Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
tyx_neu f20b438392 | 1 year ago | |
---|---|---|
.. | ||
data | 1 year ago | |
README.md | 1 year ago | |
const.py | 1 year ago | |
corpus.py | 1 year ago | |
data_loader.py | 1 year ago | |
lstm_cnns_crf.png | 1 year ago | |
model.py | 1 year ago | |
optim.py | 1 year ago | |
train.py | 1 year ago |
Module implemention from "CEnd-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF".
Perform experiments on the English data from CoNLL 2003
python3 train.py -h
You will get:
usage: train.py [-h] [--epochs EPOCHS] [--batch-size BATCH_SIZE] [--seed SEED]
[--cuda-able] [--lr LR] [--use-crf] [--save SAVE]
[--save-epoch] [--data DATA] [--char-ebd-dim CHAR_EBD_DIM]
[--kernel-num KERNEL_NUM] [--filter-size FILTER_SIZE]
[--word-ebd-dim WORD_EBD_DIM] [--dropout DROPOUT]
[--lstm-hsz LSTM_HSZ] [--lstm-layers LSTM_LAYERS] [--l2 L2]
[--clip CLIP]
LSTM CNN CRF
optional arguments:
-h, --help show this help message and exit
--epochs EPOCHS number of epochs for train
--batch-size BATCH_SIZE
batch size for training
--seed SEED random seed
--cuda-able enables cuda
--lr LR learning rate
--use-crf use crf
--save SAVE path to save the final model
--save-epoch save every epoch
--data DATA location of the data corpus
--char-ebd-dim CHAR_EBD_DIM
number of char embedding dimension
--kernel-num KERNEL_NUM
number of kernel
--filter-size FILTER_SIZE
filter size
--word-ebd-dim WORD_EBD_DIM
number of word embedding dimension
--dropout DROPOUT the probability for dropout
--lstm-hsz LSTM_HSZ BiLSTM hidden size
--lstm-layers LSTM_LAYERS
biLSTM layer numbers
--l2 L2 l2 regularization
--clip CLIP gradient clipping
python3 train.py
Acc: 91.5%
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》