Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data
Wei-Jen Ko, Ahmed El-Kishky, Adithya Renduchintala, Vishrav Chaudhary, Naman Goyal, Francisco Guzmán, Pascale Fung, Philipp Koehn
Abstract
The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are linguistically related or similar to high-resource languages; these related languages may share many lexical or syntactic structures. In this work, we exploit this linguistic overlap to facilitate translating to and from a low-resource language with only monolingual data, in addition to any parallel data in the related high-resource language. Our method, NMT-Adapt, combines denoising autoencoding, back-translation and adversarial objectives to utilize monolingual data for low-resource adaptation. We experiment on 7 languages from three different language families and show that our technique significantly improves translation into low-resource language compared to other translation baselines.
BibTeX
@inproceedings{ko-etal-2021-adapting,
title = "Adapting High-resource {NMT} Models to Translate Low-resource Related Languages without Parallel Data",
author = "Ko, Wei-Jen and
El-Kishky, Ahmed and
Renduchintala, Adithya and
Chaudhary, Vishrav and
Goyal, Naman and
Guzm{\'a}n, Francisco and
Fung, Pascale and
Koehn, Philipp and
Diab, Mona",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.66/",
doi = "10.18653/v1/2021.acl-long.66",
pages = "802--812"
}