2020/10/23 by Lukas Lange, Xiang Dai, Lange, Lukas +5 · 2 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Mathematics · #Artificial intelligence #Artificial neural network #Biology #Biomedical Text Mining and Ontologies #Computation and Language (cs.CL) #Computer science #Context (archaeology) #Engineering #F1 score #FOS: Computer and information sciences #Information extraction #Machine Learning (cs.LG) #Mathematics #Named-entity recognition #Natural Language Processing Techniques #Natural language processing #Normalization (sociology) #Parsing #Rank (graph theory) #Sequence (biology) #Sequence labeling #Task (project management) #Topic Modeling #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.2010.12322
published in arXiv (Cornell University), 335-346 (Cornell University) · IberLEF 2020
arxiv created 2020/10/23 · openalex publication_date 2020/10/23 · arxiv updated 2020/10/26 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
The recognition and normalization of clinical information, such as tumor\nmorphology mentions, is an important, but complex process consisting of\nmultiple subtasks. In this paper, we describe our system for the CANTEMIST\nshared task, which is able to extract, normalize and rank ICD codes from\nSpanish electronic health records using neural sequence labeling and parsing\napproaches with context-aware embeddings. Our best system achieves 85.3 F1,\n76.7 F1, and 77.0 MAP for the three tasks, respectively.\n