bi-att-flow
bi-att-flow copied to clipboard
allenai
Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to ach...
Dear Team, The code below doesn't work and the context doesn't sententce token. if args.tokenizer == "PTB": import nltk sent_tokenize = nltk.sent_tokenize def word_tokenize(tokens): return [token.replace("''", '"').replace("``", '"') for token...
I am trying to run this benchmark using a compiled version of the dev branch. The execution environment consists of python 3.5 and tensorflow 1.2 compiled with MKL support. I...
Traceback (most recent call last): File "C:\Users\MSI\AppData\Local\Programs\Python\Python36\lib\runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "C:\Users\MSI\AppData\Local\Programs\Python\Python36\lib\runpy.py", line 85, in _run_code exec(code, run_globals) File "C:\Users\MSI\bi-att-flow-dev\basic\cli.py", line 119, in tf.app.run() File "C:\Users\MSI\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\platform\app.py", line...
In the paper it gives the impression that when M is computed, you feed that to a bidirectional LSTM to get M^2. However in the code base there are a...
Hey, I was wondering if it is possible to upload a trained model for the CNN\Daily Mail to CodaLab as you did for the SQuAD. This will be very helpful....
I want to reduce the size of data enormously to just 500 Question from something around 200 passages or less. I do not care about the accuracy or F1 score,...
When predicting answer, sometimes I get empty answer, however the score is high enough. Finally I locate the problem. A function called `_get2` at line 284 and 382 in file...
In `model.py/_build_loss()`, when computing the average loss of start position `ce_loss`, `loss_mask` is used to avoid counting in these samples where `0 == len(question)`. However, when computing the average loss...