0

Mapping Supervised Bilingual Word Embeddings from English to low-resource languages

Mapping word embeddings from English to low-resource languages using a shared vector space improves machine translation tasks when bilingual data is available, and unsupervised learning on monolingual data is effective for these languages.

Year
2019
Venue
arXiv 2019
Authors
1
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/1910.06411ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

It is very challenging to work with low-resource languages due to the inadequate availability of data. Using a dictionary to map independently trained word embeddings into a shared vector space has proved to be very useful in learning bilingual embeddings in the past. Here we have tried to map individual embeddings of words in English and their corresponding translated words in low-resource languages like Estonian, Slovenian, Slovakian, and Hungarian. We have used a supervised learning approach. We report accuracy scores through various retrieval strategies which show that it is possible to approach challenging tasks in Natural Language Processing like machine translation for such languages, provided that we have at least some amount of proper bilingual data. We also conclude that we can follow an unsupervised learning path on monolingual text data as that is more suitable for low-resource languages.

Authors

1