Bridging Neural Machine Translation and Bilingual Dictionaries

TL;DR

This paper introduces two innovative methods to integrate bilingual dictionaries into neural machine translation, enhancing translation quality especially for rare words by transforming dictionaries into effective training data.

Contribution

The paper proposes novel models that convert bilingual dictionaries into sentence pairs, improving NMT's ability to translate rare words by leveraging dictionary information.

Findings

Significant improvement in translation quality.

Rare words covered by dictionaries are translated correctly.

Methods outperform baseline NMT models.

Abstract

Neural Machine Translation (NMT) has become the new state-of-the-art in several language pairs. However, it remains a challenging problem how to integrate NMT with a bilingual dictionary which mainly contains words rarely or never seen in the bilingual training data. In this paper, we propose two methods to bridge NMT and the bilingual dictionaries. The core idea behind is to design novel models that transform the bilingual dictionaries into adequate sentence pairs, so that NMT can distil latent bilingual mappings from the ample and repetitive phenomena. One method leverages a mixed word/character model and the other attempts at synthesizing parallel sentences guaranteeing massive occurrence of the translation lexicon. Extensive experiments demonstrate that the proposed methods can remarkably improve the translation quality, and most of the rare words in the test sentences can obtain correct translations if they are covered by the dictionary.