Chinese entity HiExpan issues

[weather319]

Hi jiaming,
Thanks for your idea and codes. When I run those codes in Chinese corpus, I found some issues:

• First, Dependent syntax and part of speech seem to be unnecessary in corpus processing.

• Second, getCombinedWeightByFeatureMap function use too much time when the featuresOfSeed size is large(the skip gram patterns size reaches hundreds of thousands of levels). So I only retained the 600 features with the highest score and standard length in "eidSkipgram2TFIDFStrength.txt" for each entity. This method reduced the run time from 30 hours to 30 minutes, but there is the possibility of reducing the accuracy of the calculation of the combinedWeight score.

• Third, type feature is useless for Chinese, I have to use the LDA model's score instead. Now I am evaluating the effectiveness of this method.

• At last, I didn't find the code for the Taxonomy Global Optimization section. Where can I find it?

[fredia]

Hi weather319，I also want to use HiExpan in Chinese corpus, but the porbase which HiExpand used to extract features does not suit Chinese， would you like to share which Chinese probase did you use or how did you extract type feature in Chinese？ Thanks！