Litcius/Paper detail

Denoising Multi-Source Weak Supervision for Neural Text Classification

Wendi Ren, Yinghao Li, Hanting Su, David Kartchner, Cassie S. Mitchell, Chao Zhang

202045 citationsDOIOpen Access PDF

Abstract

We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and incomplete. To address these two challenges, we design a label denoiser, which estimates the source reliability using a conditional soft attention mechanism and then reduces label noise by aggregating rule-annotated weak labels. The denoised pseudo labels then supervise a neural classifier to predicts soft labels for unmatched samples, which address the rule coverage issue. We evaluate our model on five benchmarks for sentiment, topic, and relation classifications.

Topics & Concepts

Computer scienceClassifier (UML)Artificial intelligenceNoisy dataSource codeNoise reductionMachine learningPattern recognition (psychology)Labeled dataNoise (video)Artificial neural networkReliability (semiconductor)Code (set theory)Data miningImage (mathematics)Quantum mechanicsPower (physics)Programming languageOperating systemSet (abstract data type)PhysicsText and Document Classification TechnologiesTopic ModelingMachine Learning and Data Classification