#sen_simi_cal
test email...
Calculate sentence similarity by word vector
To do list:
DONE 1. Use jieba to cut Chinese sentences (probably add specific word dic before doing this)
DONE 2. Load trained Chinese word vector file (binary format)
DONE 3. Process original data and get the core words (~100k)
DONE 4. Define function that calculate the sentence vector (input: cutted sentence and word vector; output: sentence vector)
DONE 5. Define function that calculate sentence similarity