Investigation of Nonlinear Transformations by Neural Networks of Vector Representations of Communication Languages in Translation Models

Student: Barinova Anna

Supervisor: Vladimir Krylov

Faculty: Faculty of Informatics, Mathematics, and Computer Science (HSE Nizhny Novgorod)

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2019

The main goal of this study is to create a mechanism that extracts relevant information from text in another language. This mechanism can be used in search and question-answer systems, where there is no need for a literal translation, but the general meaning of the question asked has the most importance. For this purpose, trained neural networks are implemented in this program. Also text embedding plays a great role in my study, but the one that is used is BERT or Bidirectional Encoder Representations from Transformers which is a recent paper published by researchers at Google AI Language.

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