semanticRetrievalMRS
semanticRetrievalMRS copied to clipboard
easonnie
This is the repo for the paper "Revealing the Importance of Semantic Retrieval for Machine Reading at Scale".
This looks like a wonderful model. However, when I run your model according to your README.md, it gave me em,f1,prec,recall all about 0.04. Is there any thing I should change...
The file is too large, is their any way by which I can directly download it on an ubuntu server. I tried wget and other alternatives, but those does not...
I tried to train the model on a single GTX2080 GPU but got CUDA out of memory error. Can you provide your system configuration? Especially the GPU configuration to successfully...
I'm still going through all the scripts... is there an easy way to run an interactive shell to test/ask new questions? thanks,
The file whole_for_rindex.db is too big for me to download. How does it come from? Can I create it locally?
I got lots of warnings from logger.warning("Can not find answer span from whitespace-tokenized context, there might be a problem") logger.warning("Could not find answer: '%s' vs. '%s'", a, b) I checked...