A Dependency-Based Neural Reordering Model for Statistical Machine Translation
This work addresses word order issues in machine translation for languages like Chinese and English, representing an incremental improvement over existing dependency-based methods.
The paper tackles the challenge of word order in machine translation between languages with different structures by using a neural network with dependency-based embeddings to predict reordering. It achieves a statistically significant improvement of 0.57 BLEU points on Chinese-to-English translation compared to a prior state-of-the-art system.
In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge. The dependency parse tree of a source sentence can help to determine the correct word order of the translated words. In this paper, we present a novel reordering approach utilizing a neural network and dependency-based embeddings to predict whether the translations of two source words linked by a dependency relation should remain in the same order or should be swapped in the translated sentence. Experiments on Chinese-to-English translation show that our approach yields a statistically significant improvement of 0.57 BLEU point on benchmark NIST test sets, compared to our prior state-of-the-art statistical MT system that uses sparse dependency-based reordering features.