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

被引：0

作者：

Choi, DongHyun ^{[1
,2
]}

Shin, Myeong Cheol ^{[1
]}

Kim, EungGyun ^{[1
]}

Shin, Dong Ryeol ^{[2
]}

机构：

[1] Kakao Enterprise, Seongnam, South Korea

[2] Sungkyunkwan Univ, Seoul, South Korea

来源：

FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021 | 2021年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：504 / 512

页数：9

共 50 条

[31] Unsupervised Out-of-Domain Detection via Pre-trained Transformers
Xu, Keyang
Ren, Tongzheng
Zhang, Shikun
Feng, Yihao
Xiong, Caiming
59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 (ACL-IJCNLP 2021), 2021, : 1052 - 1061
[32] Out-of-domain utterance detection using classification confidences of multiple topics
Lane, Ian
Kawahara, Tatsuya
Matsui, Tomoko
Nakamura, Satoshi
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (01): : 150 - 161
[33] Out-of-domain detection based on confidence measures from multiple topic classification
Lane, IR
Kawahara, T
Matsui, T
Nakamura, S
2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 757 - 760
[34] OUT-OF-DOMAIN SLOT VALUE DETECTION FOR SPOKEN DIALOGUE SYSTEMS WITH CONTEXT INFORMATION
Kobayashi, Yuka
Yoshida, Takami
Iwata, Kenji
Fujimura, Hiroshi
Akamine, Masami
2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018), 2018, : 854 - 861
[35] ADVERSARIAL GENERATIVE DISTANCE-BASED CLASSIFIER FOR ROBUST OUT-OF-DOMAIN DETECTION
Zeng, Zhiyuan
Xu, Hong
He, Keqing
Yan, Yuanmeng
Liu, Sihong
Liu, Zijun
Xu, Weiran
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 7658 - 7662
[36] A subjective-logic-based model uncertainty estimation mechanism for out-of-domain detection
Xie, Jiarui
Chateau, Thierry
Antoine, Violaine
2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
[37] Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection in Task Oriented Dialog
Gangal, Varun
Arora, Abhinav
Einolghozati, Arash
Gupta, Sonal
THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 7764 - 7771
[38] Neural sentence embedding using only in-domain sentences for out-of-domain sentence detection in dialog systems
Ryu, Seonghan
Kim, Seokhwan
Choi, Junhwi
Yu, Hwanjo
Lee, Gary Geunbae
PATTERN RECOGNITION LETTERS, 2017, 88 : 26 - 32
[39] Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates
Kim, Joo-Kyung
Kim, Young-Bum
19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 556 - 560
[40] ANCHOR-GUIDED GAN WITH CONTRASTIVE LOSS FOR LOW-RESOURCE OUT-OF-DOMAIN DETECTION
Zhu, Jiankai
Huang, Peijie
Ruan, Ziheng
Zhu, Yuhui
Liang, Chaojie
Xu, Yuhong
2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2024), 2024, : 11516 - 11520

← 1 2 3 4 5 →