Original title: Generating Semantic Networks from Natural Language using BERT
Authors: GRIFFO DUARTE, Raphael
Document type: Master’s theses
Year: 2025
Language: eng
Abstract: This master thesis proposes SemNet, a new method for constructing semantic networks from natural language text. It compares SemNet to the benchmark model Netts, demonstrating comparable performance while highlighting key differences attributed to specific modules within Netts. SemNet excels in efficiency and scalability, particularly when leveraging GPU acceleration, making it a promising foundation for subsequent natural language processing tasks. SemNet effectively utilizes a SRL BERT model however, limitations in capturing complex relationships beyond verb-based interactions were identified. A comprehensive literature review helped define the model's architecture, leading to the selection of BERT as the optimal foundation given the balance of size and scalability compared to large language models and supervised learning approaches.
Keywords: BERT; efficiency; natural language processing; Netts; scalability; semantic network generation; SemNet
Citation: GRIFFO DUARTE, Raphael. Generating Semantic Networks from Natural Language using BERT. České Budějovice, 2025. diplomová práce (Mgr.). JIHOČESKÁ UNIVERZITA V ČESKÝCH BUDĚJOVICÍCH. Přírodovědecká fakulta

Institution: University of South Bohemia in České Budějovice (web)
Document availability information: Fulltext is available in the Digital Repository of University of South Bohemia.
Original record: http://www.jcu.cz/vskp/76929

Permalink: http://www.nusl.cz/ntk/nusl-671162


The record appears in these collections:
Universities and colleges > Public universities > University of South Bohemia in České Budějovice
Academic theses (ETDs) > Master’s theses