Most news organizations have realized that keeping a list/database/taxonomy of all the interesting entities they write about, takes a lot of work. Some have built up extensive databases over the years or are using external sources such as Wikidata, but new entities just keep popping up and old ones need to be maintained on top of that. This is perhaps the most challenging aspect of taxonomy management. What if you could significantly simplify this process?
In this Living Talk we will talk about how this is possible using a combination of NLP techniques such as Information Extraction, Named Entity Recognition and Entity Disambiguation. We are also going to tell you about auto-tagging AI-startup iMatrics' on-going project, called ConceptCore 2.0. Which includes this as one of the highest anticipated features.
Speaker of this meetup is Christoffer Krona, Co-Founder and CTO of iMatrics.