Study the paper
Attention Is All You Need
Lessons, visuals, quizzes, flashcards, and resources—organized in teaching order.
Empirical Performance and Generalization
F1 scores on English constituency parsing
F1 scores on English constituency parsing
The Transformer generalizes well to English constituency parsing, achieving competitive F1 scores on Section 23 of WSJ under both discriminative (WSJ only) and semi-supervised training setups.
Sources
S6.T4
Table 4: The Transformer generalizes well to English constituency parsing (Results are on Section 23 of WSJ) Parser Training WSJ 23 F1 Vinyals & Kaiser el al. (2014) [37] WSJ only, discriminative 88.3 Petrov et al. (2006) [29] WSJ only, discriminative 90.4 Zhu et al. (2013) [40] WSJ only, discriminative 90.4 Dyer et al. (2016) [8] WSJ only, discriminative 91.7 Transformer (4 layers) WSJ only, discriminative 91.3 Zhu et al. (2013) [40] semi-supervised 91.3 Huang & Harper (2009) [14] semi-supervised 91.3 McClosky et al. (2006) [26] semi-supervised 92.1 Vinyals & Kaiser el al. (2014) [37] semi-supervised 92.1 Transformer (4 layers) semi-supervised 92.7 Luong et al. (2015) [23] multi-task 93.0 Dyer et al. (2016) [8] generative 93.3
| Measure | Value |
|---|---|
| Transformer (4 layers) WSJ only, discriminative F1 | 91.3 F1 |
| Transformer (4 layers) semi-supervised F1 | 92.7 F1 |
Sources
S6.T4
Table 4: The Transformer generalizes well to English constituency parsing (Results are on Section 23 of WSJ) Parser Training WSJ 23 F1 Vinyals & Kaiser el al. (2014) [37] WSJ only, discriminative 88.3 Petrov et al. (2006) [29] WSJ only, discriminative 90.4 Zhu et al. (2013) [40] WSJ only, discriminative 90.4 Dyer et al. (2016) [8] WSJ only, discriminative 91.7 Transformer (4 layers) WSJ only, discriminative 91.3 Zhu et al. (2013) [40] semi-supervised 91.3 Huang & Harper (2009) [14] semi-supervised 91.3 McClosky et al. (2006) [26] semi-supervised 92.1 Vinyals & Kaiser el al. (2014) [37] semi-supervised 92.1 Transformer (4 layers) semi-supervised 92.7 Luong et al. (2015) [23] multi-task 93.0 Dyer et al. (2016) [8] generative 93.3