Institutional Repository of Vilnius University
Modeling of movie recommendation system based on sentencebert /
Abstract
dc:descriptionThis final bachelor thesis project is the comparison of different SentenceBert models based on BERT (Bidirectional Encoder Representations from Transformers) technology, and the creation of a movie recommendation system, providing recommendations based on movie overview similarities. SentenceBert is a state-of-the-art framework, based on PyTorch and Transformers, used for sentence, text, and image embeddings for more than 100 languages. However, SentenceBert is a fairly new and not extensively analyzed and used model, therefore, there are few SentenceBert models comparisons and result evaluations. Therefore, the goal of this project is to compare multiple models suited for SentenceBert by creating a movie recommendation system and evaluating results. The research was done on Natural Language Processing, its techniques, and other methods needed to better understand SentenceBert and its purpose. The result is a developed movie recommendation system with data of 2000 different movies and the comparison of four SentenceBert models.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Alaburda, Vytenis,
- Contributors dc:contributor
-
- Būtėnas, Linas
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- eng
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD107118741&prefLang=en_US