Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning

Yutao Mou; Keqing He; Yanan Wu; Zhiyuan Zeng; Hong Xu; Huixing Jiang; Wei Wu; Weiran Xu

ACL 2022short23 citations

Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning

Yutao Mou, Keqing He, Yanan Wu, Zhiyuan Zeng, Hong Xu, Huixing Jiang, Wei Wu, Weiran Xu

Abstract

Discovering Out-of-Domain(OOD) intents is essential for developing new skills in a task-oriented dialogue system. The key challenge is how to transfer prior IND knowledge to OOD clustering. Different from existing work based on shared intent representation, we propose a novel disentangled knowledge transfer method via a unified multi-head contrastive learning framework. We aim to bridge the gap between IND pre-training and OOD clustering. Experiments and analysis on two benchmark datasets show the effectiveness of our method.

BibTeX

@inproceedings{mou-etal-2022-disentangled,
    title = "Disentangled Knowledge Transfer for {OOD} Intent Discovery with Unified Contrastive Learning",
    author = "Mou, Yutao  and
      He, Keqing  and
      Wu, Yanan  and
      Zeng, Zhiyuan  and
      Xu, Hong  and
      Jiang, Huixing  and
      Wu, Wei  and
      Xu, Weiran",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-short.6/",
    doi = "10.18653/v1/2022.acl-short.6",
    pages = "46--53"
}