| DC Field | Value | Language |
|---|
| dc.contributor.author | Krez, K. S. | - |
| dc.coverage.spatial | Минск | en_US |
| dc.date.accessioned | 2025-06-03T09:53:20Z | - |
| dc.date.available | 2025-06-03T09:53:20Z | - |
| dc.date.issued | 2025 | - |
| dc.identifier.citation | Krez, K. S. From words to vectors: text vectorization techniques in natural language processing / K. S. Krez // Электронные системы и технологии : сборник материалов 61-й научной конференции аспирантов, магистрантов и студентов БГУИР, Минск, 21–25 апреля 2025 г. / Белорусский государственный университет информатики и радиоэлектроники ; редкол.: Д. В. Лихаческий [и др.]. – Минск, 2025. – С. 60–62. | en_US |
| dc.identifier.uri | https://libeldoc.bsuir.by/handle/123456789/59949 | - |
| dc.description.abstract | This paper discusses the process of text vectorization, which is a key step in Natural Language Processing (NLP). The main vectorization methods are described, including One-Hot Encoding, Bag of Words, TF-IDF and Word Embeddings. The advantages and disadvantages of each method are analyzed, as well as their application in various NLP tasks. Text vectorization converts textual data into numerical vectors that can be processed by machine learning algorithms. This is necessary because computers cannot directly interpret text. | en_US |
| dc.language.iso | en | en_US |
| dc.publisher | БГУИР | en_US |
| dc.subject | материалы конференций | en_US |
| dc.subject | encoding | en_US |
| dc.subject | vectorization | en_US |
| dc.subject | text | en_US |
| dc.subject | algorithm | en_US |
| dc.subject | analysis | en_US |
| dc.title | From words to vectors: text vectorization techniques in natural language processing | en_US |
| dc.type | Article | en_US |
| Appears in Collections: | Электронные системы и технологии : материалы 61-й конференции аспирантов, магистрантов и студентов (2025)
|
