Improved biomedical word embeddings in the transformer era.

Journal: Journal of biomedical informatics
Published Date:

Abstract

BACKGROUND: Recent natural language processing (NLP) research is dominated by neural network methods that employ word embeddings as basic building blocks. Pre-training with neural methods that capture local and global distributional properties (e.g., skip-gram, GLoVE) using free text corpora is often used to embed both words and concepts. Pre-trained embeddings are typically leveraged in downstream tasks using various neural architectures that are designed to optimize task-specific objectives that might further tune such embeddings.

Authors

  • Jiho Noh
    Department of Computer Science, University of Kentucky, United States of America. Electronic address: jiho.noh@uky.edu.
  • Ramakanth Kavuluru
    Div. of Biomedical Informatics, Dept. of Internal Medicine, Dept. of Computer Science, University of Kentucky, Lexington, KY.