Kuaishou Tech
Nov 16, 2021 · Artificial Intelligence
KuaiSearch's PERKS Pre‑trained Language Model Sets New Record on the CLUE Benchmark
The KuaiSearch research team introduced PERKS, a large‑scale Chinese pre‑trained language model that achieved an 80.618 score on the CLUE 1.1 language classification task, narrowing the gap to human annotation and demonstrating significant advances in multi‑stage training, model optimization, and real‑world search applications.
CLUE benchmarkKuaiSearchNLP
0 likes · 7 min read