Repurposing KGBART for storytelling
Opened this issue · 3 comments
Hello. I'm interested in using KGBART to create a model capable of generating stories usin commonsense. I have a dataset with stories and the respective refered concepts. What I did was separate my dataset into train, test and dev sets and then created two files for each set: one containing a set of concepts per line (the src) and other with the correpsonding stories (the target).
But I think I need to preprare this data, right? I need to generate the knowledge graphs for the KGBART model?
I've tried to preprate the data as instructed (run reorder.py, conceptnet.py, train the entity and embedding using TranE), however when I trie to generate the one hop graphs by running entity_onehot.py it says that "commongen.train.index.txt" is missing.
What is this file? How should I generate it?
Thank you in advance.
Hi， I also got the issue, but I resolved this by run "formatter.py" in the path of "dataset/commongen_data/". Wish it is useful for you.
Hello @ana3A , I am curious to know if you were able to succeed in repurposing KG-BART or if it didn't work out. If you were able to get it to work, I would like to know more about how it went, although that might be a conversation best kept away from the comments here.
你好，我也遇到了这个问题，但是我通过在“dataset/commongen_data/”路径中运行“formatter.py”解决了这个问题。希望它对你有用。
Where are the conceptnet_train. txt and conceptnet_dev. txt in the formatter.py file