Zero-Resource Cross-Domain Named Entity Recognition

TL;DR

This paper introduces a novel zero-resource cross-domain NER model that employs multi-task learning and a Mixture of Entity Experts framework, achieving competitive results without external data.

Contribution

The paper proposes a new zero-resource NER approach combining multi-task learning and MoEE, eliminating the need for external unlabeled or labeled data in target domains.

Findings

Outperforms strong unsupervised cross-domain models

Close performance to resource-intensive state-of-the-art models

Effective domain adaptation without external resources

Abstract

Existing models for cross-domain named entity recognition (NER) rely on numerous unlabeled corpus or labeled NER training data in target domains. However, collecting data for low-resource target domains is not only expensive but also time-consuming. Hence, we propose a cross-domain NER model that does not use any external resources. We first introduce a Multi-Task Learning (MTL) by adding a new objective function to detect whether tokens are named entities or not. We then introduce a framework called Mixture of Entity Experts (MoEE) to improve the robustness for zero-resource domain adaptation. Finally, experimental results show that our model outperforms strong unsupervised cross-domain sequence labeling models, and the performance of our model is close to that of the state-of-the-art model which leverages extensive resources.