Multilingual low-resource translation for Indo-European languages

Abstract

Neural machine translation is the task of translating text between a source language and a target language using artificial neural networks. Typically, training neural machine translation models is computationally expensive and requires vast amounts of data in order to build a model which is able to translate accurately enough for use in the real-world. Some of the best translation models in the world such as those developed by Google and Facebook are trained on billions of sentences where data is available. These models provide coverage for over 100 languages, however many of these languages do not have large parallel corpora and this becomes evident from the grammatical and linguistic errors that can be seen in translation outputs. This project focuses on neural machine translation in the context of low-resource languages, which possess far less online corpora available when compared with other widely spoken languages such as English, Spanish and Mandarin. A dataset was constructed from an amalgamation of different multilingual sources in order to create a single larger multilingual corpus which included the English, Danish, German, Icelandic, Norwegian and Swedish languages. A combination of pre-trained neural network as well as novel neural networks were trained on this new dataset, primarily using the technique of transfer learning.