ragflow icon indicating copy to clipboard operation
ragflow copied to clipboard

[Question]: Is there any problem with part-of-speech tagging of huqie

Open 1556900941lizerui opened this issue 1 year ago • 4 comments

Describe your problem

Does nr represent the part of speech of a person in huqie.txt?If so, two words such as "金童玉商" and "青禾服装" should not belong to nr, and there are many other words that are marked as nr parts of speech. Looking forward to your reply, thank you

1556900941lizerui avatar Jul 01 '24 07:07 1556900941lizerui

I dojn't think nr is for person, it is for a proper noun.

KevinHuSh avatar Jul 02 '24 01:07 KevinHuSh

Thank you for your answer, but I have one more question. After searching on the Internet, I found that the part-of-speech of huqie.txt contains most part-of-speech abbreviations of the part-of-speech tagg set of Peking University, which makes me think that tagg is carried out in accordance with the standards of this tagg set, and "nr" in it represents the name of a person. What part of speech standard does huqie.txt make part of speech tagging according to?

1556900941lizerui avatar Jul 02 '24 01:07 1556900941lizerui

image

KevinHuSh avatar Jul 03 '24 01:07 KevinHuSh

Ok, thank you for your reply. Could you please send me the link explanation of the corresponding parts of speech, I hope to grasp the specific meaning of each part of speech, and because in my actual scene, I may need to adjust the weight distribution of different parts of speech in the code.

1556900941lizerui avatar Jul 03 '24 01:07 1556900941lizerui

image

@KevinHuSh Could you please send me the link explanation of the corresponding parts of speech?

chongchuanbing avatar Nov 01 '24 06:11 chongchuanbing

What about this.

KevinHuSh avatar Nov 01 '24 09:11 KevinHuSh