DATNet: Dual Adversarial Transfer for Low-resource Named Entity Recognition

Joey Tianyi Zhou, Hao Zhang, Di Jin, Hongyuan Zhu, Rick Siow Mong Goh, Kenneth Kwok

Abstract: We propose a new architecture termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER). Specifically, two variants of DATNet, i.e., DATNet-F and DATNet-P, are proposed to explore effective feature fusion between high and low resource. To address the noisy and imbalanced training data, we propose a novel Generalized Resource-Adversarial Discriminator (GRAD). Additionally, adversarial training is adopted to boost model generalization. We examine the effects of different components in DATNet across domains and languages and show that significant improvement can be obtained especially for low-resource data. Without augmenting any additional hand-crafted features, we achieve new state-of-the-art performances on CoNLL and Twitter NER---88.16% F1 for Spanish, 53.43% F1 for WNUT-2016, and 42.83% F1 for WNUT-2017.

Keywords: Low-resource, Named Entity Recognition

TL;DR: We propose a new architecture termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER) and achieve new state-of-the-art performances on CoNLL and Twitter NER.

Data: [CoNLL 2002](https://paperswithcode.com/dataset/conll-2002)