Transition-based parser-Stack-LSTM
Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing4 results
- F1 Full· 2017-07-24SOTA63best: 78.5 (APT (IBM))
- F1 Newswire· 2017-07-24SOTA68best: 73.3 (Transition-based+improved aligner+ensemble)
- F1 Full· 2017-07-24SOTA63best: 78.5 (APT (IBM))
- F1 Newswire· 2017-07-24SOTA68best: 73.3 (Transition-based+improved aligner+ensemble)