Deep Learning Based Abstractive Text Summarization

Student: Dubinina Darya

Educational Programme: Master of Data Science (Master)

Year of Graduation: 2024

In the field of automatic text summarization the cross-lingual text summarization task is still a very specific subfield that suffers from the lack of sufficient amount of effective solution. This thesis explores existing approaches to automatic abstractive text summarization and aims at development of end-to-end solution for automatic abstractive single-document cross-lingual (Russian to English) generic multi-sentence news summarization based by fine-tuning pre-trained multilingual sequence-to-sequence model (mBart). Performance of the model is evaluated in terms of several metrics: ROUGE-1, ROUGE-2, ROUGE-L, BLEU and METEOR. The resulting model is compared with two pipelines frameworks (consisting of separate models for summarization and translation).

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