Neural Machine Translation for Low Resource Languages

Student: Stepachev Pavel

Supervisor: Francis M. Tyers

Educational Programme: Computational Linguistics (Master)

Year of Graduation: 2019

Recent approaches based on unsupervised techniques propose completely novel direction for machine translation by abandoning the parallel texts. Comparing to default neural machine translation as a supervised task, it uses no supervision signal at all and relies only on monolingual data. This methods can be data-efficient compared to regular NMT. The goal of the research is to test them in low-resourced language scenario (Sinhala, Nepali, Urdu and Kazakh languages).

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses