Dependency Parsing on CoNLL 2009 (test)
91.86UASEnsemble MST Parser
Evaluation results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Ensemble MST ParserParsing Approach=Transition (greedy), Pretrained word embeddings=true, Ensemble Size=202016.09 | 91.86 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 89.98 | |
| Neural FOG, CD (distilled)Parsing Approach=Graph (1st order), Pretrained word embeddings=true, Distilled=true2016.09 | 91.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 89.24 | |
| Bohnet and Nivre (2012)Parsing Approach=Transition (beam), Pretrained word embeddings=false2016.09 | 91.37 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 89.38 | |
| Neural FOG, CHParsing Approach=Graph (1st order), Pretrained word embeddings=true2016.09 | 91.22 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 88.82 | |
| Andor et al. (2016)Parsing Approach=Transition (beam), Pretrained word embeddings=true2016.09 | 90.91 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 89.15 | |
| CRF2OMBR decoding=true2020.05 | 89.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86.52 | |
| Yazdani and Henderson (2015)Parsing Approach=Transition (beam), Pretrained word embeddings=false2016.09 | 89.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86 | |
| CRF2OMBR decoding=false2020.05 | 89.49 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86.39 | |
| CRFMBR decoding=true2020.05 | 89.28 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86.18 | |
| Loc2020.05 | 89.15 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 85.98 | |
| CRFMBR decoding=false2020.05 | 89.14 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86.06 | |
| Biaffine172020.05 | 88.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 85.38 | |
| Ballesteros et al. (2015)Parsing Approach=Transition (greedy), Pretrained word embeddings=false2016.09 | 88.83 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86.1 | |
| Li192020.05 | 88.77 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 85.58 | |
| Alberti et al. (2015)2016.03 | — | 92.31 | 89.17 | 83.57 | 79.9 | 88.45 | 83.57 | 92.7 | 90.56 | 90.58 | 88.2 | 93.99 | 93.1 | 92.26 | 89.33 | — | |
| Ballesteros et al. (2015)2016.03 | — | 90.22 | 86.42 | 80.64 | 76.52 | 79.87 | 73.62 | 90.56 | 88.01 | 88.83 | 86.1 | 93.47 | 92.55 | 90.38 | 86.59 | — | |
| Best Shared Task Result2016.03 | — | 87.86 | — | 79.17 | — | 80.38 | — | 89.88 | — | 87.48 | — | 92.57 | — | 87.64 | — | — | |
| Bohnet and Nivre (2012)2016.03 | — | 92.44 | 89.6 | 82.52 | 78.51 | 88.82 | 83.73 | 92.87 | 90.6 | 91.37 | 89.38 | 93.67 | 92.63 | 92.24 | 89.6 | — | |
| Lei et al. (2014)2016.03 | — | 91.33 | 87.22 | 81.67 | 76.71 | 88.76 | 81.77 | 92.75 | 90 | 90.81 | 87.81 | 94.04 | 91.84 | 91.16 | 87.38 | — | |
| Our GlobalNormalization strategy=Global, Beam size=162016.03 | — | 92.67 | 89.83 | 84.72 | 80.85 | 88.94 | 84.56 | 93.22 | 91.23 | 90.91 | 89.15 | 93.65 | 92.84 | 92.62 | 89.95 | — | |
| Our LocalNormalization strategy=Local, Beam size=12016.03 | — | 91.24 | 88.21 | 81.29 | 77.29 | 85.78 | 80.63 | 91.44 | 89.29 | 89.12 | 86.95 | 93.71 | 92.85 | 91.01 | 88.14 | — | |
| Our LocalNormalization strategy=Local, Beam size=162016.03 | — | 91.91 | 88.93 | 82.22 | 78.26 | 86.25 | 81.28 | 92.16 | 90.05 | 89.53 | 87.4 | 93.61 | 92.74 | 91.64 | 88.88 | — | |
| Zhang and McDonald (2014)2016.03 | — | 91.41 | 87.91 | 82.87 | 78.57 | 86.62 | 80.59 | 92.69 | 90.01 | 89.88 | 87.38 | 92.82 | 91.87 | 90.82 | 87.34 | — |