Are Pre-trained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection

Jianguo Zhang, Kazuma Hashimoto, Yao Wan, Zhiwei Liu, Ye Liu, Caiming Xiong, Philip Yu


Abstract
Pre-trained Transformer-based models were reported to be robust in intent classification. In this work, we first point out the importance of in-domain out-of-scope detection in few-shot intent recognition tasks and then illustrate the vulnerability of pre-trained Transformer-based models against samples that are in-domain but out-of-scope (ID-OOS). We construct two new datasets, and empirically show that pre-trained models do not perform well on both ID-OOS examples and general out-of-scope examples, especially on fine-grained few-shot intent detection tasks.
Anthology ID:
2022.nlp4convai-1.2
Volume:
Proceedings of the 4th Workshop on NLP for Conversational AI
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Bing Liu, Alexandros Papangelis, Stefan Ultes, Abhinav Rastogi, Yun-Nung Chen, Georgios Spithourakis, Elnaz Nouri, Weiyan Shi
Venue:
NLP4ConvAI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12–20
Language:
URL:
https://aclanthology.org/2022.nlp4convai-1.2
DOI:
10.18653/v1/2022.nlp4convai-1.2
Bibkey:
Cite (ACL):
Jianguo Zhang, Kazuma Hashimoto, Yao Wan, Zhiwei Liu, Ye Liu, Caiming Xiong, and Philip Yu. 2022. Are Pre-trained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection. In Proceedings of the 4th Workshop on NLP for Conversational AI, pages 12–20, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Are Pre-trained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection (Zhang et al., NLP4ConvAI 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.nlp4convai-1.2.pdf
Data
BANKING77