A Diffusion Weighted Graph Framework for New Intent Discovery

Wenkai Shi, Wenbin An, Feng Tian, Qinghua Zheng, QianYing Wang, Ping Chen


Abstract
New Intent Discovery (NID) aims to recognize both new and known intents from unlabeled data with the aid of limited labeled data containing only known intents. Without considering structure relationships between samples, previous methods generate noisy supervisory signals which cannot strike a balance between quantity and quality, hindering the formation of new intent clusters and effective transfer of the pre-training knowledge. To mitigate this limitation, we propose a novel Diffusion Weighted Graph Framework (DWGF) to capture both semantic similarities and structure relationships inherent in data, enabling more sufficient and reliable supervisory signals. Specifically, for each sample, we diffuse neighborhood relationships along semantic paths guided by the nearest neighbors for multiple hops to characterize its local structure discriminately. Then, we sample its positive keys and weigh them based on semantic similarities and local structures for contrastive learning. During inference, we further propose Graph Smoothing Filter (GSF) to explicitly utilize the structure relationships to filter high-frequency noise embodied in semantically ambiguous samples on the cluster boundary. Extensive experiments show that our method outperforms state-of-the-art models on all evaluation metrics across multiple benchmark datasets. Code and data will be made public.
Anthology ID:
2023.emnlp-main.499
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8033–8042
Language:
URL:
https://aclanthology.org/2023.emnlp-main.499
DOI:
10.18653/v1/2023.emnlp-main.499
Bibkey:
Cite (ACL):
Wenkai Shi, Wenbin An, Feng Tian, Qinghua Zheng, QianYing Wang, and Ping Chen. 2023. A Diffusion Weighted Graph Framework for New Intent Discovery. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8033–8042, Singapore. Association for Computational Linguistics.
Cite (Informal):
A Diffusion Weighted Graph Framework for New Intent Discovery (Shi et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.499.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.499.mp4