Word Sense Disambiguation On Supervised
評価指標
SemEval 2007
SemEval 2013
SemEval 2015
Senseval 2
Senseval 3
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
モデル名 | SemEval 2007 | SemEval 2013 | SemEval 2015 | Senseval 2 | Senseval 3 |
---|---|---|---|---|---|
モデル 1 | 63.1 | 66.8 | 71.8 | 72.7 | 70.6 |
improved-word-sense-disambiguation-using-pre | 63.3 | 69.2 | 74.4 | 73.8 | 71.6 |
モデル 3 | 61.3 | 65.6 | 71.9 | 71.8 | 69.1 |
incorporating-glosses-into-neural-word-sense | --* | 67.2 | 72.6 | 72.2 | 70.5 |
improving-the-coverage-and-the-generalization | 66.81 | 72.63 | 74.46 | 75.15 | 70.11 |
sandwich-semantical-analysis-of-neighbours | 80.9 | 92.6 | 91.5 | 87.8 | 85.7 |
sparsity-makes-sense-word-sense | 73.0 | 79.4 | 81.3 | 79.6 | 77.3 |
deep-contextualized-word-representations | 62.2 | 66.2 | 71.3 | 71.6 | 69.6 |
neural-sequence-learning-models-for-word | 63.7* | 66.4 | 72.4 | 72.0 | 69.4 |
breaking-through-the-80-glass-ceiling-raising | 71.0 | 78.9 | 79.3 | 78.9 | 78.4 |
consec-word-sense-disambiguation-as | 77.4 | 83.2 | 85.2 | 82.3 | 79.9 |
incorporating-glosses-into-neural-word-sense | --* | 66.7 | 71.6 | 72.0 | 70.0 |
neural-sequence-learning-models-for-word | 64.8* | 66.9 | 71.5 | 72.0 | 69.1 |
improved-word-sense-disambiguation-using-pre | 68.1 | 71.1 | 76.2 | 75.5 | 73.6 |
with-more-contexts-comes-better-performance | 71.0 | 77.3 | 83.2 | 78.0 | 77.1 |
モデル 16 | 60.2 | 65.8 | 70.0 | 71.3 | 68.8 |
improved-word-sense-disambiguation-with | 77.0 | 81.5 | 84.1 | 81.3 | 79.9 |
improved-word-sense-disambiguation-with | 78.5 | 82.3 | 85.3 | 82.5 | 80.2 |
モデル 19 | 54.5 | 63.8 | 67.1 | 65.6 | 66.0 |
esc-redesigning-wsd-with-extractive-sense | 76.3 | 82.2 | 83.2 | 81.7 | 77.8 |
moving-down-the-long-tail-of-word-sense-1 | 74.5 | 79.7 | 81.7 | 79.4 | 77.4 |
consec-word-sense-disambiguation-as | 78.5 | 85.2 | 87.5 | 82.7 | 81.0 |
sense-vocabulary-compression-through-the | 73.4 | 78.7 | 82.6 | 79.7 | 77.8 |
glossbert-bert-for-word-sense-disambiguation | 72.5 | 76.1 | 80.4 | 77.7 | 75.2 |
breaking-through-the-80-glass-ceiling-raising | 75.2 | 80.7 | 81.8 | 80.8 | 79.0 |
sparsity-makes-sense-word-sense | 68.8 | 76.1 | 77.5 | 77.9 | 77.8 |