BiLSTM-LAN

Reported on 4 benchmarks across 3 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 Processing4 results

Part-Of-Speech TaggingonUD
Avg accuracy· 2019-08-23
96.88
SOTA
Hierarchically-Refined Label Attention Network for Sequence Labeling arXiv:1908.08676
Part-Of-Speech TaggingonPenn Treebank
Accuracy· 2019-08-23
97.65
best: 98.15 (SALE-BART encoder)
Hierarchically-Refined Label Attention Network for Sequence Labeling arXiv:1908.08676
Named Entity Recognition (NER)onOntonotes v5 (English)
F1· 2019-08-23
88.16
best: 92.07 (BERT-MRC+DSC)
Hierarchically-Refined Label Attention Network for Sequence Labeling arXiv:1908.08676
CCG SupertaggingonCCGbank
Accuracy· 2019-08-23
94.7
best: 96.29 (Heterogeneous Dynamic Convolutions)
Hierarchically-Refined Label Attention Network for Sequence Labeling arXiv:1908.08676