A working group of the XBRL[1]-Europe Association developed a taxonomy system which connects different concepts coming from different national legislations to each other. The system elaborated by a working group of the Monnet European research project extracts all labels associated with a particular expression automatically. Now they are focusing on the Belgian and Spanish taxonomies. This system allows a semantic processing.
Have a look to the publication
[1]eXtensible Business Reporting Language
Multilingual extraction refers to the process of extracting information from a variety of languages. In the business domain, multilingual extraction can besed to gather information from global sources in order to make informed decisions. This could include extracting data from financial reports, news articles, and other relevant sources in multiple languages. The extracted information can be used for market analysis, competitive intelligence, and other business purposes.
There are several tools and techniques that can be used to facilitate multilingual extraction. One approach is to use machine translation to translate the source documents into a common language, and then use natural language processing (NLP) algorithms to extract the relevant information. Another approach is to use NLP algorithms that are trained on multiple languages, such as multilingual language models, to directly extract information from the source documents.
where is the link to the publication?
hi Sylvie, click on the word “publication” or on the following link http://www.ep.liu.se/ecp/072/006/ecp12072006.pdf
you can get more info on Extensible Business Reporting Language here https://www.xbrl.org/