Local Translation Prediction with Global Sentence Representation

TL;DR

This paper introduces a neural network approach that incorporates global sentence-level features to improve translation prediction, leading to significant quality enhancements over traditional models.

Contribution

It proposes a novel bilingually-constrained chunk-based CNN for sentence representation and integrates it into translation prediction, combining local and global information.

Findings

Substantial improvements in translation quality over baseline models

Effective use of sentence-level features for translation prediction

Enhanced model performance demonstrated through large-scale experiments

Abstract

Statistical machine translation models have made great progress in improving the translation quality. However, the existing models predict the target translation with only the source- and target-side local context information. In practice, distinguishing good translations from bad ones does not only depend on the local features, but also rely on the global sentence-level information. In this paper, we explore the source-side global sentence-level features for target-side local translation prediction. We propose a novel bilingually-constrained chunk-based convolutional neural network to learn sentence semantic representations. With the sentence-level feature representation, we further design a feed-forward neural network to better predict translations using both local and global information. The large-scale experiments show that our method can obtain substantial improvements in translation quality over the strong baseline: the hierarchical phrase-based translation model augmented with the neural network joint model.