Tutorials on training the Skip
Tutorials on training the Skip-thoughts vectors for features extraction of sentence.
The, it's time to get the 2100# features now.
2. Open and download the tensorflow version code.
Do as the following links: https://github.com/tensorflow/models/tree/master/skip_thoughts
Then, you will see the processing as follows:
the dataset used in skip_thoughts vectors is from [BookCorpus]: http://yknzhu.wixsite.com/mbweb
For this moment, you already defined the environment, then, you need also do the followings:
(2). input the following code to the terminal:
Now that, you have obtain the features of the input sentence. you can now load your texts to obtain the results. Come on ...
unzip these files in the current folders.
[Attention] when you install the bazel, you need to install this software, but do not update it. Or, it may shown you some errors in the following operations.
(1). First, open a terminal and input "ipython" :
1. Send emails and download the training dataset.
first, you should send a email to the auther of this paper and ask for the link of this dataset. Then you will download the following files:
3. Encoding Sentences :
You can see the results of the algorithm as followings: