ZEN (Init with Chinese BERT)

Reported on 2 benchmarks across 2 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

ChineseonMSR
F1· 2019-11-02
98.35
best: 98.63 (BABERT-LE)
SOTA
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations arXiv:1911.00720
Named Entity Recognition (NER)onMSRA
F1· 2019-11-02
95.25
best: 96.72 (BERT-MRC+DSC)
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations arXiv:1911.00720