FlowQA

FlowQA copied to clipboard

Hello, I want to ask a question. What is the version number of the package in the requirement document？

hhhhhqqqqq

EOFError: Ran out of input

5

When I execute python train_QuAC.py,there are errors as following: Traceback (most recent call last): File "train_QuAC.py", line 324, in main() File "train_QuAC.py", line 175, in main model = QAModel(opt, train_embedding)...

zou-longkun

Can you know which part of the code the hidden representation described in the paper is?

tmdwls2805

Hi, Thank you for releasing the code! Could you please also share the code corresponding to the SCONE experiments?

hugochan

I see that the FlowQA has already got a score on the leaderboard of the CoQA. CoQA requires run experiments on Codalab. So , Do you have a docker image...

ZhengDeQuan

QuAC does not work when '--no_elmo' is set

2

Yash-5

As a recent SOTA model in dialog QA, do you plan to add the FlowQA model to AllenNLP library? Or other NLP library such as fairseq and openNMT.

xptree

a question in predict for CoQA

2

Hello, I want to ask a question. In the training, each question is provided with previous N gold answers, and it is also operated on the development set, but at...

WSTC2007

This fixes issue #20.

Yash-5

what is "dialog_ctx * 3" means in general_utils?

1

hi, i don't know what the means of "*3", what 3 means? `context_feature = torch.Tensor(batch_size, question_num, context_len, \ feature_len + (self.dialog_ctx * 3)).fill_(0).to(self.device)` and `if prv_ans_choice == 3: # There...

susht3