OphNER: Named Entity Recognition for Ophthalmology Newspapers
Bao Le, Thi Quynh Pham, Anh Thi Van Hoang, Binh Thanh Nguyen · 2023
The Fourth Industrial Revolution has turned electronic devices into the main tools in human daily life. At the same time, the consequences of the developed economy, such as environmental pollution, viruses, and bacterial strains, are also the main causes of eye diseases. Under the development of media, eye diseases have been quickly and fully synthesized through different types of texts. Texts on ophthalmology provide information about symptoms, disease manifestations, agents, prevention, or treatment in great detail. A large amount of information makes it more difficult to find and filter. Since then, it has become more urgent to build both a corpus and a system to identify and categorize the information from official sources so that everyone can easily find relevant information and better understand related terms to ophthalmology. One of the systems to search for information related to keywords is named entity recognition (NER). To help address this problem, we release the OphNER (Ophthalmology Named Entity Recognition) dataset - the first corpus containing nearly 9,000 sentences with more than a total of 17,447 labels of 16 entities. We also conduct experiments with state-of-the-art models. The highest result belongs to$\mathbf{RoBERTa}_{large}$, which is better than XLM$\mathbf{R}_{large}$or$\mathbf{XLNet}_{large}$. Our dataset is publicly released on Github11https://github.com/baohl00/OphNER for further reference in the research community.