Uncover the Ground-Truth Relations in Distant Supervision: A Neural Expectation-Maximization Framework
This addresses a critical bottleneck in real-world relation extraction by handling label noise, which is incremental as it builds on prior models that assumed clean labels.
The paper tackles the problem of noisy labels in distant supervision for relation extraction by proposing a neural expectation-maximization framework that denoises labels during learning, resulting in significant improvements in uncovering ground-truth relations.
Distant supervision for relation extraction enables one to effectively acquire structured relations out of very large text corpora with less human efforts. Nevertheless, most of the prior-art models for such tasks assume that the given text can be noisy, but their corresponding labels are clean. Such unrealistic assumption is contradictory with the fact that the given labels are often noisy as well, thus leading to significant performance degradation of those models on real-world data. To cope with this challenge, we propose a novel label-denoising framework that combines neural network with probabilistic modelling, which naturally takes into account the noisy labels during learning. We empirically demonstrate that our approach significantly improves the current art in uncovering the ground-truth relation labels.