Automatic Text Summarization Using Deep Learning

Student: Alaev Evgenii

Educational Programme: Business Informatics (Bachelor)

Year of Graduation: 2020

The main goal of this study is to implement an algorithm that can create short summaries of court judgments. To accomplish this goal, a research of modern text summarizations methods was carried out. As a result of this research, it was decided to implement a text summarization algorithm called SummaRuNNer due to its ability to produce interpretable results. It was proposed to make changes to this model’s architecture. The results of conducted experiments showed that the model tends to create better summaries by employing these architecture modifications. Furthermore, as indicated by ROUGE scores and human evaluation, the resulted model produces good results, so that it is ready to be used in practice. Another important result of this study is the dataset that was constructed from 170 thousand court judgments and annotations written in Russian 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