| dc.contributor.advisor | Fischer, Andreas | |
| dc.contributor.author | Thurnbauer, Matthias Johannes | |
| dc.date.accessioned | 2026-01-06T11:55:30Z | |
| dc.date.available | 2026-01-06T11:55:30Z | |
| dc.date.issued | 2023 | |
| dc.date.submitted | 2023-02-06 | |
| dc.identifier.uri | https://dspace.jcu.cz/handle/20.500.14390/48678 | |
| dc.description.abstract | The influence of the window size on semantic and thematic similarities between words was
analyzed for the algorithms Word2Vec and Glove. Furthermore, a disambiguation method was
proposed using a density based clustering algorithm called DBSCAN. The report also contains
performance measurements regarding the training times of these static word embedding algorithms showing the influence of the token normalization process. | cze |
| dc.format | 130 | |
| dc.format | 130 | |
| dc.language.iso | eng | |
| dc.publisher | Jihočeská univerzita | cze |
| dc.rights | Práce není přístupná | |
| dc.subject | Word Embeddings | cze |
| dc.subject | DBSCAN | cze |
| dc.subject | Cosine Similarity | cze |
| dc.subject | Semantic | cze |
| dc.subject | Thematic | cze |
| dc.subject | Word2Vec | cze |
| dc.subject | GloVe | cze |
| dc.subject | Word Embeddings | eng |
| dc.subject | DBSCAN | eng |
| dc.subject | Cosine Similarity | eng |
| dc.subject | Semantic | eng |
| dc.subject | Thematic | eng |
| dc.subject | Word2Vec | eng |
| dc.subject | GloVe | eng |
| dc.title | Analysis of Word Embeddings | cze |
| dc.title.alternative | Analysis of Word Embeddings | eng |
| dc.type | diplomová práce | cze |
| dc.identifier.stag | 70517 | |
| dc.description.abstract-translated | The influence of the window size on semantic and thematic similarities between words was
analyzed for the algorithms Word2Vec and Glove. Furthermore, a disambiguation method was
proposed using a density based clustering algorithm called DBSCAN. The report also contains
performance measurements regarding the training times of these static word embedding algorithms showing the influence of the token normalization process. | eng |
| dc.date.accepted | 2023-03-02 | |
| dc.description.department | Přírodovědecká fakulta | cze |
| dc.thesis.degree-discipline | Artificial Intelligence and Data Science | cze |
| dc.thesis.degree-grantor | Jihočeská univerzita. Přírodovědecká fakulta | cze |
| dc.thesis.degree-name | Mgr. | |
| dc.thesis.degree-program | Artificial Intelligence and Data Science | cze |
| dc.description.grade | Dokončená práce s úspěšnou obhajobou | cze |
| dc.contributor.referee | Goller, Christoph | |
| dc.contributor.referee | Torkler, Phillipp | |
| dc.description.defence | <p>Committee: doc. Dr.rer.nat Jan Valdman, Ing. Rudolf Vohnout, Ph.D., Prof. Dr. Andreas Berl, Prof. Dr. Phillipp Torkler, Mgr. Jakub Geyer, Ing. Ondřej Budík, Dr. Amrit Mukherjee, Ph.D.</p>
<p>Student has presented his master thesis and focused on main aspects and gaols of the work. </p>
<p>Student made the presentation on time. Student presentation was clear to understand. </p>
<p>Which if the presented goals was the most challenging?</p>
<p>Could you explain the clustering used in your thesis?</p> | cze |
