A single Named Entity Recognition model that is trained jointly on many languages simultaneously is able to decode these languages with better accuracy than models trained only on one language . The model could be used to make zero-shot predictions on a new language, even ones for which training data is not available, out of the box . The results show that this model not only performs competitively with monolingual models, but it also achieves state-of-the-art results on the CoNLL02 Dutch and Spanish datasets, OntoNotes Arabic and Chinese datasets. Moreover, it performs reasonably well on unseen languages, achieving state of the art for zero-shots on three CoNll languages. It can also be used out-of the box for new languages, even if training data isn’t available, to make predictions on new languages that are not available in the training data available to the new language. The model can be used in the new data is available to identify new languages. The results are published in the journal’s open-source version of this article .

Links: PDF - Abstract

Code :


Keywords : languages - model - data - language - results -

Leave a Reply

Your email address will not be published. Required fields are marked *


Enjoy this blog? Please spread the word :)