Question about CoNLL - Githubissues

mxhofer / Named-Entity-Recognition-BidirectionalLSTM-CNN-CoNLL

Keras implementation of "Few-shot Learning for Named Entity Recognition in Medical Text"

https://arxiv.org/abs/1811.05468

MIT License

178 stars 83 forks source link

Question about CoNLL #3

Open herruli opened 5 years ago

herruli commented 5 years ago

Hi, I would like to ask another question. As I would like to prepare my own data to test out the NER. I would like to know whether the tense including POS tag and Chunk tag matters? Can I just have the Word Tag and NER tag is sufficient?

mxhofer commented 5 years ago

This parser might help you to tag your own data: https://github.com/mxhofer/i2b2_2009-to-CoNLL/blob/master/parser.ipynb. It parses i2b2 medical data to CoNLL format, which is used for this network architecture. It's very easy to add chunk and POS tags with NLTK, so I recommend sticking to that format.