List your company

Chinese Word Segmentation on PKU (test)

97.16F1ChineseBERT
77.649682.714887.7892.8452Jun 30, 2021Feb 22, 2022Oct 18, 2022Jun 13, 2023Feb 5, 2024Sep 30, 2024May 26, 2025

Evaluation results

MethodLinks
ChineseBERTModel size=Large, Pre-trained on extended data=false2021.0697.1698.01
ChineseBERTModel size=Base, Pre-trained on extended data=false2021.0697.0297.81
RoBERTaModel size=Large, Pre-trained on extended data=true2021.0696.9597.8
RoBERTaModel size=Base, Pre-trained on extended data=true2021.0696.8897.72
BABERT-LECategory=Supervised Lexicon Enhanced Model, External Knowledge=Yes2022.1096.84—
BERTModel size=Base, Pre-trained on extended data=true2021.0696.8297.7
BABERTCategory=Pre-Trained Language Model2022.1096.7—
BERT-LECategory=Supervised Lexicon Enhanced Model, External Knowledge=Yes, Reproduced=Yes2022.1096.7—
NEZHACategory=Pre-Trained Language Model2022.1096.67—
ZENCategory=Pre-Trained Language Model2022.1096.55—
MEM-ZENCategory=Supervised Lexicon Enhanced Model, External Knowledge=Yes2022.1096.53—
BERT-wwmCategory=Pre-Trained Language Model2022.1096.51—
MEM-BERTCategory=Supervised Lexicon Enhanced Model, External Knowledge=Yes2022.1096.51—
ERNIE-GramCategory=Pre-Trained Language Model2022.1096.36—
ERNIECategory=Pre-Trained Language Model2022.1096.3—
BERTCategory=Pre-Trained Language Model2022.1096.26—
LatticeCategory=Supervised Lexicon Enhanced Model, External Knowledge=Yes2022.1095.8—
LLACABackbone=Qwen1.5-14B2025.0589.3—
LLACABackbone=Qwen1.5-72B2025.0588.7—
LLACABackbone=Qwen1.5-7B2025.0587.7—
LLACABackbone=Qwen1.5-32B2025.0587.6—
UniBackbone=Qwen1.5-7B2025.0587.5—
LLM-WSBackbone=Qwen1.5-14B2025.0587—
LLM-WSBackbone=Qwen1.5-7B2025.0586.7—
LLM-WSBackbone=Qwen1.5-32B2025.0586.3—
PYHSMM2025.0581.6—
Joint2025.0581.1—
SLM-22025.0580.2—
nVBE2025.0580—
SGB-C-42025.0580—
SLM-32025.0579.8—
SGB-C-52025.0578.4—