An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract)

Qi Peng, Changmeng Zheng, Yi Cai, Tao Wang, Haoran Xie, Qing Li

AAAI 2021 pp. 15865-15866

doi:10.1609/AAAI.V35I18.17929 /aaai/2021/peng2021aaai-entity/

Abstract

Existing methods for named entity recognition (NER) are critically relied on the amount of labeled data. However, these methods suffer from performance decline in a new domain which is fully-unlabeled. To handle the situation, we propose an entity-aware adversarial domain adaptation network, which utilizes the labeled data from source domain and then adapts to unlabeled target domain. We first apply adversarial training to reduce the distribution gap between different domains. Furthermore, we introduce an entity-aware attention to guide adversarial to achieve the alignment of entity features. The experimental results show that our model outperforms the state-of-the-art approaches.

PDF AAAI Semantic Scholar

Cite

Text

Peng et al. "An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17929

Markdown

[Peng et al. "An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/peng2021aaai-entity/) doi:10.1609/AAAI.V35I18.17929

BibTeX

@inproceedings{peng2021aaai-entity,
  title     = {{An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract)}},
  author    = {Peng, Qi and Zheng, Changmeng and Cai, Yi and Wang, Tao and Xie, Haoran and Li, Qing},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15865-15866},
  doi       = {10.1609/AAAI.V35I18.17929},
  url       = {https://mlanthology.org/aaai/2021/peng2021aaai-entity/}
}