Closed kemalaraz closed 4 years ago
To use the pre-trained MTB model for fine-tuning for SemEval, set use_pretrained_blanks=1 in main_task.py.
For inference after fine-tuning on SemEval, please see inference section under readme. I did not provide a script for this, but rather as a python API package.
For eg. you can write your own script in the project directory and import the package like this:
from src.tasks.infer import infer_from_trained
inferer = infer_from_trained(args, detect_entities=False)
test = "The surprise [E1]visit[/E1] caused a [E2]frenzy[/E2] on the already chaotic trading floor."
inferer.infer_sentence(test, detect_entities=False)
If you want it to automatically detect entities using Spacy, set detect_entities=True
Currently I am pre-training the bert model for MTB but how can I use that pre-trained model for fine-tuning for SemEval2010 Task 8? I saw that you gave information about how to fine-tune the actual bert model for SemEval2010 Task 8 however I couldn't find any information about how to fine tuned pre-trained MTB model? In addition to that after fine-tuning on SemEval2010 Task 8 should I do NER first or the model does that itself?
Thanks