Doubling the number of words (N = 64) produces a small gain, and defining the pairwise dominance model using N = 128 most frequent words produces a statistically significant 1-point gain over the baseline (p < 0.01).

Larger values of N yield statistically significant performance above the baseline, but without further improvements over N = 128.

Statistically significant results (p < 0.01) over the baseline are in bold.

all experiments, we report performance using the BLEU score (Papineni et al., 2002), and we assess statistical significance using the standard bootstrapping approach introduced by (Koehn, 2004).

We show that it achieves a statistically significantly higher BLEU score than the baseline system without these features.

In comparison to a baseline model, we achieve statistically significant improvement in BLEU score.

The improvement in BLEU is statistically significant (p < 0.01) using the paired bootstrap resampling significance test (Koehn, 2004).

(2007) and the model that only takes syntactic-based asymmetries into account is not statistically significant, while the difference between Model 1 and this model is statistically significant (p < 0.05).

However, the difference between the multiplicative model and the noun model is not statistically significant in this case.

The difference is statistically significant at p < 0.05.

Although neither difference is statistically significant , this clearly shows a pattern different from the attribute-specifying adjectives.

They compared the composition models to human similarity ratings and found that all models were statistically significantly correlated with human judgements.

Statistically significant improvements were realized on Dutch, French, and German.

The only case where it had no statistically significant effect was on English.

From this perspective, to achieve statistically significant improvements on five of six L2P datasets (without ever being beaten by random) is an excellent result for QBB.