Bi-LSTM seq2seq: BERT + characters in 1 encoder
Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing2 results
- F1· 2020-11-09SOTA88.3
- F1· 2020-11-09SOTA89.3