Resilience of Named Entity Recognition Models under Adversarial Attack
Sudeshna Das, Jiaul H. Paik · 2022
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 modelagnostic 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.