How Can We Use Massive Multilingual Models for More Inclusive Named Entity Recognition?
Using massive multilingual Named Entity Recognition for more inclusive NLP
Borach Jansema, a machine learning engineer at Slimmer AI, recently published an article in Towards Data Science entitled, “Unlocking Inclusivity Possibilities with Polyglot-NER”, in which he talks about challenges faced when using Named Entity Recognition on non-English data sets.
The English bias prevalent in NER is effectively leaving out a considerable part of the world from this important technological advancement.
In this article, Borach explores the importance of polyglot models and goes into detail on specific models. In later posts, he plans to focus on tests and results.
Follow us on LinkedIn and Twitter for more stories like this.