Ruidan He

All the parameters are already set correctly as default and there is no need to tune. If you follow the evaluation instruction in README, the results should be exactly as...

1) Seems you are using Python 3. The code is tested under Python 2.7. Not sure whether this will affect the results. Also check the versions of other dependencies. 2)...

I used cuda 7.5, cudnn 5.1, theano 0.9.0. But you should be able to run the code with cuda 8.0, cudnn 6.0, and theano 1.0.

I did not record precisions in the paper. Is there a big gap on macro-F1 scores? Which dataset are you talking about? You should be able to get similar results...

@tc-yue which paper are you talking about? (as this issue was originally talking about another paper). For this aspect-level-sentiment paper, the configuration (hyper-params) are selected based on dev set. During...

@tc-yue There are multiple ways to implement multi-task learning. I usually do that in a multi inputs and outputs way as implemented in my code. It should be straightforward to...

The current code print the metrics and losses of train, dev, and test sets at the end of each epoch. If you want to test on other datasets , you...

应该是library版本或者python版本导致的， 请参考README里面的实验环境

You can check the dependency section in README for package versions.

@dongyang12138 目前代码只在python2的环境测试过， 直接换成python3可能有些问题。