Normalization of Russian Dialect Texts Using Character-Level Statistical Machine Translation (CSMT)

Student: Ignatev Grigoriy

Supervisor: Timofey Arkhangelskiy

Educational Programme: Fundamental and Computational Linguistics (Bachelor)

Year of Graduation: 2017

The purpose of this work is to develop a robust tool for normalization of Russian dialect texts using Character-level Statistical Machine Translation (CSMT). The work provides overview of normalization methods and state-of-the art text normalization techniques. The work describes experiments that were conducted in order to figure out how much data is needed for the model training, what type and size of additional text set for the language model is needed. As an outcome of this work, CSMT model was trained. The results show that the model outperformed the baseline at a statistically significant level, providing the accuracy of 84%.

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