},
sentences_vector.classifications_vec,
batch_size=sentences_vector.sentence_vec.shape[1],
epochs=100,
# validation_split=0.2,
# validation_data=({'sequence_input': x_test, 'posi_input': x_test_posi}, y_test),
callbacks=callbacks_list)
return model
if __name__ == '__main__':
config = Configuration(
word_segmentor=EnSegmentor(),
EMBEDDING_DIM=128,
position_matrix_file_path="../data/posi_matrix.npy",
word2vec_file_path="../data/needed_word2vec.bin",
POS_list_file_path="../data/pos_list.txt",
types_file_path="../data/relations_en.txt",
corpus_file_path="../data/train_en.txt",
model_file_path="../data/model/re_sem_eval_en_model.cnn.hdf5",
)
inputer = Inputer(config)
trainer = Trainer(inputer, CnnTrainerEn())
outputer = Outputer(trainer)
predict_texts = [
" <e1>level</e1> of experience has already been mentioned in the previous <e2>chapter</e2>.",
" <e1>level</e1> of experience has already been mentioned in the previous <e2>chapter</e2>."
]
import json
print(
json.dumps(outputer.getDescription(predict_texts), ensure_ascii=False))
def predict(self, sentence_vector: SentencesVector):
classVector = np.ones(sentence_vector.classifications_vec.shape)
prop = self.model.predict({
'sequence_input': sentence_vector.embedded_sequences,
"posi_input": sentence_vector.position_vec,
"typeInput": classVector
})
return sentence_vector.prop2index(prop)
if __name__ == '__main__':
config = Configuration(
position_matrix_file_path="../data/posi_matrix.npy",
word2vec_file_path="../data/needed_zh_word2vec.bin",
POS_list_file_path="../data/military/pos_list.txt",
types_file_path="../data/military/relations_zh.txt",
corpus_file_path="../data/military/train_zh.txt",
model_file_path="../data/model/re_military_zh_model.bilstm.hdf5",
)
inputer = Inputer(config)
trainer = Trainer(inputer, BiLstmTrainer())
outputer = Outputer(trainer)
predict_texts = [
"<loc>美国</loc>目前共有2级11艘航空母舰，包括企业级核动力航母1艘，尼米兹级核动力航母10<loc>艘，</loc>全部采用核动力发动机",
"<loc>美国</loc>经过多年航空母舰的发<loc>展，</loc>一直以来都是全球拥有最多、排水量和体积最大、舰载机搭载数量最多、作战效率最强大、而且全部使用核动力航空母舰的国家"
]
import json
print(
json.dumps(outputer.getDescription(predict_texts), ensure_ascii=False))
batch_size=50,
epochs=50000,
validation_split=0.2,
# validation_data=({'sequence_input': x_test, 'posi_input': x_test_posi}, y_test),
callbacks=callbacks_list)
return model
if __name__ == '__main__':
testType = input("CNN?RNN:")
config = Configuration(
word_segmentor=EnSegmentor(),
EMBEDDING_DIM=300,
position_matrix_file_path="../data/posi_matrix.npy",
word2vec_file_path="../data/needed_word2vec.pkl",
POS_list_file_path="../data/pos_list.txt",
types_file_path="../data/relations_en.txt",
corpus_file_path="../data/train_en.txt",
model_file_path="../data/model/re_sem_eval_en_model_" + testType +
".hdf5",
n_gram_size=1,
)
inputer = Inputer(config)
trainer = Trainer(inputer, testType)
outputer = Outputer(trainer)
outputer.getEvaluation(testType)
predict_texts = [
" <e1>level</e1> of experience has already been mentioned in the previous <e2>chapter</e2>.",
" <e1>level</e1> of experience has already been mentioned in the previous <e2>chapter</e2>."
]
import json
# print(json.dumps(outputer.getDescription(predict_texts, testType), ensure_ascii=False))