failable

Any news of this?

I second this!

Thanks ! But doesn't word here too. I think faces are useful since it help recognising the items when using fuzzy matching.

> 之所以这么做是因为，尽管entity mention的boundary被DS错误匹配了，但是inner ties是没有受影响的，因此更健壮。 这个可以举一个例子吗。。 另外，还说到unigram更可能是FP，而这种标注方法对这个问题更健壮，似乎我也需要一个例子。。😂

还有一个疑问就是关于高质量phrases，它们是否能为需要识别的实体的类型？（虽然它们没有标签而被标为unknown）如果可以，那它们在AutoNER的第二步不是会被识别为`Entity Type: None`？这样对识别出该种实体没有影响吗？比如Figure 1里的例子应用AutoNER的话，`prostaglandin synthesis`这个实体能被AutoNER识别出类型吗？还是AutoNER本来就没有打算识别它。。（因为它是unknown，所以会被识别为Entity Type: None`）

I feel about 500ms delay to have a response when pressing an Enter with empty input, is it related to this?

What happens if we don't have this `is_complete_request`?

Thanks for the explanation. Although the Jupyter notebook way is a bit different from the traditional comint way, I will vote it if it could speed up the input experience....

README里的例子不是混用吗？

Any news?