Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation

TL;DR

This paper enhances character-based neural machine translation by integrating target-side morphological information, significantly improving translation quality for morphologically rich languages like German, Russian, and Turkish.

Contribution

It introduces a novel extension to existing character-level NMT models by incorporating a morphology table that provides auxiliary affix signals during decoding.

Findings

Significant BLEU score improvements for German, Russian, and Turkish translations.

Effective use of morphological signals to constrain decoder predictions.

Enhanced handling of out-of-vocabulary words in MRLs.

Abstract

Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches. However, its performance drops considerably in the presence of morphologically rich languages (MRLs). Neural engines usually fail to tackle the large vocabulary and high out-of-vocabulary (OOV) word rate of MRLs. Therefore, it is not suitable to exploit existing word-based models to translate this set of languages. In this paper, we propose an extension to the state-of-the-art model of Chung et al. (2016), which works at the character level and boosts the decoder with target-side morphological information. In our architecture, an additional morphology table is plugged into the model. Each time the decoder samples from a target vocabulary, the table sends auxiliary signals from the most relevant affixes in order to enrich the decoder's current state and constrain it to provide better predictions. We evaluated our model to translate English into German, Russian, and Turkish as three MRLs and observed significant improvements.