Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning

TL;DR

This paper introduces a confidence-based multi-class positive and unlabeled learning approach to improve distant supervision in named entity recognition, addressing high false negative rates due to incomplete annotations.

Contribution

It proposes a novel Conf-MPU method that estimates confidence scores for tokens and trains a classifier, advancing distant supervision techniques for NER.

Findings

Conf-MPU outperforms existing DS-NER methods on benchmark datasets.

The approach effectively handles incomplete annotations in distant supervision.

Experimental results demonstrate improved accuracy in NER tasks.

Abstract

In this paper, we study the named entity recognition (NER) problem under distant supervision. Due to the incompleteness of the external dictionaries and/or knowledge bases, such distantly annotated training data usually suffer from a high false negative rate. To this end, we formulate the Distantly Supervised NER (DS-NER) problem via Multi-class Positive and Unlabeled (MPU) learning and propose a theoretically and practically novel CONFidence-based MPU (Conf-MPU) approach. To handle the incomplete annotations, Conf-MPU consists of two steps. First, a confidence score is estimated for each token of being an entity token. Then, the proposed Conf-MPU risk estimation is applied to train a multi-class classifier for the NER task. Thorough experiments on two benchmark datasets labeled by various external knowledge demonstrate the superiority of the proposed Conf-MPU over existing DS-NER methods.