SCU-MESCLab at ROCLING-2022 Shared Task: Named Entity Recognition Using BERT Classifier

SCU-MESCLab at ROCLING-2022 Shared Task: Named Entity Recognition Using BERT Classifier

本研究構建了命名實體識別模型，並將其應用於醫療領域。資料是以BIO格式進行標記。例如''肌肉''會被標記成''B-BODY''和''I-BODY''，''咳嗽''則是''B-SYMP''和''I-SYMP''。不屬於命名實體類別以外的字全標為''O''。訓練資料Chinese HealthNER Corpus包含30,692句，其中的2531句切分為此次評測的驗證集(dev)，而最終大會提供另外的3204句的測試集(test)。我們分別使用BLSTM_CRF、Roberta+BLSTM_CRF與BERT Classifier三種方式提交三個預測結果。最後，提交為RUN3的BERT Classifier系統取得了最好的預測效能，其精準度為80.18%、召回率為78.3%，F1-score為79.23。

In this study, named entity recognition is constructed and applied in the medical domain. Data is labeled in BIO format. For example, ''muscle'' would be labeled ''B-BODY'' and ''I-BODY'', and ''cough'' would be ''B-SYMP'' and ''I-SYMP''. All words outside the category are marked with ''O''. The Chinese HealthNER Corpus contains 30,692 sentences, of which 2531 sentences are divided into the validation set (dev) for this evaluation, and the conference finally provides another 3204 sentences for the test set (test). We use BLSTM_CRF, Roberta+BLSTM_CRF and BERT Classifier to submit three prediction results respectively. Finally, the BERT Classifier system submitted as RUN3 achieved the best prediction performance, with an accuracy of 80.18%, a recall rate of 78.3%, and an F1-score of 79.23.