To Swap or Not to Swap? Exploiting Dependency Word Pairs for Reordering in Statistical Machine Translation

TL;DR

This paper introduces a novel reordering method for statistical machine translation that leverages dependency word pairs to improve translation accuracy, demonstrated by significant BLEU score gains in Chinese-to-English translation.

Contribution

The paper proposes a new reordering approach using dependency word pairs as sparse features, enhancing translation quality over existing methods.

Findings

Achieved a 1.21 BLEU point improvement on Chinese-to-English translation.

Demonstrated the effectiveness of dependency-based features in reordering.

Significant statistical improvement over prior reordering approaches.

Abstract

Reordering poses a major challenge in machine translation (MT) between two languages with significant differences in word order. In this paper, we present a novel reordering approach utilizing sparse features based on dependency word pairs. Each instance of these features captures whether two words, which are related by a dependency link in the source sentence dependency parse tree, follow the same order or are swapped in the translation output. Experiments on Chinese-to-English translation show a statistically significant improvement of 1.21 BLEU point using our approach, compared to a state-of-the-art statistical MT system that incorporates prior reordering approaches.