List your company
ResearchFormerly WizWand

Joint Word Segmentation and POS Tagging on Chinese (test)

84.5F1 ScoreViterbi
45.81255.85665.975.944May 31, 2025
Updated 8mo ago

Evaluation results

MethodLinks
ViterbiEncoder layers=2 layers, Training approach=BCRF training2025.0584.5
ViterbiEncoder layers=2 layers, Training approach=CRF training2025.0584.3
ViterbiEncoder layers=4 layers, Training approach=CRF training2025.0584.3
ViterbiEncoder layers=No self-attentive encoder, Training approach=CRF training2025.0584.2
BCRFEncoder layers=2 layers, Training approach=BCRF training, Iterations=102025.0584.2
ViterbiEncoder layers=4 layers, Training approach=BCRF training2025.0584
BCRFEncoder layers=4 layers, Training approach=CRF training, Iterations=102025.0583.8
BCRFEncoder layers=4 layers, Training approach=BCRF training, Iterations=102025.0583.8
BCRFEncoder layers=No self-attentive encoder, Training approach=CRF training, Iterations=102025.0583.7
BCRFEncoder layers=2 layers, Training approach=CRF training, Iterations=102025.0583.7
ViterbiEncoder layers=No self-attentive encoder, Training approach=BCRF training2025.0583.6
BCRFEncoder layers=2 layers, Training approach=BCRF training, Iterations=52025.0583.3
BCRFEncoder layers=No self-attentive encoder, Training approach=BCRF training, Iterations=102025.0583.2
BCRFEncoder layers=4 layers, Training approach=BCRF training, Iterations=52025.0582.8
BCRFEncoder layers=No self-attentive encoder, Training approach=BCRF training, Iterations=52025.0582.2
BCRFEncoder layers=4 layers, Training approach=CRF training, Iterations=52025.0582
MFEncoder layers=No self-attentive encoder, Training approach=MF training, Iterations=102025.0582
BCRFEncoder layers=No self-attentive encoder, Training approach=CRF training, Iterations=52025.0581.9
BCRFEncoder layers=2 layers, Training approach=CRF training, Iterations=52025.0581.7
MFEncoder layers=2 layers, Training approach=MF training, Iterations=102025.0581.2
MFEncoder layers=4 layers, Training approach=MF training, Iterations=102025.0581.2
ViterbiEncoder layers=4 layers, Training approach=MF training2025.0581.1
MFEncoder layers=No self-attentive encoder, Training approach=MF training, Iterations=52025.0581
MFEncoder layers=4 layers, Training approach=MF training, Iterations=52025.0580.8
MFEncoder layers=2 layers, Training approach=MF training, Iterations=52025.0580.7
ViterbiEncoder layers=2 layers, Training approach=MF training2025.0579.9
ViterbiEncoder layers=No self-attentive encoder, Training approach=MF training2025.0577.6
MFEncoder layers=No self-attentive encoder, Training approach=CRF training, Iterations=102025.0574.6
MFEncoder layers=No self-attentive encoder, Training approach=CRF training, Iterations=52025.0572.9
MFEncoder layers=4 layers, Training approach=CRF training, Iterations=102025.0572.5
MFEncoder layers=2 layers, Training approach=CRF training, Iterations=102025.0572.2
MFEncoder layers=4 layers, Training approach=CRF training, Iterations=52025.0571.9
MFEncoder layers=2 layers, Training approach=CRF training, Iterations=52025.0571.4
UnstructuredEncoder layers=4 layers2025.0564.9
UnstructuredEncoder layers=2 layers2025.0562
UnstructuredEncoder layers=No self-attentive encoder2025.0547.3