ACL Findings2021
OutFlip: Generating Examples for Unknown Intent Detection with Natural Language Attack
DongHyun Choi, Myeongcheol Shin, EungGyun Kim, Dong Ryeol Shin
Abstract
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 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on3
- Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and EntailmentDi Jin, Zhijing Jin, Joey Tianyi Zhou, Peter SzolovitsAAAI 2020 · 1,333 citations
- BERT-ATTACK: Adversarial Attack Against BERT Using BERTLinyang Li, Ruotian Ma, Qipeng Guo, Xiangyang Xue et al.EMNLP 2020 · 529 citations
- Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent ClassificationGuangfeng Yan, Lu Fan, Qimai Li, Han Liu et al.ACL 2020 · 69 citations
Related papers
- Towards Open Environment Intent PredictionYunhua Zhou, Jiawei Hong, Xipeng QiuACL Findings 2023 · 1 citation
- Out-of-Scope Intent Detection with Self-Supervision and Discriminative TrainingLi-Ming Zhan, Haowen Liang, Bo Liu, Lu Fan et al.ACL 2021
- Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue SystemYanan Wu, Zhiyuan Zeng, Keqing He, Hong Xu et al.ACL 2021
- APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD DetectionPei Wang, Keqing He, Yutao Mou, Xiaoshuai Song et al.EMNLP Findings 2023 · 4 citations
- Two Birds One Stone: Dynamic Ensemble for OOD Intent ClassificationYunhua Zhou, Jianqiang Yang, Pengyu Wang, Xipeng QiuACL 2023 · 5 citations
