ML Anthology

Constrained Self-Supervised Clustering for Discovering New Intents (Student Abstract)

Ting-En Lin, Hua Xu, Hanlei Zhang
AAAI 2020 pp. 13863-13864
doi:10.1609/AAAI.V34I10.7204 /aaai/2020/lin2020aaai-constrained/

Abstract

Discovering new user intents is an emerging task in the dialogue system. In this paper, we propose a self-supervised clustering method that can naturally incorporate pairwise constraints as prior knowledge to guide the clustering process and does not require intensive feature engineering. Extensive experiments on three benchmark datasets show that our method can yield significant improvements over strong baselines.

PDF AAAI Semantic Scholar

Cite

Text

Lin et al. "Constrained Self-Supervised Clustering for Discovering New Intents (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7204

Markdown

[Lin et al. "Constrained Self-Supervised Clustering for Discovering New Intents (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/lin2020aaai-constrained/) doi:10.1609/AAAI.V34I10.7204

BibTeX

@inproceedings{lin2020aaai-constrained,
  title     = {{Constrained Self-Supervised Clustering for Discovering New Intents (Student Abstract)}},
  author    = {Lin, Ting-En and Xu, Hua and Zhang, Hanlei},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13863-13864},
  doi       = {10.1609/AAAI.V34I10.7204},
  url       = {https://mlanthology.org/aaai/2020/lin2020aaai-constrained/}
}