search

kyzhouhzau / BERT-NER

Use Google's BERT for named entity recognition （CoNLL-2003 as the dataset）.
MIT License
1.25k stars 334 forks source link

BERT-NER and conll 2003 for research in industry #67

Open ahmadshabbir2468 opened 5 years ago

ahmadshabbir2468 commented 5 years ago

Hi, I new in the field of NLP Kindly guide me . i want to train Ner for on new entities i.e i have to find Programming keywords from CV and build context and I found Google bert (https://github.com/kyzhouhzau/BERT-NER) is best for ner training but google bert use conll 2003 and conll-2003 is available for research purpose only

As my work is around finding programming keywords and I dont need ner corpus for (People ,Loc and other entities etc) so can i use google bert or other repo which use conll-2003 format in industry ?

Thanks

tanmayag78 commented 5 years ago

Hey do lemme know if you find anything related to industry.

zwd13122889 commented 5 years ago

Hey, i want to know the data set.The first raw is word ,the fourth raw is the label, what's the second and third raw meaning? Another question is the output label_test.txt , its second and third raw are same, does it have another meaning ?