Unsupervised Semantic Change Detection in Arabic
dc.contributor.advisor | Dubossarsky, Haim | |
dc.contributor.author | Sindi, Kenan | |
dc.date.accessioned | 2024-02-01T09:03:46Z | |
dc.date.available | 2024-02-01T09:03:46Z | |
dc.date.issued | 2023-10-23 | |
dc.description.abstract | This study employs pretrained BERT models— AraBERT, CAMeLBERT (CA), and CAMeLBERT (MSA)—to investigate semantic change in Arabic across distinct time periods. Analyzing word embeddings and cosine distance scores reveals variations in capturing semantic shifts. The research highlights the significance of training data quality and diversity, while acknowledging limitations in data scope. The project's outcome—a list of most stable and changed words—contributes to Arabic NLP by shedding light on semantic change detection, suggesting potential model selection strategies and areas for future exploration. | |
dc.format.extent | 15 | |
dc.identifier.uri | https://hdl.handle.net/20.500.14154/71355 | |
dc.language.iso | en | |
dc.publisher | Queen Mary University of London | |
dc.subject | Natural Language Processing | |
dc.subject | Arabic NLP | |
dc.subject | Langauge Models | |
dc.subject | BERT | |
dc.subject | Data Science | |
dc.subject | Semantic Change | |
dc.subject | Unsupervised | |
dc.title | Unsupervised Semantic Change Detection in Arabic | |
dc.type | Thesis | |
sdl.degree.department | Electronic Engineering and Computer Science | |
sdl.degree.discipline | Data Science and Artificial Intelligence | |
sdl.degree.grantor | Queen Mary University of London | |
sdl.degree.name | Master of Science |