ARTÍCULO
TITULO

Sketch Engine and TermoStat tools for automatic term extraction

A. A. Novikova    

Resumen

The paper considers comparison of Sketch Engine and TermoStat tools in automatic term extraction for a small English-language corpus. The corpus includes technical texts of ?Water supply? subject domain. Nowadays there are a lot of specialized programme tools for term extraction purposes. These tools also allow to work with large text data. The methods of corpus linguistics are often used in natural language processing. Text corpus is a collection of texts with specific genre. It could represent a so-called ?language model? in general and is often used as a basis for language research. There are many special programme tools which allow to create different corpora. Different specific linguistic problems could be solved using text corpora, especially term extraction which is very important task for linguists, lexicographers and terminologists to solve. It is very important to correct and improve terminological standarts, glossaries, dictionaries, etc. because of new terms which appear permanently. It is also important for stable work of online-dictionaries and machine translation systems, and it also helps translation specialists. The results of using term extraction tools with small English text corpus of water supply subject domain are discussed in the paper.

 Artículos similares