ML Anthology

Towards Robust Named Entity Recognition via Temporal Domain Adaptation and Entity Context Understanding

Oshin Agarwal
AAAI 2022 pp. 12866-12867
doi:10.1609/AAAI.V36I11.21570 /aaai/2022/agarwal2022aaai-robust/

Abstract

Named Entity Recognition models perform well on benchmark datasets but fail to generalize well even in the same domain. The goal of my th esis is to quantify the degree of in-domain generalization in NER, probe models for entity name vs. context learning and finally improve their robustness, focusing on the recognition of ethnically diverse entities and new entities over time when the models are deployed.

PDF AAAI Semantic Scholar

Cite

Text

Agarwal. "Towards Robust Named Entity Recognition via Temporal Domain Adaptation and Entity Context Understanding." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21570

Markdown

[Agarwal. "Towards Robust Named Entity Recognition via Temporal Domain Adaptation and Entity Context Understanding." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/agarwal2022aaai-robust/) doi:10.1609/AAAI.V36I11.21570

BibTeX

@inproceedings{agarwal2022aaai-robust,
  title     = {{Towards Robust Named Entity Recognition via Temporal Domain Adaptation and Entity Context Understanding}},
  author    = {Agarwal, Oshin},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {12866-12867},
  doi       = {10.1609/AAAI.V36I11.21570},
  url       = {https://mlanthology.org/aaai/2022/agarwal2022aaai-robust/}
}