Runqi Yang
Runqi Yang
Yes, there should be only those modifications you mentioned. The most tricky part should be the Chinese SpaCy models, which are not officially supported.
You should tokenize your Chinese data first. Prepare your data as "这是 一个 分词 后 的 样例" (separate tokens by spaces) and provide corresponding POS and NER tags. This not...
Hello, You can use `scores[s_idx, e_idx]` in function "predict"(https://github.com/hitvoice/DrQA/blob/master/drqa/model.py#L98) to get the prediction score and return it. A warning: The score is not calibrated, which means in real applications there...
This will not affect the fairness of the dev set evaluation. Here's why: 1. Whether a word is UNK is completely determined by whether it appears in GloVe, which does...
Got it. Thanks for answering!
看最新的ReadMe已经有了
标题：Deep Learning for Natural Language Processing 自然语言处理和深度学习 链接： * 课件 http://cs224d.stanford.edu/syllabus.html * 视频 https://www.youtube.com/playlist?list=PLlJy-eBtNFt4CSVWYqscHDdP58M3zFHIG 作者：Richard Socher 标签：深度学习; 自然语言处理
标题： Deep Learning Papers Reading Roadmap 深度学习论文阅读路线图 链接： https://github.com/songrotek/Deep-Learning-Papers-Reading-Roadmap 作者： [Flood Sung](https://github.com/songrotek) 标签： 深度学习
I had the same issue without using sentry. It worked after downgrading `werkzeug`. I think it's a bug from there.
没有什么特别的，用一个靠谱的中文词向量就好。