Processing Texts with Sakha-Russian Code-Switching

Student: Bazhukov Maksim

Educational Programme: Computational Linguistics (Master)

Final Grade: 8

Year of Graduation: 2024

Active research is currently in progress to provide advanced NLP models for low-resource languages. Sakha, a Turkic language in the Northeast of Russia doesn't seem low-resource: the number of speakers is half a million, there is literature and some internet usage. Despite this, Sakha is poorly covered by NLP research: there are no large text datasets, no foundation models trained. We attempt to help this situation by making a dataset of web texts and training 2 BERT-base models. The models are also trained for classifying languages in Sakha-Russian code-switched texts, useful for future research.

Full text (added June 7, 2024)

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