Issues
- 10
- 0
如果要训练中文的模型有对应的预训练模型吗?
#35 opened by xyxhchb - 2
AAPD 数据集无法下载
#25 opened by cjopengler - 13
关于运行效果到不到论文中进度的问题
#31 opened by NLPER-luo - 0
- 0
- 5
- 0
About train/test split of RCV1
#32 opened by yzhangcs - 0
- 3
The text in dataset seems no meaning
#26 opened by MaYB2333 - 0
beam设置的问题
#29 opened by terminator123 - 1
AAPD Dataset
#28 opened by rajcscw - 1
config.yaml是SGM的配置文件还是SGM+GE的配置文件?
#21 opened by WrRan - 0
添加license
#27 opened by shenlanyilang - 2
请问用preprocess处理后的训练数据集的标签有没有按照标签的频率排序呢
#18 opened by HaimianYu - 14
The size of tensor a (576) must match the size of tensor b (64) at non-singleton dimension 1
#12 opened by mochp - 1
运行了你的代码,设置了GPU,但是GPU显示存在任务,但没有占用GPU,gpu空转
#23 opened by cm-xcju - 2
运行preprocess.py时出错
#10 opened by hanyegirl - 1
想问下关于评价的问题
#22 opened by Canadalynx - 2
why sorting matters?
#7 opened by eveliao - 1
解码的时候LSTM输入的问题
#17 opened by HaimianYu - 0
请问能不能提供一下基准模型的代码呢
#19 opened by HaimianYu - 1
Where is the tgt seq in loss computation?
#9 opened by Decalogue - 6
dataset words repeat so many times.
#11 opened by Langjiaqi - 7
- 0
Definition of loss function
#1 opened by JianWenJun - 1
RuntimeError: While copying the parameter named decoder.embedding.weight, whose dimensions in the model are torch.Size([58, 256]) and whose dimensions in the checkpoint are torch.Size([107, 256]).
#3 opened by SeekPoint - 1
What is the format of label_test?
#5 opened by linxid - 6
预测为 label 序列,例如 MCAT ECAT M13 M131 E12
#4 opened by Decalogue - 1
请问词向量是随机初始化的吗
#15 opened by HaimianYu - 1
- 0
Attention layer
#13 opened by nooralahzadeh - 1
does the order of predicted labels matter? and what if the length of prediction is not the same as ground trut?
#6 opened by eveliao - 1