Neural machine translation (NMT) aims at solving machine translation (MT) problems using neural networks and has exhibited promising results in recent years. However, most of the existing NMT models are shallow and there is still a performance gap between a single NMT model and the best conventional MT system. In this work, we introduce a new type of linear connections, named fastforward connec...

The gold standard for measuring machine translation quality is the rating of candidate sentences by by experienced translators. However, automated measures are necessary for rapid iterative development. BLEU (Papineni et al. 2002) is the best-known automatic measure of translation quality. BLEU and related measures are used to automatically evaluate machine translation (MT) systems, as well as ...

BLEU is the de facto standard machine translation (MT) evaluation metric. However, because BLEU computes a geometric mean of n-gram precisions, it often correlates poorly with human judgment on the sentence-level. Therefore, several smoothing techniques have been proposed. This paper systematically compares 7 smoothing techniques for sentence-level BLEU. Three of them are first proposed in this...

This paper describes a new method to compare reordering constraints for Statistical Machine Translation. We investigate the best possible (oracle) BLEU score achievable under different reordering constraints. Using dynamic programming, we efficiently find a reordering that approximates the highest attainable BLEU score given a reference and a set of reordering constraints. We present an empiric...

We show that, consistent with MEANTtuned systems that translate into Chinese, MEANT-tuned MT systems that translate into English also outperforms BLEUtuned systems across commonly used MT evaluation metrics, even in BLEU. The result is achieved by significantly improving MEANT’s sentence-level ranking correlation with human preferences through incorporating a more accurate distributional semant...

We have applied BLEU (Papineni et al., 2001), a method originally designed to evaluate automatic Machine Translation systems, in assessing short essays written by students. We study how much BLEU scores correlate to human scorings and other keyword-based evaluation metrics. We conclude that, although it is only applicable to a restricted category of questions, BLEU attains better results than o...

Long-distance reordering remains one of the biggest challenges facing machine translation. We derive soft constraints from the source dependency parsing to directly address the reordering problem for the hierarchical phrasebased model. Our approach significantly improves Chinese–English machine translation on a large-scale task by 0.84 BLEU points on average. Moreover, when we switch the tuning...

We have evaluated the two-stage machine translation (MT) system. The first stage is a state-of-the-art trial rule-based machine translation system. The second stage is a normal statistical machine translation system. For Japanese-English machine translation, first, we used a Japanese-English rule-based MT, and we obtained "ENGLISH" sentences from Japanese sentences. Second, we used a standard s...