Distilled neural FOG

Reported on 3 benchmarks across 1 task · 1 paper

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

Natural Language Processing3 results

Dependency ParsingonPenn Treebank
LAS· 2016-09-24
92.06
best: 96.26 (Label Attention Layer + HPSG + XLNet)
Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser arXiv:1609.07561
Dependency ParsingonPenn Treebank
POS· 2016-09-24
97.44
best: 97.97 (jPTDP)
Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser arXiv:1609.07561
Dependency ParsingonPenn Treebank
UAS· 2016-09-24
94.26
best: 97.42 (Label Attention Layer + HPSG + XLNet)
Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser arXiv:1609.07561