S-LSTM

Reported on 4 benchmarks across 3 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· 2018-05-07
97.55
best: 98.15 (SALE-BART encoder)
Sentence-State LSTM for Text Representation arXiv:1805.02474
Sentiment AnalysisonMR
Accuracy· 2018-05-07
76.2
best: 93.3 (VLAWE)
Sentence-State LSTM for Text Representation arXiv:1805.02474
Sentiment AnalysisonIMDb
Accuracy· uses extra data· 2018-05-07
87.15
best: 96.68 (RoBERTa-large with LlamBERT)
Sentence-State LSTM for Text Representation arXiv:1805.02474
Named Entity Recognition (NER)onCoNLL 2003 (English)
F1· 2018-05-07
91.57
best: 94.6 (ACE + document-context)
Sentence-State LSTM for Text Representation arXiv:1805.02474