Task Adapters

CONLL2003

CoNLL-2003 shared task:language-independent named entity recognition is a dataset corpus consisting of the Reuters news stories between August 1996 and August 1997. Each line of the corpus has four fields: the word, its part-of-speech tag, its chunk tag and its named entity tag. We used chunked tag field.

chunk/conll2003@vblagoje bert-base-uncased

1 version Architecture: pfeiffer Head:

Pfeiffer Adapter trained on "Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition" with F1 score of 91.3. See example notebook at https://bit.ly/33Nh84t