Open BrambleXu opened 4 years ago
Summary:
通过文本挖掘的技巧来生成domain-specific lexicon
Resource:
Paper information:
Notes:
The coverage is the proportion of vocabulary covered by the lexicon 这里的coverage定义就比较简单了。直接拿test set里所有的entity在lexicon里进行检索,找到的概率越高,说明coverage越高。(找到的entity / test set里的所有entity)。这不就是recall嘛
Model Graph:
Result::
Thoughts:
Next Reading:
Summary:
通过文本挖掘的技巧来生成domain-specific lexicon
Resource:
Paper information:
Notes:
The coverage is the proportion of vocabulary covered by the lexicon 这里的coverage定义就比较简单了。直接拿test set里所有的entity在lexicon里进行检索,找到的概率越高,说明coverage越高。(找到的entity / test set里的所有entity)。这不就是recall嘛
Model Graph:
Result::
Thoughts:
Next Reading: