sjchasel

Does Neuspell have this function: we can find each error and know the type of this error, or we can know what kind of syntax error does this error fall...

I download ```model.pth.tar``` and ```vocab.pkl``` of subwordbert-probwordnoise from google docs by myself, the copy them to ```/environment/python/versions/miniconda3-4.7.12/envs/sj/lib/python3.7/site-packages/neuspell/../data/checkpoints/subwordbert-probwordnoise```. When I run ``` checker = BertChecker() checker.from_pretrained() ``` It warns ``` Some...

about training rl model

7

I have trained catSeq model and its performance is as your reported. When I use `python3 train.py -data data/kp20k/kp20k_separated/rl/ -vocab data/kp20k/kp20k_separated/rl/ -exp_path=exp -exp catSeq_rl_kp20k -epochs 20 -model_path=model/catSeq_rl_9527 -copy_attention -train_rl -one2many...

I note that you visualize phrases with T-SNE projection in your new paper. Could you tell me what method did you use to get the phrase representation？

In your paper, the input of the word distribution over vocabulary is a context-rich representation `c_t=[u_t; s_t; c_text + c_fuse]`. But in your code, it seems that you only concate...