Junyang Lin comments

Results 173 comments of


                                            Junyang Lin

the format of input

I am interested in the prediction of next sentence. If the input data are all continuous sentences, how can the model randomly select 50% for the continuous and 50% for...

训练耗时？

这是因为早期的时候用单向lstm，参考斯坦福那边的做法将首尾顺序反过来，效果能更好。现在用了双向的lstm做encoder，翻转影响已经不大了

训练耗时？

> > 请问一下你们的模型在LCSTS数据集训练好大概需要多长时间呀？ > > > 请问一下你们的模型在LCSTS数据集训练好大概需要多长时间呀？ > > 您好，可把你的LCSTS数据集共享给我吗？[[email protected]](mailto:[email protected])，谢谢可以跟LCSTS的作者要

lcsts数据集训练时，ROUGE报异常 Illegal division by zero

全部映射成id处理，数字也视为character，转换成id就行。 ps 这个pyrouge也比较麻烦不太好用，我尽快更新一个比较好用的计算rouge的脚本

Some trouble when running your code

> 那请问可以把你处理好的saved_data传到我的邮箱吗？[[email protected]](mailto:[email protected]) ,我按着作者所说的处理方式在train的时候报错RuntimeError: Length of all samples has to be greater than 0, but found an element in 'lengths' that is

Some trouble when running your code

> Traceback (most recent call last): > File "train.py", line 322, in > main() > File "train.py", line 314, in main > train_model(model, data, optim, i, params) > File "train.py",...

Some trouble when running your code

> Traceback (most recent call last): > File "train.py", line 322, in > main() > File "train.py", line 314, in main > train_model(model, data, optim, i, params) > File "train.py",...

Gigaword Validation Data

This problem may stem from empty lines in your dataset. Check if you have this issue.