@article{Liu_Xu_Yu_Dai_Ji_Cahyawijaya_Madotto_Fung_2021, title={CrossNER: Evaluating Cross-Domain Named Entity Recognition}, volume={35}, url={https://ojs.aaai.org/index.php/AAAI/article/view/17587}, DOI={10.1609/aaai.v35i15.17587}, abstractNote={Cross-domain named entity recognition (NER) models are able to cope with the scarcity issue of NER samples in target domains. However, most of the existing NER benchmarks lack domain-specialized entity types or do not focus on a certain domain, leading to a less effective cross-domain evaluation. To address these obstacles, we introduce a cross-domain NER dataset (CrossNER), a fully-labeled collection of NER data spanning over five diverse domains with specialized entity categories for different domains. Additionally, we also provide a domain-related corpus since using it to continue pre-training language models (domain-adaptive pre-training) is effective for the domain adaptation. We then conduct comprehensive experiments to explore the effectiveness of leveraging different levels of the domain corpus and pre-training strategies to do domain-adaptive pre-training for the cross-domain task. Results show that focusing on the fractional corpus containing domain-specialized entities and utilizing a more challenging pre-training strategy in domain-adaptive pre-training are beneficial for the NER domain adaptation, and our proposed method can consistently outperform existing cross-domain NER baselines. Nevertheless, experiments also illustrate the challenge of this cross-domain NER task. We hope that our dataset and baselines will catalyze research in the NER domain adaptation area. The code and data are available at https://github.com/zliucr/CrossNER.}, number={15}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Liu, Zihan and Xu, Yan and Yu, Tiezheng and Dai, Wenliang and Ji, Ziwei and Cahyawijaya, Samuel and Madotto, Andrea and Fung, Pascale}, year={2021}, month={May}, pages={13452-13460} }