How did you generate the input data files like data.pkl, word2id and word_embedding.pkl ?

Open yangliuy opened this issue 6 years ago • 4 comments

Firstly thanks for the great ACL paper and open source code!

I have a question on the data preprocessing part. How did you generate the input data files like data.pkl, word2id,vocab.txt and word_embedding.pkl ? Let's take UDC as the example. The raw data only contains train.txt/valid.txt/test.txt. I checked your code and there are no scripts on generating these files like data.pkl and word_embedding.pkl. Could you also upload these data preprocessing scripts ?

Mar 05 '19 01:03 yangliuy

Hi,

We got those data by hacking the source code of SMN, to make sure that our experimental data sets are the same.

Xiangyang

Mar 05 '19 02:03 xyzhou-puck

Hi Xiangyang,

Thank you for your reply! I found a similar question here #5 . I will check the preprocessing code of SMN.

Mar 05 '19 04:03 yangliuy

You are welcome.

Mar 05 '19 08:03 xyzhou-puck

Hi! Do you know how to deal with .w2v file? How to transfer it to word_embedding.pkl?

Apr 16 '19 13:04 MASTERPlECE