Coverage Embedding Models for Neural Machine Translation

TL;DR

This paper introduces coverage embedding models for neural machine translation to improve translation accuracy by explicitly tracking source word coverage, reducing errors like repetition and omission.

Contribution

It proposes a novel coverage embedding approach that dynamically updates coverage information during translation, enhancing NMT performance.

Findings

Significant improvement in translation quality on Chinese-English tasks

Effective reduction of repeated and dropped translations

Enhanced model outperforms baseline NMT systems

Abstract

In this paper, we enhance the attention-based neural machine translation (NMT) by adding explicit coverage embedding models to alleviate issues of repeating and dropping translations in NMT. For each source word, our model starts with a full coverage embedding vector to track the coverage status, and then keeps updating it with neural networks as the translation goes. Experiments on the large-scale Chinese-to-English task show that our enhanced model improves the translation quality significantly on various test sets over the strong large vocabulary NMT system.