Search Engine Guided Non-Parametric Neural Machine Translation

TL;DR

This paper introduces a two-stage method combining search engine retrieval and a novel TM-NMT model to improve neural machine translation by leveraging an entire training set during translation.

Contribution

It presents a new retrieval-augmented NMT approach that uses external sentence pairs to enhance translation quality, a novel integration not previously explored.

Findings

Significant translation quality improvements over baseline models.

Performance improves with more relevant retrieved sentence pairs.

Effective on multiple language pairs (En-Fr, En-De, En-Es).

Abstract

In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first stage--retrieval stage--, an off-the-shelf, black-box search engine is used to retrieve a small subset of sentence pairs from a training set given a source sentence. These pairs are further filtered based on a fuzzy matching score based on edit distance. In the second stage--translation stage--, a novel translation model, called translation memory enhanced NMT (TM-NMT), seamlessly uses both the source sentence and a set of retrieved sentence pairs to perform the translation. Empirical evaluation on three language pairs (En-Fr, En-De, and En-Es) shows that the proposed approach significantly outperforms the baseline approach and the improvement is more significant when more relevant sentence pairs were retrieved.