-
@karkaroff, @achyudhk do you think we need Castor compatible character level CNN ?
-
## How to load AG_NEWS data from local files
I can't get ag news data with `train_iter, test_iter = AG_NEWS(split=('train', 'test'))` online because of my bad connection. So I download the the `tra…
-
Hi,
Really impressive work and a nice repository combining all the NER models.
I was trying to comprehend the codebase and what all are its capabilities. To that end, I made a list of NER-baselines …
-
@achyudhk reports that CharCNN on some dataset uses 63GB of RAM (Hydra and Dragon both have 64GB). I think a solution would be some mechanism for moving data between disk and RAM when needed?
-
I am trying to recreate your results from Synthetic and Natural Noise Both Break Neural Machine Translation and run the model on my systems.
Is there any documentation about how to run the model, …
-
do the csvs happen to be available anywhere - public dataset somewhere?
https://github.com/mhjabreel/CharCNN/tree/master/data/ag_news_csv
they are mentioned here:
https://github.com/johnb30/py_cr…
-
When subclassing existing modules, a common use case I've encountered is to automatically fill certain arguments of the super class constructor based on HParams values. By design, HParams are realized…
-
Hi, sorry for asking about something that is explained in the repository, but it took me two days to deal with changing data directory and I didn't manage to do it.
I want to test NER model on my o…
-
We can implement capitalization token features in our common context encoder. I propose following categorized features: `allUpper`, `allLower`, `upperFirst`, `upperNotFirst`, `numeric`, `noAlphaNum`.
-
## 論文リンク
https://arxiv.org/pdf/1711.02173.pdf
## ひとことで言うと
文字ベースNMTにおいて人工ノイズの影響を調べた論文
## 概要
人間は例えば以下のような文字レベルのノイズがあっても文を解釈できる
![Screen Shot 2020-10-23 at 15 49 44](https://user-images.g…