Look It Up: Bilingual Dictionaries Improve Neural Machine Translation

TL;DR

This paper introduces a novel method for integrating bilingual dictionaries into neural machine translation models, significantly improving translation quality for rare words by enabling the model to learn how to utilize dictionary definitions.

Contribution

A new approach for attaching dictionary definitions to rare words in NMT, allowing the model to learn their effective usage and improve translation accuracy.

Findings

Up to 1.8 BLEU improvement with bilingual dictionaries

Effective method for incorporating dictionaries into NMT

Enhanced translation of rare words

Abstract

Despite advances in neural machine translation (NMT) quality, rare words continue to be problematic. For humans, the solution to the rare-word problem has long been dictionaries, but dictionaries cannot be straightforwardly incorporated into NMT. In this paper, we describe a new method for "attaching" dictionary definitions to rare words so that the network can learn the best way to use them. We demonstrate improvements of up to 1.8 BLEU using bilingual dictionaries.