Fairy Tale Text Generation by Brief Description

Student: Sidorova Anastasiya

Educational Programme: Machine Learning and Data-Intensive Systems (Master)

Year of Graduation: 2024

Modern deep learning methods, especially large language models (LLMs), provide new capabilities in the field of text generation. This thesis examines the process of developing a high-load application for generating fairy tale texts based on a short description using the Mistral model, additionally trained on a specialized data set. The main focus is on setting up LLM to create personalized text - a personal fairy tale, as well as developing an effective application architecture that can process a large number of requests and provide high-quality answers based on user data.

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