Zero-Resource Cross-Lingual Named Entity Recognition

TL;DR

This paper introduces an unsupervised cross-lingual NER model that transfers knowledge between languages without any labeled data, using adversarial learning and feature augmentation, achieving state-of-the-art results.

Contribution

It presents a novel unsupervised approach for cross-lingual NER that does not require bilingual resources, outperforming existing methods.

Findings

Outperforms existing models on five languages

Sets new SOTA for each language pair

Effective transfer without bilingual data

Abstract

Recently, neural methods have achieved state-of-the-art (SOTA) results in Named Entity Recognition (NER) tasks for many languages without the need for manually crafted features. However, these models still require manually annotated training data, which is not available for many languages. In this paper, we propose an unsupervised cross-lingual NER model that can transfer NER knowledge from one language to another in a completely unsupervised way without relying on any bilingual dictionary or parallel data. Our model achieves this through word-level adversarial learning and augmented fine-tuning with parameter sharing and feature augmentation. Experiments on five different languages demonstrate the effectiveness of our approach, outperforming existing models by a good margin and setting a new SOTA for each language pair.