Named Entity Recognition(NER)

Users can directly download the model to use. The details are as follows：

1. Name the downloaded folder as checkpoints

2. Modify the `get_labels`function in the source code. The returned labels are given in type.txt

  def get_labels(self):
      return ['O', 'B-YAS', 'I-YAS', 'B-TOJ', 'I-TOJ', 'B-NGS', 'I-NGS',
              'B-QCV', 'I-QCV', 'B-OKB', 'I-OKB', 'B-BQF', 'I-BQF', 'B-CAR',
              'I-CAR', 'B-ZFM', 'I-ZFM', 'B-EMT', 'I-EMT', 'B-UER', 'I-UER',
              'B-QEE', 'I-QEE', 'B-UFT', 'I-UFT', 'B-GJS', 'I-GJS', 'B-SVA',
              'I-SVA', 'B-ANO', 'I-ANO', 'B-KEJ', 'I-KEJ', 'B-ZDI', 'I-ZDI',
              'B-CAT', 'I-CAT', 'B-GCK', 'I-GCK', 'B-FQK', 'I-FQK', 'B-BAK',
              'I-BAK', 'B-RET', 'I-RET', 'B-QZP', 'I-QZP', 'B-QAQ', 'I-QAQ',
              'B-ZRE', 'I-ZRE', 'B-TDZ', 'I-TDZ', 'B-CVC', 'I-CVC', 'B-PMN',
              'I-PMN', '[CLS]', '[SEP]']
							

3. Modify the parameter text in predict.yaml to the text to be predicted

4. Predict. The text and entity pairs to be predicted are input to the program through the terminal

  python predict.py
							

To use the trained model, just input the sentence "《星空黑夜传奇》是连载于起点中文网的网络小说，作者是啤酒的罪孽". After running `python oredict.py`, results can be obtained which show that the entity type "星空黑夜传奇" is "网络小说" aligned with cnschema, "起点中文网" is "网站" and "啤酒的罪孽" is "人物".

Modify the parameter text in predict.yaml to the text to be predicted

  text=“《星空黑夜传奇》是连载于起点中文网的网络小说，作者是啤酒的罪孽”
							

Finally, output the results:

  NER句子：
  《星空黑夜传奇》是连载于起点中文网的网络小说，作者是啤酒的罪孽
  NER结果：
  [('星','B-UER'),('空','I-UER'),('黑','I-UER'),('夜','I-UER'),('传','I-UER'),
   ('奇','I-UER'),('起','B-ZFM'),('点','I-ZFM'),('中','I-ZFM'),('文','I-ZFM')
   ('网','I-ZFM'),('啤','B-YAS'),('酒','I-YAS'),('的','I-YAS'),('罪','I-YAS'),
   ('孽','I-YAS')]
							

Relation Extraction(RE)

Users can directly download the model to use. The details are as follows：

1. Modify the parameter fp in predict.yaml to the path of downloaded file and num_relations in embedding.yaml to 51(relation nums)

2. Predict. The text and entity pairs to be predicted are input to the program through the terminal

  python predict.py
							

To use the trained model, run `python predict.py` and input the sentence "歌曲《人生长路》出自刘德华国语专辑《男人的爱》，由李泉作词作曲，2001年出行发版". The given entity pair are "男人的爱" and "人生长路". Finally, the extracted relation is "所属专辑" aligned with cnschema.

To change the text to be predicted, modify the _get_predict_instance function in predict.py to the following example:

  def _get_predict_instance(cfg):
      flag = input('是否使用范例[y/n]，退出请输入: exit .... ')
      flag = flag.strip().lower()
      if flag == 'y' or flag == 'yes':
          sentence = '歌曲《人生长路》出自刘德华国语专辑《男人的爱》，由李泉作词作曲
                      2001年出行发版'
          head = '男人的爱'
          tail = '人生长路'
          head_type = ''
          tail_type = ''
      elif flag == 'n' or flag == 'no':
          sentence = input('请输入句子：')
          head = input('请输入句中需要预测关系的头实体：')
          head_type = input('请输入头实体类型（可以为空，按enter跳过）：')
          tail = input('请输入句中需要预测关系的尾实体：')
          tail_type = input('请输入尾实体类型（可以为空，按enter跳过）：')
      elif flag == 'exit':
          sys.exit(0)
      else:
          print('please input yes or no, or exit!')
          _get_predict_instance()
							
      instance = dict()
      instance['sentence'] = sentence.strip()
      instance['head'] = head.strip()
      instance['tail'] = tail.strip()
      if head_type.strip() == '' or tail_type.strip() == '':
          cfg.replace_entity_with_type = False
          instance['head_type'] = 'None'
          instance['tail_type'] = 'None'
      else:
          instance['head_type'] = head_type.strip()
          instance['tail_type'] = tail_type.strip()
							
      return instance
							

Finally, output the results:

  “男人的爱”和“人生长路”在句中关系为“所属专辑”，置信度为0.99