إن إزالة الكيانات المسماة (NED)، والتي تنطوي على رسم الخرائط النصية للكيانات الهيكلية، تحديا بشكل خاص في المجال الطبي بسبب وجود كيانات نادرة.تقتصر الأساليب الحالية بوجود الموارد الهيكلية الخشونة في قواعد المعرفة الطبية الحيوية وكذلك استخدام مجموعات البيانات التدريبية التي توفر تغطية منخفضة على الموارد غير الشائعة.في هذا العمل، نتعلم هذه المشكلات من خلال اقتراح طريقة تكامل بيانات عبر المجال التي تنقل المعرفة الهيكلية من قاعدة معارف النص العامة إلى المجال الطبي.نحن نستخدم مخطط الاندماج لدينا لزيادة الموارد الهيكلية وتوليد مجموعة بيانات كبيرة بييوميديا للأحاد المحاكمة.يحقق نموذج عائليتنا مع المعرفة الهيكلية المحقونة أداء حديثة على مجموعة بيانات القياس الطبية القياسية: التوصيلات و BC5CDR.علاوة على ذلك، فإننا نحسن الغموض من كيانات نادرة تصل إلى 57 نقطة دقة.
Named entity disambiguation (NED), which involves mapping textual mentions to structured entities, is particularly challenging in the medical domain due to the presence of rare entities. Existing approaches are limited by the presence of coarse-grained structural resources in biomedical knowledge bases as well as the use of training datasets that provide low coverage over uncommon resources. In this work, we address these issues by proposing a cross-domain data integration method that transfers structural knowledge from a general text knowledge base to the medical domain. We utilize our integration scheme to augment structural resources and generate a large biomedical NED dataset for pretraining. Our pretrained model with injected structural knowledge achieves state-of-the-art performance on two benchmark medical NED datasets: MedMentions and BC5CDR. Furthermore, we improve disambiguation of rare entities by up to 57 accuracy points.
References used
https://aclanthology.org/
Current work in named entity recognition (NER) shows that data augmentation techniques can produce more robust models. However, most existing techniques focus on augmenting in-domain data in low-resource scenarios where annotated data is quite limite
The domain-specialised application of Named Entity Recognition (NER) is known as Biomedical NER (BioNER), which aims to identify and classify biomedical concepts that are of interest to researchers, such as genes, proteins, chemical compounds, drugs,
It has been shown that named entity recognition (NER) could benefit from incorporating the long-distance structured information captured by dependency trees. We believe this is because both types of features - the contextual information captured by t
Cross-domain Named Entity Recognition (NER) transfers the NER knowledge from high-resource domains to the low-resource target domain. Due to limited labeled resources and domain shift, cross-domain NER is a challenging task. To address these challeng
Named Entity Recognition is an essential task in natural language processing to detect entities and classify them into predetermined categories. An entity is a meaningful word, or phrase that refers to proper nouns. Named Entities play an important r