To Swap or Not to Swap? Exploiting Dependency Word Pairs for Reordering in Statistical Machine Translation
This work addresses reordering problems in statistical machine translation for languages like Chinese and English, offering an incremental improvement over prior methods.
The paper tackled the challenge of reordering in machine translation between languages with different word orders by using sparse features based on dependency word pairs, resulting in a statistically significant improvement of 1.21 BLEU points in Chinese-to-English translation compared to a state-of-the-art system.
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.