bug about triggerner HOT 7 CLOSED

I use command: python supervised.py --device cuda:0 --dataset CONLL --percentage 3. The result is 85.56. I think the bug should mainly focus on the data (training data is not 3%).

from triggerner.

naive.py is normal. supervised.py and semi_supervised.py have problem.

from triggerner.

Hope you can fix it as soon as possible.

from triggerner.

Hi @wjczf123,

Sorry for the late reply.

Thanks for pointing it out. We will add a new argument --unlabeled_percentage for controlling the percentage of the unlabeled data we used for semi-supervised training. We will add a new script to generate the splits and the use of the --percentage argument to load the respective data split for both supervised.py and semi-supervised.py, by the end of this week.

Yeah, it is indeed the BiLSTM model for char-modeling, we will update the description in the paper. (We also tried CNN before, it performed slightly worse. )

Thanks again.

from triggerner.

OK. Thank you.

from triggerner.

Hope you can fix it as soon as possible.

from triggerner.

Hi @wjczf123,

I apologize for the late reply due to other project deadlines.

We just updated the repo.
Thank you for your suggestion.

Here are the tips for running the code

• The dataset we used for supervised.py and semi_supervised.py is 20% of original training data with triggers.
  (Sentences are split into a single-entity sentence, and each single-entity sentence has triggers)
• If you run python supervised.py --device cuda:0 --dataset CONLL --percentage 3, it means you will use 3% of such trigger dataset. (It should be 0.8% of the training dataset)
• To enable 3% of the original training dataset, you should use --percentage 15

from triggerner.