Label Attention Layer + HPSG + XLNet

Reported on 4 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Natural Language Processing4 results

Dependency ParsingonPenn Treebank
LAS· 2019-11-10
96.26
SOTA
Rethinking Self-Attention: Towards Interpretability in Neural Parsing arXiv:1911.03875
Dependency ParsingonPenn Treebank
UAS· 2019-11-10
97.42
SOTA
Rethinking Self-Attention: Towards Interpretability in Neural Parsing arXiv:1911.03875
Constituency ParsingonPenn Treebank
F1 score· 2019-11-10
96.38
best: 96.43 (Hashing + XLNet)
SOTA
Rethinking Self-Attention: Towards Interpretability in Neural Parsing arXiv:1911.03875
Dependency ParsingonPenn Treebank
POS· 2019-11-10
97.3
best: 97.97 (jPTDP)
Rethinking Self-Attention: Towards Interpretability in Neural Parsing arXiv:1911.03875