Xin Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xin Wang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Fei Long
Tsinghua University, Beijing, China
1 shared publication - Hanlei Zhang
State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China
1 shared publication - Hua Xu
Tsinghua University, Beijing, China
1 shared publication - Kai Gao
School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, Hebei, China
1 shared publication
Latest Publications
- 8 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (11) , 5468-5481
A Clustering Framework for Unsupervised and Semi-Supervised New Intent Discovery
New intent discovery is of great value to natural language processing, allowing for a better understanding of user needs and providing friendly services. However, most existing methods struggle to capture the complicated semantics of discrete text representations when limited or no prior knowledge of labeled data is available. To tackle this problem, we propose a novel clustering framework, USNID, for u nsupervised and s emi-supervised n ew i ntent d iscovery, which has three key technologies. First, it fully utilizes of unsupervised or semi-supervised data to mine shallow semantic similarity relations and provide well-initialized representations for clustering. Second, it designs a centroid-guided clustering mechanism to address the issue of cluster allocation inconsistency and provide high-quality self-supervised targets for representation learning. Third, it captures high-level semantics in unsupervised or semi-supervised data to discover fine-grained intent-wise clusters by optimizing both cluster-level and instance-level objectives. We also propose an effective method for estimating the cluster number in open-world scenarios without knowing the number of new intents beforehand. USNID performs exceptionally well on several benchmark intent datasets, achieving new state-of-the-art results in unsupervised and semi-supervised new intent discovery, and demonstrating robust performance with different cluster numbers.
- 8 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (11) , 5468-5481
A Clustering Framework for Unsupervised and Semi-Supervised New Intent Discovery
New intent discovery is of great value to natural language processing, allowing for a better understanding of user needs and providing friendly services. However, most existing methods struggle to capture the complicated semantics of discrete text representations when limited or no prior knowledge of labeled data is available. To tackle this problem, we propose a novel clustering framework, USNID, for u nsupervised and s emi-supervised n ew i ntent d iscovery, which has three key technologies. First, it fully utilizes of unsupervised or semi-supervised data to mine shallow semantic similarity relations and provide well-initialized representations for clustering. Second, it designs a centroid-guided clustering mechanism to address the issue of cluster allocation inconsistency and provide high-quality self-supervised targets for representation learning. Third, it captures high-level semantics in unsupervised or semi-supervised data to discover fine-grained intent-wise clusters by optimizing both cluster-level and instance-level objectives. We also propose an effective method for estimating the cluster number in open-world scenarios without knowing the number of new intents beforehand. USNID performs exceptionally well on several benchmark intent datasets, achieving new state-of-the-art results in unsupervised and semi-supervised new intent discovery, and demonstrating robust performance with different cluster numbers.