Reference Network for Neural Machine Translation

Abstract

Neural Machine Translation (NMT) has achieved notable success in recent years. Such a framework usually generates translations in isolation. In contrast, human translators often refer to reference data, either rephrasing the intricate sentence fragments with common terms in source language, or just accessing to the golden translation directly. In this paper, we propose a Reference Network to incorporate referring process into translation decoding of NMT. To construct a reference book, an intuitive way is to store the detailed translation history with extra memory, which is computationally expensive. Instead, we employ Local Coordinates Coding (LCC) to obtain global context vectors containing monolingual and bilingual contextual information for NMT decoding. Experimental results on Chinese-English and English-German tasks demonstrate that our proposed model is effective in improving the translation quality with lightweight computation cost.

Syntax-aware bidirectional decoding Neural Machine Translation model

“…Further advancements followed in 2019 when Fu et al [6] introduced a reference network that integrated the reference process into the translation decoding process. Utilizing local coordinate encoding, they acquired a global context vector encompassing monolingual and bilingual context information.…”