LINGUISTIC ANALYSIS FOR THE BELARUSIAN CORPUS WITH THE APPLICATION OF NATURAL LANGUAGE PROCESSING AND MACHINE LEARNING TECHNIQUES
The article focuses on the problems existing in text-to-speech synthesis. Different morphological, lexical and syntactical elements were localized with the help of the Belarusian unit of NooJ program. Those types of errors, which occur in Belarusian texts, were analyzed and corrected. Language model...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
National Academy of Sciences of Belarus, the United Institute of Informatics Problems
2017-12-01
|
| Series: | Informatika |
| Online Access: | https://inf.grid.by/jour/article/view/241 |
| Summary: | The article focuses on the problems existing in text-to-speech synthesis. Different morphological, lexical and syntactical elements were localized with the help of the Belarusian unit of NooJ program. Those types of errors, which occur in Belarusian texts, were analyzed and corrected. Language model and part of speech tagging model were built. The natural language processing of Belarusian corpus with the help of developed algorithm using machine learning was carried out. The precision of developed models of machine learning has been 80–90 %. The dictionary was enriched with new words for the further using it in the systems of Belarusian speech synthesis. |
|---|---|
| ISSN: | 1816-0301 |