Decomposition of word embeddings
Organization
Language Technology
Abstract
This thesis will study the decomposition of the word embeddings
into ontological categories.
The decomposition is initially performed using the evaluative framework described in [Yaghoobzadeh et al. (2019)]. The framework's idea is that classifiers can be trained to decompose an ambiguous word embedding into the categories its different senses belong.
The thesis will implement the evaluative framework mentioned above and go beyond this by using the mappings between Wordnet and various formal ontologies.
into ontological categories.
The decomposition is initially performed using the evaluative framework described in [Yaghoobzadeh et al. (2019)]. The framework's idea is that classifiers can be trained to decompose an ambiguous word embedding into the categories its different senses belong.
The thesis will implement the evaluative framework mentioned above and go beyond this by using the mappings between Wordnet and various formal ontologies.
Graduation Theses defence year
2020-2021
Supervisor
Eduard Barbu
Spoken language (s)
English
Requirements for candidates
Level
Masters
Keywords
Application of contact
Name
Eduard Barbu
Phone
E-mail