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

Analysis of Affine Transformations in BERT Semantical Space

Student: Solodiankin Andrei

Supervisor: Eduard Klyshinskiy

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Information Science and Computation Technology (Bachelor)

Year of Graduation: 2021

Modern methods of natural language processing (NLP) are based on models of vector representation of words. One of the features of these models is to solve the problem of proportional analogy. This problem has been repeatedly investigated for non contextualized models. In this paper, we investigate affine transformations of parallel transport for contextualized models. Numerical experiments were carried out with vector representations of the ELMo and BERT models, which showed that parallel transfer does not always make it possible to obtain the correct solution.

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