DeepAI
Log In Sign Up

OutFlip: Generating Out-of-Domain Samples for Unknown Intent Detection with Natural Language Attack

05/12/2021
by   DongHyun Choi, et al.
0

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 out-of-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 out-of-domain samples into the training dataset could significantly improve an intent classification model's out-of-domain detection performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/03/2020

A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples

Generating adversarial examples for natural language is hard, as natural...
09/09/2019

Out-of-domain Detection for Natural Language Understanding in Dialog Systems

In natural language understanding components, detecting out-of-domain (O...
09/21/2020

Composed Variational Natural Language Generation for Few-shot Intents

In this paper, we focus on generating training examples for few-shot int...
08/29/2022

Intent-based Industrial Network Management Using Natural Language Instructions

Intent-based Networks (IBNs) allow specifying network operations using n...
08/17/2020

Resolving Intent Ambiguities by Retrieving Discriminative Clarifying Questions

Task oriented Dialogue Systems generally employ intent detection systems...
05/26/2020

Generating Semantically Valid Adversarial Questions for TableQA

Adversarial attack on question answering systems over tabular data (Tabl...