Di Jin

question for version

5

I noticed that in the log file, the version "baseline+attentive pooling" can get the result: 05-10 21:12 Epoch: 21 Train: 94.81% Test: 75.19%. What are the model configurations in details...

how to tune hyper-parameters to balance between sentiment accuracy and BLEU score

3

hi, I tried re-running your code without changing any hyper-parameters, however, I got this result: 0-1_Test(Batch:1600) Senti:77.300 BLEU(4ref):61.125(A:55.520+B:66.730) G-score:68.738 H-score:68.267 Cost time:2.57. Could you provide some experience about how to...

Segmentation fault (core dumped)

2

When I used "ImageData" layer in this version of Caffe to read an image and a label, I received the error of "Segmentation fault (core dumped)". There is no such...

Hi, have you tried to pull request into the tensorflow contrib layer? That would be much more convenient to use your code! Thanks!

Could you also provide code for preparing the training data?

1

Hi, could you also help provide the code for getting and processing the training data? BTW, in the train data, there are many weird tokens like "", which are also...

file "qkr_train.src.10000" is missing

2

When I ran "bash test.sh", I encountered this error: Traceback (most recent call last): File "PPL.py", line 22, in from PPL_modeling import BertForPreTrainingLossMask File "/home/ec2-user/ZRKGC/PPL_modeling.py", line 56, in with open("qkr_train.src.10000",...

Hi, I tried to run this code but encountered one problem: there are several special tokens such as "", "", and "" after bert tokenization, however, the original bert vocab...

what is your method for generating the back-translated data augmentation

1

hi, could you share more info about the scripts or tools you used for generating the back-translated data augmentation? Thanks!

When will you release this code?

2

Hi, I really enjoyed reading your paper, and I am wondering when you can actually release the code. Thanks!