This project compare five approachs of sentences embedding using data introduced by ICLR2017 paper
"A SIMPLE BUT TOUGH-TO-BEAT BASELINE FOR SENTENCE EMBEDDINGS" (https://openreview.net/pdf?id=SyK00v5xx) We only test on sentiment task
in this paper.
Five approaches including:
1、implemention of paper "A SIMPLE BUT TOUGH-TO-BEAT BASELINE FOR SENTENCE EMBEDDINGS"
2、tf-idf
3、average glove word vector
4、A brilliant method for Engineering which combine the bag-of-word and word vector,can also be considered as a variety of bag-of-word
pearsonr's coefficient
as follow:
quick start
1、first you should download the glove word2vector glove_model.txt
and place it into dir data/res
2、glove_model.txt
iS too big you can contact me 1174950106@qq.com for the data
3、python main.py "approach" #approach is optional in ["ICLR2017","variety-of-bow","tf-idf","ave-glove-vector"]
-
Notifications
You must be signed in to change notification settings - Fork 2
wenrui2015/sentence-embedding
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
comparation of diffrent approaches of sentence embedding
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published