نظرا لعدد كبير من الكيانات في قواعد المعرفة الطبية الحيوية، فإن جزء بسيط من الكيانات الصغيرة فقط بيانات التدريب المسمى. وهذا يستلزم كيان ربط النماذج التي يمكن أن تصل إلى ربط تذكر الكيانات غير المرئية باستخدام التمثيلات المستفادة للكيانات. يتذكر كل منهما السابقة بشكل مستقل، وتجاهل العلاقات داخل الوثائق وعبر الوثائق بين الكيان. يمكن أن تكون هذه العلاقات مفيدة للغاية لربط الذكور في النص الطبي الطبيعي حيث غالبا ما تذكر القرارات ذات الصلة وجود نموذج عام أو متخصص للغاية. في هذه الورقة، نقدم نموذجا يمكن فيه إلقاء النموذج الذي يمكن فيه اتخاذ قرارات مرتبطة فقط بالربط بالكيان الأساسي المعرفي ولكن أيضا من خلال تجميع تذكر معا عبر التجميع والاشتراك في ربط التوقعات. في تجارب في أكبر مجموعة بيانات بيئية متوفرة للجمهور، نحسن أفضل التنبؤ المستقل للكيان الذي يربط بمقدار 3.0 نقطة من الدقة، ويحسن نموذج الاستدلال القائم على التجميع كيان يربط بمقدار 2.3 نقطة.
Due to large number of entities in biomedical knowledge bases, only a small fraction of entities have corresponding labelled training data. This necessitates entity linking models which are able to link mentions of unseen entities using learned representations of entities. Previous approaches link each mention independently, ignoring the relationships within and across documents between the entity mentions. These relations can be very useful for linking mentions in biomedical text where linking decisions are often difficult due mentions having a generic or a highly specialized form. In this paper, we introduce a model in which linking decisions can be made not merely by linking to a knowledge base entity but also by grouping multiple mentions together via clustering and jointly making linking predictions. In experiments on the largest publicly available biomedical dataset, we improve the best independent prediction for entity linking by 3.0 points of accuracy, and our clustering-based inference model further improves entity linking by 2.3 points.
References used
https://aclanthology.org/
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,
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-grain
Many open-domain question answering problems can be cast as a textual entailment task, where a question and candidate answers are concatenated to form hypotheses. A QA system then determines if the supporting knowledge bases, regarded as potential pr
Biomedical Concept Normalization (BCN) is widely used in biomedical text processing as a fundamental module. Owing to numerous surface variants of biomedical concepts, BCN still remains challenging and unsolved. In this paper, we exploit biomedical c
Natural language inference (NLI) is the task of determining whether a piece of text is entailed, contradicted by or unrelated to another piece of text. In this paper, we investigate how to tease systematic inferences (i.e., items for which people agr