基於Transformer的生醫輕量化命名實體識別系統

NCU1415 at ROCLING 2022 Shared Task: A light-weight transformer-based approach for Biomedical Name Entity Recognition

NER (Name Entity Recognition)是傳統NLP任務中非常重要也是非常基礎的一項。在生醫領域，各廠商發展的各種技術中，NER任務都有被廣泛地運用。其中包括句子語義分析parsing、問答、對話系統中的關鍵訊息提取和替換以及知識圖譜的實際運用等等。在不同的領域，包括生物醫學、通訊、電商平台等，都需要NER技術來識別其中的藥物、疾病、商品等物件。本實作主要對於ROCLING 2022 SHAREDTASK(Lee et al. 2022)的生醫領域NER任務，基於語言模型做出了一定程度的調整和實驗。

Name Entity Recognition (NER) is a very important and basic task in traditional NLP tasks. In the biomedical field, NER tasks have been widely used in various products developed by various manufacturers. These include parsing, QA system, key information extraction or replacement in dialogue systems, and the practical application of knowledge parsing. In different fields, including bio-medicine, communication technology, ecommerce etc., NER technology is needed to identify drugs, diseases, commodities and other objects. This implementation focuses on the CLING 2022 SHARED TASK's(Lee et al. 2022) NER TASK in biomedical field, with a bit of tuning and experimentation based on the language models.