Xin Wang

Xin Wang

Auto-generated profile, based on publicly available information

Xin Wang

State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 December 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
HZHanlei Zhang
Hanlei Zhang
HXHua Xu
Hua Xu
XWXin Wang
Xin Wang
FLFei Long
Fei Long
KGKai Gao
Kai Gao
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.