Joint-Extraction-of-Entities-and-Relations-Based-on-a-Novel-Tagging-Scheme

Joint-Extraction-of-Entities-and-Relations-Based-on-a-Novel-Tagging-Scheme copied to clipboard

缺少train.json

7

我在跑这个模型是，发现少了一个train.json文件，请问下，这个是字母得到的。我看文件里面是没有这个的，train.txt也没有 

mzc421

Excuse me, can this model be used to run Chinese data sets

3

I converted the dataset to Chinese dataset but there was an error. Traceback (most recent call last): File "E:/PycharmProjects/LSTM_LSTM_Bias/train.py", line 276, in train() File "E:/PycharmProjects/LSTM_LSTM_Bias/train.py", line 168, in train loss...

lalala1020

Does anyone know how to get the NPY file？

3

syfshigechunvzuo

syfshigechunvzuo

Is it an error, or was it implemented like this for simplification purposes? Paper:  Code: https://github.com/gswycf/Joint-Extraction-of-Entities-and-Relations-Based-on-a-Novel-Tagging-Scheme/blob/78b664f0007e0668e16e679ff11522ad660d4f40/model.py#L64-L79

ivsanro1

i have already download your update in Google.drive， but when i run train.py ，there are sone errors in model.py，in “def forward” ,char_output 's dimensions is wrong

3

z786760876

I found a mistake in predict.py and it will have an influence on the evaluation result

1

There is a mistake in the 206 row in predict.py 206 temp[relation_label][int(role) - 1].append(idx) if pos == "B" or pos == "S": if relation_label not in temp: temp[relation_label] = [[],...

coderGray1296

I read the data.py and found that seems overlaps of tags are just counted but not used in sentence tag. After data precessing, there are a hug number of overlap....

baudzhou

why do you all use train_data in function get_batch in function evaluate ?

1

mymxhdd