In addition to its work in the traditional fields of lexicography and terminology, UZEI is a technology center. Research, basic and applied, is currently one of our main lines of work, and in particular, in the field of Natural Language Processing.
UZEI has developed a complete system of applications and resources to help draw up dictionaries, translations and terminology, and improve efficiency while guaranteeing the quality of its work.
All these resources were developed using its own technology.
RESOURCES AND BASIC TOOLS FOR NLP
A lexical database in Basque. It is constantly updated according to the standards and recommendations of Euskaltzaindia, the Royal Academy of the Basque Language, and is the basis of the Basque morphological analyzer.
An automatic lemmatizer created by UZEI for Basque. (demo)
A lexical database in Spanish. It is constantly updated according to the standards and recommendations of the Spanish Royal Academy, and is the basis for the Spanish morphological analyzer.
An automatic lemmatizer created by UZEI for Spanish. (demo)
A collection of terminological decisions taken by UZEI to create its dictionaries.
The purpose of this tool is to determine the subject matter of the text documents using document categorization.
VOCABULARY AND DICTIONARIES
Using text corpora in Basque and Spanish, this tool was developed to automatically identify and analyze the term candidates contained in those text corpora.
A quantification system using PLN tools for the terminological implementation of terms in Basque.
Created by UZEI, this resource detects and automatically extracts multiword lexical units (collocations) from Basque and Spanish.
This tool for the semi-automatic creation of dictionaries uses parallel corpora to detect and automatically extract the term pairs of the correspondences in Basque and Spanish; or in other words, this tool extracts bilingual lexicons.
TRANSLATIONS AND TRANSLATION MEMORIES
Software designed for managing translation memories, generating multilingual and parallel corpora. There are no restrictions regarding the number of languages, and it can be adapted to suit the specific needs of each client.
It automatically detects and sanitizes the personal data in the written texts, in Basque as well as in Spanish.
A tool for guaranteeing the quality and consistency of the text translated to Basque, while optimizing the translation process and making it more cost effective.