Morphology Generation for Statistical Machine Translation using Deep Learning Techniques

TL;DR

This paper introduces a neural network approach to morphological simplification in machine translation, focusing on gender and number, leading to improved translation quality for Chinese-Spanish tasks.

Contribution

It proposes a novel neural classification architecture for morphology generation that outperforms standard methods and enhances translation performance.

Findings

Achieved over 98% accuracy in gender classification

Attained over 93% accuracy in number classification

Improved translation quality by 0.7 METEOR points

Abstract

Morphology in unbalanced languages remains a big challenge in the context of machine translation. In this paper, we propose to de-couple machine translation from morphology generation in order to better deal with the problem. We investigate the morphology simplification with a reasonable trade-off between expected gain and generation complexity. For the Chinese-Spanish task, optimum morphological simplification is in gender and number. For this purpose, we design a new classification architecture which, compared to other standard machine learning techniques, obtains the best results. This proposed neural-based architecture consists of several layers: an embedding, a convolutional followed by a recurrent neural network and, finally, ends with sigmoid and softmax layers. We obtain classification results over 98% accuracy in gender classification, over 93% in number classification, and an overall translation improvement of 0.7 METEOR.