Sujit Pal

Did you check that this actually happens? I just tried this sentence "All new. Norfolk gets a facelift" (because there is a New Norfolk (id:2155415) in the cities list) and...

Yes, my field type is little different from the one suggested in the QUICK_START.md. That is why I wasn't sure if you saw the same thing I was seeing. As...

Hi @ynuwm sorry but I don't have the index data anymore. The README.md file has a link to the flashcards data that I used to generate it. You will need...

That is expected, as long as it's not the same set of flashcards that get attached to every story. The idea is that you are treating the flashcards as background...

Thanks for debugging! Might be worth doing [x.decode("utf8") for x in stories] to convert to string. I don't have access to the data anymore, so can't test, but since you...

Right now it's not a true Python package, if you copy it to your current directory and put "import custom_attn", then you should be able to refer to the custom...

Thank you for the detailed advice and the pointers. I will probably need some time to digest all this. The bloom filter embedding sounds like a very cool trick, I...

I was able to solve this locally using the following. replace `args.s` and `args.t` in `question.py` with `args.sentence` and `args.question_type` respectively, i.e. the long forms of the two arguments. Maybe...

Also needed the Crabbe + Candito FR POS tags to convert POS tags generated by pretrained OpenNLP French POSTagger to Universal POS tags, so found this mapping contributed by @duhaime...

Wanted to mention here that I merged your fix into my fork of auquantoolkit and then tried to use it in the Coursera lab on momentum strategies and it still...