Universal Vector Neural Machine Translation With Effective Attention

TL;DR

This paper introduces a universal neural machine translation model that can handle multiple languages with a single encoder-decoder architecture, reducing the need for multiple models and improving translation flexibility.

Contribution

The paper presents a novel universal NMT model with an integrated attention mechanism that supports multiple languages within one model, streamlining multilingual translation tasks.

Findings

Reduces the number of models needed for multilingual translation

Increases translation accuracy for long sentences

Supports multiple language pairs with a single model

Abstract

Neural Machine Translation (NMT) leverages one or more trained neural networks for the translation of phrases. Sutskever introduced a sequence to sequence based encoder-decoder model which became the standard for NMT based systems. Attention mechanisms were later introduced to address the issues with the translation of long sentences and improving overall accuracy. In this paper, we propose a singular model for Neural Machine Translation based on encoder-decoder models. Most translation models are trained as one model for one translation. We introduce a neutral/universal model representation that can be used to predict more than one language depending on the source and a provided target. Secondly, we introduce an attention model by adding an overall learning vector to the multiplicative model. With these two changes, by using the novel universal model the number of models needed for multiple language translation applications are reduced.