings to automatically generate weakly labeled training data. However, learning with weak rules is challenging due to their inherent heuristic and noisy nature. An additional challenge is rule coverage and overlap, where prior work on weak supervision only considers instances that are covered by weak rules, thus leaving valuable unlabeled data behind. In this work, we develop a weak supervision framework (ASTRA) that leverages all the available data for a given task. To this end, we leverage task-specific unlabeled data through self-training with a model (student) that considers contextualized representations and predicts pseudo-labels for instances that may not be covered by weak rules. We further develop a rule attention network (teacher) that learns how to aggregate student pseudo-labels with weak rule labels, conditioned on their fidelity and the underlying context of an instance. Finally, we construct a semi-supervised learning objective for end-to-end training with unlabeled data, domain-specific rules, and a small amount of labeled data. Extensive experiments on six benchmark datasets for text classification demonstrate the effectiveness of our approach with significant improvements over state-of-the-art baselines.