import json


# load dataset
with open("dataset_qc.json", encoding="utf-8") as f:
    raw_data = json.load(f)

tokens = [[t.lower().strip() for t in item["tokens"]] for item in raw_data]
ner_tags = [item["ner"] for item in raw_data]
srl_tags = [item["srl"] for item in raw_data]
questions = [item["question"].lower().strip() for item in raw_data]
answers = [item["answer"].lower().strip() for item in raw_data]
types = [item["type"] for item in raw_data]