Publication at Faculty of Mathematics and Physics |
2016
Abstract
We propose two contributions to discriminative rule selection in hierarchical machine translation. First, we test previous approaches on two French-English translation tasks in domains for which only limited resources are available and show that they fail to improve translation quality.
To improve on such tasks, we propose a rule selection model that is (i) global with rich label-dependent features (ii) trained with all available negative samples. Our global model yields significant improvements, up to 1 BLEU point, over previously proposed rule selection models.