Lesan – Machine Translation for Low Resource Languages

by   Asmelash Teka Hadgu, et al.

Millions of people around the world can not access content on the Web because most of the content is not readily available in their language. Machine translation (MT) systems have the potential to change this for many languages. Current MT systems provide very accurate results for high resource language pairs, e.g., German and English. However, for many low resource languages, MT is still under active research. The key challenge is lack of datasets to build these systems. We present Lesan, an MT system for low resource languages. Our pipeline solves the key bottleneck to low resource MT by leveraging online and offline sources, a custom OCR system for Ethiopic and an automatic alignment module. The final step in the pipeline is a sequence to sequence model that takes parallel corpus as input and gives us a translation model. Lesan's translation model is based on the Transformer architecture. After constructing a base model, back translation, is used to leverage monolingual corpora. Currently Lesan supports translation to and from Tigrinya, Amharic and English. We perform extensive human evaluation and show that Lesan outperforms state-of-the-art systems such as Google Translate and Microsoft Translator across all six pairs. Lesan is freely available and has served more than 10 million translations so far. At the moment, there are only 217 Tigrinya and 15,009 Amharic Wikipedia articles. We believe that Lesan will contribute towards democratizing access to the Web through MT for millions of people.


page 1

page 2

page 3

page 4


Evaluating Amharic Machine Translation

Machine translation (MT) systems are now able to provide very accurate r...

Two New Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English

The vast majority of language pairs in the world are low-resource becaus...

ChatGPT MT: Competitive for High- (but not Low-) Resource Languages

Large language models (LLMs) implicitly learn to perform a range of lang...

From Zero to Production: Baltic-Ukrainian Machine Translation Systems to Aid Refugees

In this paper, we examine the development and usage of six low-resource ...

Facilitating Access to Multilingual COVID-19 Information via Neural Machine Translation

Every day, more people are becoming infected and dying from exposure to ...

Finetuning a Kalaallisut-English machine translation system using web-crawled data

West Greenlandic, known by native speakers as Kalaallisut, is an extreme...

Evaluating Multiway Multilingual NMT in the Turkic Languages

Despite the increasing number of large and comprehensive machine transla...

Please sign up or login with your details

Forgot password? Click here to reset