Сборники тезисов • Инновации и урбанистика • Языковая культура в сфере инновационных технологий
Сборник тезисов докладов конгресса молодых ученых. Электронное издание. – СПб: Университет ИТМО, 2015.
Preprocessing of historical text for using NLP algorithms
УДК: 81'322.2
Аннотация:
The international cooperation demands multilinguistic approach to information processing. Researchers of the whole world have to work with information irrespective of language in which it is submitted. It is especially important at historical researches. The NLP methods can give big help in the solution of this problem. However application of the NLP methods directly to the printing text is impossible. The text has to be previously transferred to a machine-readable form. In this work we describe our experience of preparation of the text of the 17th century written in Old French language for the subsequent application of the NLP methods.