• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Transformer Based Paraphrase Generation

Student: Zhordaniya Tamara

Supervisor: Anastasiya A. Bonch-Osmolovskaya

Faculty: Faculty of Humanities

Educational Programme: Computational Linguistics (Master)

Year of Graduation: 2020

The master's thesis is devoted to the problem of automatic paraphrase generation in Russian. The work described and classified modern methods of paraphrase generation. Two types of neural architectures were applied to model training - seq2seq LSTM with residual connection and Transformer. The models were implemented using the PyTorch deep learning framework in the Python programming 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