Future-Prediction-Based Model for Neural Machine Translation

TL;DR

This paper introduces a novel neural machine translation model that predicts future text length and words during decoding, enhancing translation quality by providing future context, and demonstrating significant improvements over baseline models.

Contribution

The paper presents a new NMT model that incorporates future prediction of length and words, which is a novel approach compared to traditional methods.

Findings

Model significantly outperforms baseline models.

Effective in predicting length and words of untranslated content.

Improves translation completeness and quality.

Abstract

We propose a novel model for Neural Machine Translation (NMT). Different from the conventional method, our model can predict the future text length and words at each decoding time step so that the generation can be helped with the information from the future prediction. With such information, the model does not stop generation without having translated enough content. Experimental results demonstrate that our model can significantly outperform the baseline models. Besides, our analysis reflects that our model is effective in the prediction of the length and words of the untranslated content.