Recursive Neural Network Based Preordering for English-to-Japanese Machine Translation
This work addresses the costly language-dependent manual feature design in preordering for machine translation, offering a more automated solution for English-to-Japanese translation.
The paper tackles the problem of word order differences between English and Japanese in machine translation by proposing a preordering method using a recursive neural network that learns features from raw inputs, achieving comparable translation quality gains to the state-of-the-art method without manual feature design.
The word order between source and target languages significantly influences the translation quality in machine translation. Preordering can effectively address this problem. Previous preordering methods require a manual feature design, making language dependent design costly. In this paper, we propose a preordering method with a recursive neural network that learns features from raw inputs. Experiments show that the proposed method achieves comparable gain in translation quality to the state-of-the-art method but without a manual feature design.