CVT + Multi-Task

Reported on 3 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 Processing3 results

Named Entity Recognition (NER)onCoNLL 2003 (English)
F1· uses extra data· 2018-09-22
92.61
best: 94.6 (ACE + document-context)
SOTA
Semi-Supervised Sequence Modeling with Cross-View Training arXiv:1809.08370
Dependency ParsingonPenn Treebank
LAS· 2018-09-22
95.02
best: 96.26 (Label Attention Layer + HPSG + XLNet)
Semi-Supervised Sequence Modeling with Cross-View Training arXiv:1809.08370
Dependency ParsingonPenn Treebank
UAS· 2018-09-22
96.61
best: 97.42 (Label Attention Layer + HPSG + XLNet)
Semi-Supervised Sequence Modeling with Cross-View Training arXiv:1809.08370