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

Empirical Study of Transformers for Symbolic Mathematics

Student: Gelvan Kirill

Supervisor: Nadezhda Chirkova

Faculty: Faculty of Computer Science

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2021

Developed for natural language processing (NLP), the Transformer architecture is now widely used with all kinds of sequences, including symbolic mathematical expressions. Given an example as a sequence of tokens, the model is able to solve complex math tasks like differentiation or integration. In this work, we investigate whether feeding data structure to the Transformer improves its performance on integration and solving ordinary differential equations (ODEs). We study recently developed tree-based model modifications and compare them. In our experience, the use of these alterations provides no benefit over the base approach. We assume this is due to an uncommonly large amount of 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