Explainable Word-Embeddings for Medical Digital Libraries - A Context-Aware Approach
Janus Wawrzinek, Said Ahmad Ratib Hussaini, Oliver Wiehr, José María González Pinto, Wolf‐Tilo Balke · 2020
State of the Art Neural Language Models (NLMs) such as Word2Vec are becoming increasingly successful for important biomedical tasks such as the literature-based prediction of com-plex chemical properties or for finding novel drug-disease associations (DDAs). However, NLMs have the disadvantage of being hard to interpret. Therefore, it is notoriously difficult to explain why an artificial neural network learned or predicted some specific association.