monoid/ner-study
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
17 Commits 1 Branch 0 Tags 5.9 MiB
Jupyter Notebook 92.9%
Python 7.1%
30cb6b8fe0
Go to file
monoid 30cb6b8fe0 feat: tagIdConverter size property
2022-02-22 23:35:59 +09:00
[Ko, En] NER, POStag data init 2022-02-14 08:28:54 +09:00
engpre feat: support english 2022-02-22 18:59:07 +09:00
.gitignore feat: add count freq and save model 2022-02-18 18:33:51 +09:00
Batch.ipynb init 2022-02-14 08:28:54 +09:00
count_tag_freq.py feat: count tag frequency 2022-02-18 18:31:53 +09:00
cuda_test.py init 2022-02-14 08:28:54 +09:00
dataset.py refactor: free tagIdConverter 2022-02-22 17:23:14 +09:00
dataset.test.py test(dataset): change assertEquals to assertEqual 2022-02-18 17:28:31 +09:00
eng_tags.json feat: add eng_tag 2022-02-22 16:47:16 +09:00
env.yaml init 2022-02-14 08:28:54 +09:00
groupby_index.py ADD: add line sep 2022-02-22 16:31:56 +09:00
groupby_index.test.py feat: add groupby_index 2022-02-18 17:29:46 +09:00
LICENSE init 2022-02-14 08:28:54 +09:00
preprocessing.py feat: support english 2022-02-22 18:59:07 +09:00
Processing.ipynb init 2022-02-14 08:28:54 +09:00
read_data.py feat: tagIdConverter size property 2022-02-22 23:35:59 +09:00
README.md docs: fix typo README.md 2022-02-14 08:35:57 +09:00
Training.ipynb refactor: free tagIdConverter 2022-02-22 17:23:14 +09:00

README.md

Ner Task Study(Multilingual Bert finetuning)

If you want to create the conda env,

conda env create -f env.yaml

To prepare the data, you should execute the following commands:

python read_data.py
python preprocessing.py