Can Embeddings Adequately Represent Medical Terminology? New Large-Scale Medical Term Similarity Datasets Have the Answer!
arXiv:2003.11082
Abstract
A large number of embeddings trained on medical data have emerged, but it remains unclear how well they represent medical terminology, in particular whether the close relationship of semantically similar medical terms is encoded in these embeddings. To date, only small datasets for testing medical term similarity are available, not allowing to draw conclusions about the generalisability of embeddings to the enormous amount of medical terms used by doctors. We present multiple automatically created large-scale medical term similarity datasets and confirm their high quality in an annotation study with doctors. We evaluate state-of-the-art word and contextual embeddings on our new datasets, comparing multiple vector similarity metrics and word vector aggregation techniques. Our results show that current embeddings are limited in their ability to adequately encode medical terms. The novel datasets thus form a challenging new benchmark for the development of medical embeddings able to accurately represent the whole medical terminology.
arXiv commentAccepted at AAAI 2020
References in corpus (5)
- Deep Relevance Ranking Using Enhanced Document-Query Interactions
- Concept2vec: Metrics for Evaluating Quality of Embeddings for Ontological Concepts
- The MeSH-gram Neural Network Model: Extending Word Embedding Vectors with MeSH Concepts for UMLS Semantic Similarity and Relatedness in the Biomedical Domain
- Correlation Coefficients and Semantic Textual Similarity
- Snomed2Vec: Random Walk and Poincaré Embeddings of a Clinical Knowledge Base for Healthcare Analytics