Termout.org logo

Termout.org - A Terminology Extraction System

About this project                 Contact us
This version is from 28 October 2018 . It fixes a bug that the previous version had.

Paste your text here. It can be in Spanish or English. The program will try to guess which language it is.


 
This program works at the moment only in Spanish and English. The program will try to guess the language of the text, and delete fragments of text in languages different from the main one, such as titles, abstracts, keyword and lists of references, typically found in scientific papers.
Consider that this is a text-based algorithm, meaning that it will only work if you process one document at a time (ideally a scientific paper).
It will not work if the text is too short (i.e., an abstract) or if it is too long (i.e., a whole textbook).
Minimum frequency: (Warning: if set to 1, the proces will take a very, very long time to finish) ||