The contributions of Corpus Linguistics and Natural Language Processing in the elaboration of the prototype of the Ideological Dictionary of Locutions

• Autor(a) principal: da Cruz, Thyago José
• Data de Publicação: 2022
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Domínios de Lingu@gem
• Texto Completo: https://seer.ufu.br/index.php/dominiosdelinguagem/article/view/62958
• topic: Fraseografia; Linguística Computacional; Linguística de corpus; Processamento de Linguagem Natural; Dicionário Ideológico; Phraseography; Computational Linguistics; Corpus Linguistics; Natural Language Processing; Ideological Dictionary

In this work, we seek to demonstrate how resources and tools of Corpus Linguistics and Natural Language Processing could be used in the generation of the prototype of the Ideological Dictionary of Locutions, monolingual and, at the same time, onomasiological and semasiological. This type of phraseographic repertoire is composed of three large sections in the dictionary body: the synoptic-analogical part, the analogical (both corresponding to the onomasiological part of the work) and the alphabetical (with a semasiological characteristic). In developing this project, we used the Corpus Brasileiro and the Web as corpora.    As a tool for the elaboration of the dictionary body, we used the FieldWorks Language Explore software, FLEx. In the end, it was possible to verify that these computational instruments were of fundamental relevance for the accomplishment of the research purpose.