4 papers
Biomedical Data-to-Text Generation via Fine-Tuning Transformers
Ruslan Yermakov, Nicholas Drago, Angelo Ziletti
Data-to-text (D2T) generation in the biomedical domain is a promising - yet mostly unexplored - field of research. Here, we apply neural models for D2T generation to a real-world d…
Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning
Andreas Leitherer, Angelo Ziletti, Luca M. Ghiringhelli
Due to their ability to recognize complex patterns, neural networks can drive a paradigm shift in the analysis of materials science data. Here, we introduce ARISE, a crystal-struct…
Discovering key topics from short, real-world medical inquiries via natural language processing and unsupervised learning
Angelo Ziletti, Christoph Berns, Oliver Treichel +8
Millions of unsolicited medical inquiries are received by pharmaceutical companies every year. It has been hypothesized that these inquiries represent a treasure trove of informati…
NOMAD 2018 Kaggle Competition: Solving Materials Science Challenges Through Crowd Sourcing
Christopher Sutton, Luca M. Ghiringhelli, Takenori Yamamoto +7
Machine learning (ML) is increasingly used in the field of materials science, where statistical estimates of computed properties are employed to rapidly examine the chemical space…