engleski

Corpus-based analysis of keywords and multi-word lexical units in transport domain: methodological approach for vocabulary extraction

Keyword and multi-word detection represent a technique for retrieving information, using natural language processing techniques. The aim of this research is to give methodological framework for extracting keywords and multi-word units which will be used in the learning of English for Specific Purposes (ESP), for development of lexical competences in technical English. The process consists of the extraction, validation and creation of lists of informative keywords and premodifiers, that represent the best the specialized transport. The final output of the whole process is the list containing the most frequent and relevant multi-word units specific for the domain of transport, including multi-noun lexical units which are specific for the domain and harder to master in the language learning process. The methodological framework enables objective and consistent procedure into semi-automatic extraction process and the creation of the relevant vocabulary list in the technical English, as a result of the language engineering process

keyword extraction, multi-word units, multi-noun units, corpus, transport domain, vocabulary, lexical competences, NLP, English for Specific Purposes (ESP)

nije evidentirano