Scholarlink

This paper describes several key updates and improvements to the NooJ Belarusian module, which was developed in 2012. These recent additions focus on enhancing NooJ’s ability to process and analyze the Belarusian language. The following specific actions were taken. Corpus Variation: We have prepared a new representative mini corpus containing 1.5 million word forms. This extensive text collection provides a basis for linguistic and extralinguistic analysis. Dictionary and grammar updates: we have revised the Belarusian basic dictionary, with particular attention to the tagging of gerunds. We have developed new syntactic rules to improve the automatic tagging of homonyms and to enable consistent processing of phraseological units. Vocabulary expansion: we have added approximately 300 new words to the dictionary, and we have supplemented grammatical information for existing entries. These updates aim to increase the accuracy and efficiency of NooJ in the linguistic analysis of Belarusian.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Updating the Belarusian NooJ Module: Integrating New Lexical and Grammatical Resources

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Yuras Hetsevich,
  • Valery Varanovich,
  • Mikita Suprunchuk

摘要

This paper describes several key updates and improvements to the NooJ Belarusian module, which was developed in 2012. These recent additions focus on enhancing NooJ’s ability to process and analyze the Belarusian language. The following specific actions were taken. Corpus Variation: We have prepared a new representative mini corpus containing 1.5 million word forms. This extensive text collection provides a basis for linguistic and extralinguistic analysis. Dictionary and grammar updates: we have revised the Belarusian basic dictionary, with particular attention to the tagging of gerunds. We have developed new syntactic rules to improve the automatic tagging of homonyms and to enable consistent processing of phraseological units. Vocabulary expansion: we have added approximately 300 new words to the dictionary, and we have supplemented grammatical information for existing entries. These updates aim to increase the accuracy and efficiency of NooJ in the linguistic analysis of Belarusian.