Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation

Show full item record



Permalink

http://hdl.handle.net/10138/330171

Citation

Gronroos , S-A , Virpioja , S & Kurimo , M 2021 , ' Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation ' , Machine Translation , vol. 34 , pp. 251-286 . https://doi.org/10.1007/s10590-020-09253-x

Title: Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation
Author: Gronroos, Stig-Arne; Virpioja, Sami; Kurimo, Mikko
Contributor: University of Helsinki, Department of Digital Humanities
Date: 2021-01-30
Language: eng
Number of pages: 36
Belongs to series: Machine Translation
ISSN: 0922-6567
URI: http://hdl.handle.net/10138/330171
Abstract: There are several approaches for improving neural machine translation for low-resource languages: monolingual data can be exploited via pretraining or data augmentation; parallel corpora on related language pairs can be used via parameter sharing or transfer learning in multilingual models; subword segmentation and regularization techniques can be applied to ensure high coverage of the vocabulary. We review these approaches in the context of an asymmetric-resource one-to-many translation task, in which the pair of target languages are related, with one being a very low-resource and the other a higher-resource language. We test various methods on three artificially restricted translation tasks—English to Estonian (low-resource) and Finnish (high-resource), English to Slovak and Czech, English to Danish and Swedish—and one real-world task, Norwegian to North Sámi and Finnish. The experiments show positive effects especially for scheduled multi-task learning, denoising autoencoder, and subword sampling.
Subject: 113 Computer and information sciences
6121 Languages
Rights:
Full text embargoed until: 2022-01-30


Files in this item

Files Size Format View

Embargo on files ends: 2022-01-30

This item appears in the following Collection(s)

Show full item record