André

Hi @vedaanth , That would be a really nice feature to have in the library. However, I am currently very busy and don't have enough time at the moment to...

Indeed having a XLNet reader would be a nice addition to cdQA given its results on the QA tasks. The @huggingface community is currently implementing XLNet in their Transformers repository....

Implementation of `XLNetForQuestionAnswering` is pretty different from `BertForQuestionAnswering` and the official HF version does not output the logits for now. (cf. https://github.com/huggingface/pytorch-transformers/issues/838) `XLNetForQuestionAnswering` uses Beam Search to find the best...

Hi everyone, Coincidently, @fmikaelian and I just discussed this a few hours ago. Unfortunately, I got involved in other projects at the beginning of the year and recently started a...

Hi, could you please provide us with more information? eg: the code you are using, the structure of your data and the whole traceback you get from the error? Thanks

There's no support for pySpark RDDs and it's not currently in our roadmap. There are a lot of other features we are working on right now and we are very...

Hi @Drastic, I am afraid the repo as is does not work well on languages that don't have the same alphabet and word structure as English. I know nothing about...

I understand. I have to point out that we use BertTokenizer in the preprocessing phase and BasicTokenizer in the postprocessing phase: https://github.com/cdqa-suite/cdQA/blob/50e10443bc37b7bd3546465d37059260f29549f0/cdqa/reader/bertqa_sklearn.py#L969 https://github.com/cdqa-suite/cdQA/blob/50e10443bc37b7bd3546465d37059260f29549f0/cdqa/reader/bertqa_sklearn.py#L813-L815 You can check what is the vocabulary...

Hi @BojanKovachki, This `verbose_logging` parameter is inspired by the same arg used in the Hugging Face `run_squad.py` script. Actually it provides some information about the preprocessing and the training configurations....

> Implementation of XLNetForQuestionAnswering is pretty different from BertForQuestionAnswering and the official HF version does not output the logits for now. XLNetForQuestionAnswering uses Beam Search to find the best (and...