Continuous Learning in Neural Machine Translation using Bilingual Dictionaries

TL;DR

This paper introduces a framework for enhancing neural machine translation with bilingual dictionaries, enabling better continuous learning of new words and phrases, significantly improving translation accuracy for rare terms.

Contribution

It presents a novel evaluation framework and integrates one-shot learning with word representations to improve NMT's ability to learn from bilingual dictionaries.

Findings

Translation of new, rare words improved from 30% to 70%.

Correct lemmas generated over 90%.

Highlights importance of addressing morphology and one-shot learning.

Abstract

While recent advances in deep learning led to significant improvements in machine translation, neural machine translation is often still not able to continuously adapt to the environment. For humans, as well as for machine translation, bilingual dictionaries are a promising knowledge source to continuously integrate new knowledge. However, their exploitation poses several challenges: The system needs to be able to perform one-shot learning as well as model the morphology of source and target language. In this work, we proposed an evaluation framework to assess the ability of neural machine translation to continuously learn new phrases. We integrate one-shot learning methods for neural machine translation with different word representations and show that it is important to address both in order to successfully make use of bilingual dictionaries. By addressing both challenges we are able to improve the ability to translate new, rare words and phrases from 30% to up to 70%. The correct lemma is even generated by more than 90%.