def __init__(self, info_dict, trained_model_path=None):
self.info_dict = info_dict
self.bertinizer = SentenceBERTinizer()
self.model = BERTGraphRel(
num_ne=info_dict["entity_vsize"],
num_rel=info_dict["rel_vsize"],
embedding_size=self.bertinizer.embedding_size)
if trained_model_path is not None:
self.load_trained_model(trained_model_path)
os.makedirs(dumb_dataset_dir)
train_dumb_dataset_path = dumb_dataset_dir + "dumb_train.json"
test_dumb_dataset_path = dumb_dataset_dir + "dumb_test.json"
if __name__ == "__main__":
ddsc = DumbDataSetConstructor(config_path=dumb_dataset_config_path)
print("+ Preparing and saving train dataset.")
ddsc.generate_dataset(n=6000)
data, ne_list, rel_list = ddsc.get_dataset()
ddsc.write_json_dataset(train_dumb_dataset_path)
print("+ Preparing and saving descriptive json.")
sentbertnizer = SentenceBERTinizer()
er_aligner = tgtEntRelConstructor(tokenizer=sentbertnizer,
ne_tags=ne_list,
rel_tags=rel_list)
num_ne = er_aligner.NE_vsize
num_rel = er_aligner.REL_vsize
info_collector = InfoCollector()
info_collector.remember_info(
entities=ne_list,
relations=rel_list,
entity_vsize=num_ne,
rel_vsize=num_rel,
mod_entities=er_aligner.NE_biotags,
mod_relations=er_aligner.REL_mod_tags,