Adversarial Bi-LSTM

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

Part-Of-Speech TaggingonUD
Avg accuracy· 2017-11-14
96.65
best: 96.88 (BiLSTM-LAN)
SOTA
Robust Multilingual Part-of-Speech Tagging via Adversarial Training arXiv:1711.04903
Part-Of-Speech TaggingonPenn Treebank
Accuracy· 2017-11-14
97.59
best: 98.15 (SALE-BART encoder)
Robust Multilingual Part-of-Speech Tagging via Adversarial Training arXiv:1711.04903
Named Entity Recognition (NER)onCoNLL 2003 (English)
F1· 2017-11-14
91.56
best: 94.6 (ACE + document-context)
Robust Multilingual Part-of-Speech Tagging via Adversarial Training arXiv:1711.04903