Saved in:
Bibliographic Details
Main Authors: Bu, Mengyu, Gu, Shuhao, Feng, Yang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.01394
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910552640454656
author Bu, Mengyu
Gu, Shuhao
Feng, Yang
author_facet Bu, Mengyu
Gu, Shuhao
Feng, Yang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_01394
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features
Bu, Mengyu
Gu, Shuhao
Feng, Yang
Computation and Language
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.
title Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features
topic Computation and Language
url https://arxiv.org/abs/2408.01394