• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site
For visually-impairedUser profile (HSE staff only)SearchMenu

Analysis of Affine Transformations in Word2Vec Semantical Space

Student: Olga Korogodina

Supervisor: Eduard Klyshinskiy

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

Educational Programme: Control Systems and Data Processing in Engineering (Master)

Year of Graduation: 2020

Continuous word representations are an important tool for many natural language processing (NLP) tasks. One of the quality criteria for the word vectors is the ability of the model to solve problems of proportional analogy. In the master thesis, methods for solving problems of proportional analogy by affine transformations of a semantic space consisting of word vectors was studied. Numerical experiments were conducted with word2vec and fastText semantic vector models, which showed that the affine transformation of the parallel translation does not always allow finding a solution to the proportional analogy problem.

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