ent_ent_index.txt and ent_sent_index.txt files never created

[liusglz]

Hi, I'm trying to get this to work but haven't being able to do so.

I was able to use the preprocessing tool (https://github.com/mickeysjm/HiExpan/tree/master/src/corpusProcessing) and I did got the sentences.json file along with this other files:

AutoPhrase_multi-words.txt
AutoPhrase_single-word.txt
AutoPhrase.txt
entity2freq.txt
entity2id.txt
entity2surface_names.txt
segmentation.txt

Then I go back to CoRel and try:

cd c
bash run_emb_part_tax.sh

But it fails because it can not find the following files:

ent_ent_index.txt
ent_sent_index.txt

I was able to run CoRel with the yelp dataset because I got the ent_ent_index.txt and ent_sent_index.txt files directly from the repo. But how can I create those files from my existing corpus?