How to improve bist model accuracy? :Bistmodel about nlp-architect HOT 6 CLOSED

Any answer?

from nlp-architect.

@danielkorat, can you please help?

from nlp-architect.

@peteriz, thank you for requesting @danielkorat. This is very important to my project. I would like little lesser errors in parsing job descriptions. I guess improving the accuracy would result in fewer parsing errors. Please clarify this one too. I can always give it a try after improving the accuracy.

from nlp-architect.

Hi @ravishpankar, sorry for the delayed response.
93.8 UAS is the score reported in the original paper and original code implementation. As mentioned there, this result is reported on the Penn TreeBank Dataset (Stanford Dependencies).
Training on a different dataset might yield different results.

from nlp-architect.

Hi @danielkorat, Thanks a lot for answering. I understand that universal dependencies 2.0 en dataset is different from Penn tree bank dataset which is based upon Stanford dependency relations. Now the question is how did you train the bistmodel with Penn tree bank dataset to create the pretrained model for spacybistparser. Is it with the default parameters or something else? Any help will be greatly appreciated. Thank you.

from nlp-architect.

Hi @ravishpankar
From what I recall, I used the default parameters.
I did not run many training runs, and don't have an evaluation score.
Please refer to the two links in previous comment.

from nlp-architect.