Denoising Multi-Source Weak Supervision for Neural Text Classification

TL;DR

This paper introduces a novel neural text classification method that effectively denoises multiple weak supervision sources without labeled data, outperforming existing weakly-supervised approaches across various benchmarks.

Contribution

It proposes a label denoiser with a conditional soft attention mechanism to estimate source reliability and reduce label noise, enabling effective training without labeled data.

Findings

Outperforms state-of-the-art weakly-supervised methods

Achieves comparable results to fully-supervised models

Effective across sentiment, topic, and relation classification tasks

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. The results show that our model outperforms state-of-the-art weakly-supervised and semi-supervised methods consistently, and achieves comparable performance with fully-supervised methods even without any labeled data. Our code can be found at https://github.com/weakrules/Denoise-multi-weak-sources.