Comparison of Sentence Embeddings for Natural Language Understanding in Russian

Student: Popov Dmitrii

Supervisor: Ekaterina Artemova

Educational Programme: Mathematics (Bachelor)

Final Grade: 8

Year of Graduation: 2019

Over the last years, the field of natural language processing has reached great success. One of the main components of almost any task in this area is the obtaining of vector representations of text data for further application of machine learning algorithms. In this paper, I investigate the performance of several sentence embeddings models for several tasks for the Russian language such as multiple choice question answering, next sentence prediction, and paraphrase detection.

Full text (added May 31, 2019)

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