Zoey Li

I have to say, I don’t understand much of the stuff :( So unqualified for editor. On Feb 18, 2020, 2:23 AM -0600, Pinglei Guo , wrote: > Actually I...

Unfortunately, I can't think of any straightforward way to increase recall since the model is trained for generation, using token-level cross entropy loss. Perhaps you can try lowering the probability...

Are there also many cases of multiple argument values for the same role in your training dataset? I would suggest that you experiment with different templates. What worked for me...

Seconding this request. Willing to contribute to related chapters.

The two files are processed by us. See the end of the README.md for instructions on how to download these files. Note that only Span F1 (should be the original...

Hi Cresent73, It is true that the current code base does not cover the entity type statement. It was originally implemented as a postprocessing script that takes multiple decoding results...

It's generally not a good idea to make BART output very long sequences (if you think of concatenating the filled templated with all of the type statements). One workaround is...

Hi Tianhao, Just to let you know that I am trying to solve this issue but unfortunately, I don't have enough Google storage space left to host all of the...

Hi Changhy, Sorry about this, I checked the code and it seems the problem is in the test_kairos.sh script. `--mark_trigger` is one essential argument. (Note that if you have a...

btw, the fixed scripts are uploaded.