Estimating Soft Labels for Out-of-Domain Intent Detection

Hao Lang, Yinhe Zheng, Jian Sun, Fei Huang, Luo Si, Yongbin Li


Abstract
Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD samples and directly assigning one-hot OOD labels to these pseudo samples. However, these one-hot labels introduce noises to the training process because some “hard” pseudo OOD samples may coincide with In-Domain (IND) intents. In this paper, we propose an adaptive soft pseudo labeling (ASoul) method that can estimate soft labels for pseudo OOD samples when training OOD detectors. Semantic connections between pseudo OOD samples and IND intents are captured using an embedding graph. A co-training framework is further introduced to produce resulting soft labels following the smoothness assumption, i.e., close samples are likely to have similar labels. Extensive experiments on three benchmark datasets show that ASoul consistently improves the OOD detection performance and outperforms various competitive baselines.
Anthology ID:
2022.emnlp-main.18
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
261–276
Language:
URL:
https://aclanthology.org/2022.emnlp-main.18
DOI:
10.18653/v1/2022.emnlp-main.18
Bibkey:
Cite (ACL):
Hao Lang, Yinhe Zheng, Jian Sun, Fei Huang, Luo Si, and Yongbin Li. 2022. Estimating Soft Labels for Out-of-Domain Intent Detection. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 261–276, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Estimating Soft Labels for Out-of-Domain Intent Detection (Lang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.18.pdf