Transfer learning via augmentations for text classification task

Student: Sorokin Semen

Supervisor: Anastasiya A. Bonch-Osmolovskaya

Educational Programme: Computational Linguistics (Master)

Final Grade: 7

Year of Graduation: 2020

The present work is devoted to the study of augmentation methods in text classification problems. One of the common situations when building systems for automatic processing of a natural language using machine learning algorithms is the presence of a limited-sized dataset with markup. Such conditions often do not allow constructing a model that has high prediction quality and high speed in real-time operation. The study describes an effective method of augmentation using pre-trained language models, which allows increasing the accuracy of models based on LSTM, CNN, and MLP architectures.

Full text (added June 4, 2020)

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