Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model

TL;DR

This paper introduces Hypergeometric Learning, a novel denoising method for distantly supervised NER that models noise distribution explicitly, leading to improved model performance in high-noise scenarios.

Contribution

It proposes a hypergeometric distribution-based denoising algorithm that considers both noise distribution and confidence, enhancing the robustness of distant supervision for NER.

Findings

HGL effectively denoises weakly-labeled data

Significant performance improvements on NER tasks

Robustness in high noise rate settings

Abstract

Denoising is the essential step for distant supervision based named entity recognition. Previous denoising methods are mostly based on instance-level confidence statistics, which ignore the variety of the underlying noise distribution on different datasets and entity types. This makes them difficult to be adapted to high noise rate settings. In this paper, we propose Hypergeometric Learning (HGL), a denoising algorithm for distantly supervised NER that takes both noise distribution and instance-level confidence into consideration. Specifically, during neural network training, we naturally model the noise samples in each batch following a hypergeometric distribution parameterized by the noise-rate. Then each instance in the batch is regarded as either correct or noisy one according to its label confidence derived from previous training step, as well as the noise distribution in this sampled batch. Experiments show that HGL can effectively denoise the weakly-labeled data retrieved from distant supervision, and therefore results in significant improvements on the trained models.