Neural Machine Translation with External Phrase Memory

TL;DR

This paper introduces phraseNet, a neural machine translation model that incorporates an external phrase memory to improve translation quality by enabling phrase-level generation, demonstrated by a 3.45 BLEU score increase in Chinese-English translation.

Contribution

The paper presents a novel neural machine translation model that integrates external phrase memory and phrase-level generation strategies, enhancing translation performance.

Findings

Achieves 3.45 BLEU improvement over baseline NMT.

Effectively incorporates external phrase knowledge.

Extends word-by-word generation with phrase-level output.

Abstract

In this paper, we propose phraseNet, a neural machine translator with a phrase memory which stores phrase pairs in symbolic form, mined from corpus or specified by human experts. For any given source sentence, phraseNet scans the phrase memory to determine the candidate phrase pairs and integrates tagging information in the representation of source sentence accordingly. The decoder utilizes a mixture of word-generating component and phrase-generating component, with a specifically designed strategy to generate a sequence of multiple words all at once. The phraseNet not only approaches one step towards incorporating external knowledge into neural machine translation, but also makes an effort to extend the word-by-word generation mechanism of recurrent neural network. Our empirical study on Chinese-to-English translation shows that, with carefully-chosen phrase table in memory, phraseNet yields 3.45 BLEU improvement over the generic neural machine translator.