tangjialong

Thank you for finding this error in utils.py. Because this part of the code is directly from TNet (https://github.com/lixin4ever/TNet). I do not check this very carefully. However, I think the...

Thank you again for your careful inspection. I will fix this problem in the future. :-P

Hello, I'd connected with the author of TNet. Such pre-processing error indeed affects the final performances (1-2% accuracy drop). However, after discussing, considering this pre-processing error and the issue that...

Maybe you should check that there is a setting "floatX=float32" in your environment file: ".theanorc".

It seems something wrong with your environment. I'm sorry that I don't have a good solution for this error. Our TNet model is based on https://github.com/lixin4ever/TNet. Maybe you can refer...

And make sure that your theano-0.9.0 can support gpu.

GloVe向量是可以直接去官方网站下载得到的。我们用的是官方处理好的向量文件。

I think it is really easy to obtain comparable results in the paper by the default parameters I set in this code. I have run this code on different machines,...

Because of the small size of data, performance fluctuations are unavoidable.