IntNet + BiLSTM-CRF

Reported on 4 benchmarks across 4 tasks · 1 paper

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

Natural Language Processing4 results

Part-Of-Speech TaggingonPenn Treebank
Accuracy· 2018-10-29
97.58
best: 98.15 (SALE-BART encoder)
Learning Better Internal Structure of Words for Sequence Labeling arXiv:1810.12443
Named Entity Recognition (NER)onCoNLL 2003 (English)
F1· 2018-10-29
91.64
best: 94.6 (ACE + document-context)
Learning Better Internal Structure of Words for Sequence Labeling arXiv:1810.12443
ChunkingonPenn Treebank
F1 score· 2018-10-29
95.29
best: 97.3 (ACE)
Learning Better Internal Structure of Words for Sequence Labeling arXiv:1810.12443
Shallow SyntaxonPenn Treebank
F1 score· 2018-10-29
95.29
best: 97.3 (ACE)
Learning Better Internal Structure of Words for Sequence Labeling arXiv:1810.12443