tomohideshibata

From scratch.

I think most of the codes were from the following google official tf2.0 code. https://github.com/tensorflow/models/tree/master/official/nlp/bert I also tried the pre-training using the above repository, but it failed. I posted an...

Thank you for trying JGLUE. For the first comment, the latest version, v4.19.2, can work. (We have updated the explanation for the huggingface versions via https://github.com/yahoojapan/JGLUE/commit/53e5ecd9dfa7bbe6d84f818d599bfb4393dd639d.) For the second comment,...

> I should change answer_start, shoudn't I? Yes. In the current version, `sep_token` is hard-coded in the dataset. One way to solve this problem is to calculate `answer_start` in the...

Thanks for reporting your results. We are also going to test `run_qa.py`.

Thank you for reporting this issue. Yes, this is a bug. We are going to fix the JSTS label type (string -> float), and perform several experiments. Please wait the...

Sorry for not informing you of the approximate date. However, we have just started setting up the leaderboard, and cannot estimate the expected date yet. We will let you know...

I submitted the same issue before (#36), and I haven't found a solution. I think there may be a numerically unstable function in the code.

In the first row, w201106-0000440969-1 should be w201106-0001643925-3?

@theblackcat102 Thanks for your response. First, the current code does not work due to the operator precedence. The following code would work, but I think it is normal to use...