Named Entity Recognition (NER)

Users can directly download the model for usage. The details are as follows：

1. Create 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. Make inference. The text and entity pairs to be predicted are fed to the program through the terminal.

  python predict.py
							

To use the pre-trained models, 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 predict.py`, results can be obtained which show that the entity type "星空黑夜传奇" is "网络小说", "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 change the text for inference.

  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 for usage. 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. Make inference. The text and entity pairs to be predicted are fed to the program through the terminal.

  python predict.py
							

To use the pre-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
							

Joint Entity and Relation Extraction

After aforementioned trained models are downloaded, entites and their relations in a text can be extracted together. If there are more than two entities in one sentence, some predicted entity pairs may be incorrect because these entity pairs are not in training sets and need to be exracted further. The detailed steps are as follows:

1. In conf, modify text in predict.yaml as the sentence to be predicted, nerfp as the directory of the trained NER model and refp as the directory of the trained RE model.

2. Predict

  python predict.py
							

Many results will be output. Take the input text "此外网易云平台还上架了一系列歌曲，其中包括田馥甄的《小幸运》等" as example.

(1) Output the result of NER: [('田', 'B-YAS'), ('馥', 'I-YAS'), ('甄', 'I-YAS'), ('小', 'B-QEE'), ('幸', 'I-QEE'), ('运', 'I-QEE')]

(2) Output the processed result: {'田馥甄': '人物', '小幸运': '歌曲'}

(3) Output the result of RE: "田馥甄" 和 "小幸运" 在句中关系为："歌手"，置信度为0.92

(4) Output the result as jsonld:

  {
    "@context": {
	  "歌手": "https://cnschema.openkg.cn/item/%E6%AD%8C%E6%89%8B/16693#viewPageContent"
    },
    "@id": "田馥甄",
    "歌手": {
      "@id": "小幸运"
    }
  }