Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features

TL;DR

This paper proposes a novel approach to multilingual neural machine translation that disentangles semantic and linguistic features to improve zero-shot translation performance while maintaining supervised translation quality.

Contribution

It introduces a disentangling learning task and a linguistic encoder to leverage semantic and linguistic features, enhancing knowledge sharing across languages.

Findings

Significant improvement in zero-shot translation accuracy.

Maintains performance in supervised translation tasks.

Effective utilization of semantic and linguistic features.

Abstract

The many-to-many multilingual neural machine translation can be regarded as the process of integrating semantic features from the source sentences and linguistic features from the target sentences. To enhance zero-shot translation, models need to share knowledge across languages, which can be achieved through auxiliary tasks for learning a universal representation or cross-lingual mapping. To this end, we propose to exploit both semantic and linguistic features between multiple languages to enhance multilingual translation. On the encoder side, we introduce a disentangling learning task that aligns encoder representations by disentangling semantic and linguistic features, thus facilitating knowledge transfer while preserving complete information. On the decoder side, we leverage a linguistic encoder to integrate low-level linguistic features to assist in the target language generation. Experimental results on multilingual datasets demonstrate significant improvement in zero-shot translation compared to the baseline system, while maintaining performance in supervised translation. Further analysis validates the effectiveness of our method in leveraging both semantic and linguistic features. The code is available at https://github.com/ictnlp/SemLing-MNMT.