Resilience of Named Entity Recognition Models under Adversarial Attack

Sudeshna Das, Jiaul Paik


Abstract
Named entity recognition (NER) is a popular language processing task with wide applications. Progress in NER has been noteworthy, as evidenced by the F1 scores obtained on standard datasets. In practice, however, the end-user uses an NER model on their dataset out-of-the-box, on text that may not be pristine. In this paper we present four model-agnostic adversarial attacks to gauge the resilience of NER models in such scenarios. Our experiments on four state-of-the-art NER methods with five English datasets suggest that the NER models are over-reliant on case information and do not utilise contextual information well. As such, they are highly susceptible to adversarial attacks based on these features.
Anthology ID:
2022.dadc-1.1
Volume:
Proceedings of the First Workshop on Dynamic Adversarial Data Collection
Month:
July
Year:
2022
Address:
Seattle, WA
Editors:
Max Bartolo, Hannah Kirk, Pedro Rodriguez, Katerina Margatina, Tristan Thrush, Robin Jia, Pontus Stenetorp, Adina Williams, Douwe Kiela
Venue:
DADC
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–6
Language:
URL:
https://aclanthology.org/2022.dadc-1.1
DOI:
10.18653/v1/2022.dadc-1.1
Bibkey:
Cite (ACL):
Sudeshna Das and Jiaul Paik. 2022. Resilience of Named Entity Recognition Models under Adversarial Attack. In Proceedings of the First Workshop on Dynamic Adversarial Data Collection, pages 1–6, Seattle, WA. Association for Computational Linguistics.
Cite (Informal):
Resilience of Named Entity Recognition Models under Adversarial Attack (Das & Paik, DADC 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.dadc-1.1.pdf
Code
 das-sudeshna/adversarial-ner
Data
CoNLL 2003