ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection

Iftitahu Nimah, Meng Fang, Vlado Menkovski, Mykola Pechenizkiy


Abstract
The ability to detect Out-of-Domain (OOD) inputs has been a critical requirement in many real-world NLP applications. For example, intent classification in dialogue systems. The reason is that the inclusion of unsupported OOD inputs may lead to catastrophic failure of systems. However, it remains an empirical question whether current methods can tackle such problems reliably in a realistic scenario where zero OOD training data is available. In this study, we propose ProtoInfoMax, a new architecture that extends Prototypical Networks to simultaneously process in-domain and OOD sentences via Mutual Information Maximization (InfoMax) objective. Experimental results show that our proposed method can substantially improve performance up to 20% for OOD detection in low resource settings of text classification. We also show that ProtoInfoMax is less prone to typical overconfidence errors of Neural Networks, leading to more reliable prediction results.
Anthology ID:
2021.findings-emnlp.138
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1606–1617
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.138
DOI:
10.18653/v1/2021.findings-emnlp.138
Bibkey:
Cite (ACL):
Iftitahu Nimah, Meng Fang, Vlado Menkovski, and Mykola Pechenizkiy. 2021. ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1606–1617, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection (Nimah et al., Findings 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2021.findings-emnlp.138.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-4/2021.findings-emnlp.138.mp4
Code
 inimah/protoinfomax
Data
Amazon Product DataCLINC150