OutFlip: Generating Examples for Unknown Intent Detection with Natural Language Attack
Donghyun Choi, Myeong Cheol Shin, EungGyun Kim, Dong Ryeol Shin · 2021
Out-of-domain (OOD) input detection is vital in a task-oriented dialogue system since the acceptance of unsupported inputs could lead to an incorrect response of the system.This paper proposes OutFlip, a method to generate outof-domain samples using only in-domain training dataset automatically.A white-box natural language attack method HotFlip is revised to generate out-of-domain samples instead of adversarial examples.Our evaluation results showed that integrating OutFlip-generated outof-domain samples into the training dataset could significantly improve an intent classification model's out-of-domain detection performance 1 .