short text clustering

Baidu Geek Talk

Apr 16, 2021 · Artificial Intelligence

Large-Scale Short Text Clustering System Design and Practice at Baidu Search

At Baidu Search, a large‑scale short‑text clustering system was built using multi‑level semantic splitting, fine‑grained aggregation and error‑correction, evolving from v1.0 to v2.0, and now clusters 100 million queries with 95 % accuracy and 80 % recall within three days.