Programmatic weak supervision creates models without hand-labeled training data by combining the outputs of noisy, user-written rules and other heuristic labelers. Existing frameworks make the restrictive assumption that labelers output a single class label. Enabling users to create partial labelers that output subsets of possible class labels would greatly expand the expressivity of programmatic weak supervision. We introduce this capability by defining a probabilistic generative model that can estimate the underlying accuracies of multiple noisy partial labelers without ground truth labels. We prove that this class of models is generically identifiable up to label swapping under mild conditions. We also show how to scale up learning to 100k examples in one minute, a 300X speed up compared to a naive implementation. We evaluate our framework on three text classification and six object classification tasks. On text tasks, adding partial labels increases average accuracy by 9.6 percentage points. On image tasks, we show that partial labels allow us to approach some zero-shot object classification problems with programmatic weak supervision by using class attributes as partial labelers. Our framework is able to achieve accuracy comparable to recent embedding-based zero-shot learning methods using only pre-trained attribute detectors

本文提出了一种基于概率生成模型的能够估计多个噪声偏差的部分标注工具并扩展了程序化弱监督的基础，通过对3个文本分类和6个对象分类任务的评估，证明了部分标注的效果可达到8.6%的平均准确率提高，进而探讨了部分标注在零样本对象分类任务中的应用以及与最新零样本学习方法相比的效果。

多个噪声部分标注者中学习