Tao Li
Tao Li
@oneTaken Hi, I am working on reproducing BIDAF model as well. But got stuck on dev EM 0.5 while the training EM can go much higher. Changing learning rate and...
Hey it seems a query error. Do you happen to have a local ConceptNet instance running. What is the url used to make the query? Can you print it out?
Hey, sorry for the late response. The issues panel is not actively monitored. For any further question, please email me directly. It seems the issue was due to a later...
Hi, Thanks for reporting the issues. I have just pushed a commit that fixed some minor issues occurred on my end. Pleased give it a shot. The [ERROR 1] will...
Just made another push that forces indices to be long format. My hypothesis is that my numpy int is by default int64, so it worked on my end. Sometimes np.int...
Hey, Thank you for the feedback. The repo is not actively monitored. Sorry about the late response. We are looking at this issue and will update on this soon.
Hey, triple checking the code and the paper, I think it's a typo in the paper. The code is what we did in the experiments. I just submitted a correction...
And we have also updated the arxiv version. FYI.
Hey thanks for the feedback. This is weird though. The training script should run smoothly. Let's debug this. It looks like the preprocessed content word mask is off-aligned with the...
Hey @Lastdier and @92komal, I will get to the experiment and start it from scratch and see what happens. The code for fetching ConceptNet edges is already in the conceptnet.py...