A self-supervised domain-independent Named Entity Recognition using local similarity

Keerthi S. A. Vasan, Uma Satya Ranjan


Abstract
Out-of-vocabulary words can be challenging for NER systems. We introduce a self-supervised system for Named Entity Recognition based on a few-shot annotated examples provided by experts. Subsequently, the rest of the words are tagged using the closest similarity match between the word embeddings of each category, generated in the same context as the original annotations. Additionally, we use a dual-threshold scheme to improve the robustness of the method. Our results show that this method outperforms current state-of-the-art methods in both accuracy and generalisation.
Anthology ID:
2024.icon-1.59
Volume:
Proceedings of the 21st International Conference on Natural Language Processing (ICON)
Month:
December
Year:
2024
Address:
AU-KBC Research Centre, Chennai, India
Editors:
Sobha Lalitha Devi, Karunesh Arora
Venue:
ICON
SIG:
Publisher:
NLP Association of India (NLPAI)
Note:
Pages:
510–514
Language:
URL:
https://aclanthology.org/2024.icon-1.59/
DOI:
Bibkey:
Cite (ACL):
Keerthi S. A. Vasan and Uma Satya Ranjan. 2024. A self-supervised domain-independent Named Entity Recognition using local similarity. In Proceedings of the 21st International Conference on Natural Language Processing (ICON), pages 510–514, AU-KBC Research Centre, Chennai, India. NLP Association of India (NLPAI).
Cite (Informal):
A self-supervised domain-independent Named Entity Recognition using local similarity (Vasan & Satya Ranjan, ICON 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.icon-1.59.pdf