BIST graph-based parser

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· 2016-03-14
91
best: 96.26 (Label Attention Layer + HPSG + XLNet)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations arXiv:1603.04351
Dependency ParsingonPenn Treebank
POS· 2016-03-14
97.3
best: 97.97 (jPTDP)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations arXiv:1603.04351
Dependency ParsingonPenn Treebank
UAS· 2016-03-14
93.1
best: 97.42 (Label Attention Layer + HPSG + XLNet)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations arXiv:1603.04351