ABSTRACT
One of the common tasks in clinical natural language processing is medical entity linking (MEL) which involves mention detection followed by linking the mention to an entity in a knowledge base. One reason that MEL has not been solved is due to a problem that occurs in language where ambiguous texts can be resolved to several named entities. This problem is exacerbated when processing the text found in electronic health records. Recent work has shown that deep learning models based on transformers outperform previous methods on linking at higher rates of performance. We introduce NeighBERT, a custom pre-training technique which extends BERT (Devlin et al [1]) by encoding how entities are related within a knowledge graph. This technique adds relational context that has been traditionally missing in original BERT, helping resolve the ambiguity found in clinical text. In our experiments, NeighBERT improves the precision, recall, and F1-score of the state of the art by 1-3 points for named entity recognition and 10-15 points for MEL on two widely known clinical datasets. Supplementary Information: The online version contains supplementary material available at 10.1007/s41666-023-00136-3.
ABSTRACT
UNLABELLED: Telomeres and centromere are two essential features of all eukaryotic chromosomes. They provide function that is necessary for the stability of chromosomes. We developed a comprehensive database named TeCK, which covers a gamut of sequence and other related information about telomeric patterns, telomere repeat sequences, centromere sequences and centromeric patterns present in chromosomes. It also contains information about telomerase ribo-nucleoprotein complexes, centromere binding protein and centromere DNA-binding protein complexes. The database also includes a collection of all kinetochore-associated proteins including inner, outer and central kinetochore proteins. The database can be searched using a user-friendly web interface. AVAILABILITY: http://www.bioinfosastra.com/services/teck/index.html.