UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning

Yutao Mou, Pei Wang, Keqing He, Yanan Wu, Jingang Wang, Wei Wu, Weiran Xu


Abstract
Detecting out-of-domain (OOD) intents from user queries is essential for avoiding wrong operations in task-oriented dialogue systems. The key challenge is how to distinguish in-domain (IND) and OOD intents. Previous methods ignore the alignment between representation learning and scoring function, limiting the OOD detection performance. In this paper, we propose a unified neighborhood learning framework (UniNL) to detect OOD intents. Specifically, we design a KNCL objective for representation learning, and introduce a KNN-based scoring function for OOD detection. We aim to align representation learning with scoring function. Experiments and analysis on two benchmark datasets show the effectiveness of our method.
Anthology ID:
2022.emnlp-main.494
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:
7317–7325
Language:
URL:
https://aclanthology.org/2022.emnlp-main.494
DOI:
10.18653/v1/2022.emnlp-main.494
Bibkey:
Cite (ACL):
Yutao Mou, Pei Wang, Keqing He, Yanan Wu, Jingang Wang, Wei Wu, and Weiran Xu. 2022. UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7317–7325, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning (Mou et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.494.pdf