The European green taxonomies

Taxonomy is a word that suddenly appeared with financial investors and the public at large when the European Commission published its own taxonomy on sustainable activities.

Let’s quickly recall that a taxonomy is a term which originates from biology and that designates the naming in an ordered system that is intended to indicate natural relationships.a language.

In the case of the European Commission, it came down to the question whether gas and nuclear energy should be classified as energies with a favorable impact on the environment or not. In this case, it is easy to understand the consequences of such a classification for investors… and for the rest of human beings. beings.

Taxonomies at the heart of IT systems

Dictionary, thesaurus (a taxonomy without a hierarchy), taxonomy, and even ontology (a taxonomy enriched with subjective philosophical or political hierarchies) are concepts that are often used in enterprises. In fact, each business domain has its own taxonomy.

For R&D, it is the technical, scientific and medical language of researchers in each discipline.

Whether you are a lawyer, a tax expert, an economist or a financier, each domain has its own expressions, often shared by professionals, that also includes terms and hierarchies that are highly specific to the company. This is also the case when it comes to analyzing the opinions of clients, whose expressions vary according to social categories, age groups and interests.

Legal thesaurus to build a text annotator

Taxonomies and Natural Language Processing

There are many tools available today to analyze all this documentation. Some are well known: search engines, semantic analyzers, automatic categorization or summary tools. Others are less well known: word embeddings, language models, training dataset, annotators, gazetteers, etc…

However, it is essential to add to all the above-mentioned tools your own and unique taxonomies: to obtain more detailed understandings, and by the way superior to the know-how by direct competitors, to know what is happening in a particular sector of activity, to track what customers say, to monitor its economic, legal or financial environment or to find the most relevant or innovative technical or scientific documentation.

Natural Language Processing allows companies to create dictionaries and taxonomies from documents but also to prepare solid data governance using advanced artificial intelligence analytics, including solutions like recommendation engines or automated text classification systems.

Automatic annotation with legal thesaurus and Wikidata

Companies that neglect this area are condemned to remain blind and deaf and are therefore vulnerable in a world where every change, every single announcement or every discovery can be an opportunity or a threat.