Closed roozbehsadeghian closed 7 years ago
Hi,
There's an example in the README.md of how the sentences should look like in your dataset: Example: to be ,COMMA or not to be ,COMMA that is the question .PERIOD You might run into problems if the test dataset has too few words in it. If your minibatch size is 128 and sequence length 200 (the default values) then training, development and test datasets should have at least 25600 words each.
See ./example directory for an example dataset
Hi,
I was trying to run the code but I was stucked in reading the data files (train, dev). Is it possible for you to provide some sample data?