qizhex / large-scale-cloze-test-dataset-created-by-teachers Goto Github PK

Hi, I found the default data path argument is "../../data/train.pt", but this file can not be found in your code, so how can I obtain this file? The data file I downloaded only contains CLOTH.

Is the performance in the paper based on all the data or the 3000 sampled questions? If it is the latter, how can I get the same 3000 sampled data as you do for a fair comparison? Thank you!

I had run the src/classifier/prepare_data.py to process the raw inputs，but it didn't work. And I don't know how to deal with this question. "IOError: [Errno 2] No such file or directory: '../../data/train.pt'".
And then I saw this "
#set vocabulary
#vocab = makeVocabulary(get_sentences(tokenize_data(data_dir, "train", difficulty_set)), min_freq =min_freq)
#vocab.writeFile(os.path.join(output_dir, "dict.txt")):"
I tried to remove "#" and ran it again. But there was still a question.
"OSError: [Errno 2] No such file or directory: '../../data/CLOTH/train/middle' "
I would appreciate it if you can resolve my question as soon as possible.