STC(Short-text-conversation) ntcir12 task code

s1 = similarity (test_post, database_post) s2 = similarity (database_post, database_response) s3 = similarity (test_post, database_response)

final_score = a * s1 + b * s2 + c * s3

use train set and svm_rank to train parameters a, b and c

and finally sorting final score and choose top 10 as my response.

POSTER:

Name		Name	Last commit message	Last commit date
Latest commit History 13 Commits
data		data
svm_rank		svm_rank
test_set		test_set
First_output.py		First_output.py
NTCIR12-STC-LuoC_poster.pdf		NTCIR12-STC-LuoC_poster.pdf
README.md		README.md
second_output.py		second_output.py
stc.pdf		stc.pdf

Provide feedback