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

Compositionality of Distributed Data Representation

ФИО студента: Frank lawrence nii adoquaye Acquaye

Руководитель: Attila Kertesz-Farkas

Кампус/факультет: Faculty of Computer Science

Программа: Data Science (Master)

Год защиты: 2021

The concept of distributed data representation has long been believed as a suitable means of encoding information for machine learning models and, more importantly, deep learning models. In recent times research has shown that distributed data representation can be learnt via back-propagation. More importantly, such representations are compositional in nature as popularized by the “king - man + woman = queen” example. In this work, we investigate the compositionality of distributed data representation. We do this by exploring the hypernym/hyponym relationship between words to classify words using their distributed data representation. Therefore, we have been able to ascertain that distributed data representation is compositional and contains some structure.

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