Are Multilingual BERT models robust? A Case Study on Adversarial Attacks for Multilingual Question Answering

04/15/2021 ∙ by Sara Rosenthal, et al. ∙ 0

Recent approaches have exploited weaknesses in monolingual question answering (QA) models by adding adversarial statements to the passage. These attacks caused a reduction in state-of-the-art performance by almost 50 paper, we are the first to explore and successfully attack a multilingual QA (MLQA) system pre-trained on multilingual BERT using several attack strategies for the adversarial statement reducing performance by as much as 85 that the model gives priority to English and the language of the question regardless of the other languages in the QA pair. Further, we also show that adding our attack strategies during training helps alleviate the attacks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.