Oliver Adams, PhD

Data Science


Natural Language Processing
Deep Learning
Machine Learning


Ph.D., Computer Science, University of Melbourne
B.S., Computer Science, University of Melbourne



Recent Projects

Finance Startup
NLP for Document Information Extraction
Extract key-value pairs from credit agreements on the basis of minimal annotations, such as bank name, number of days, time zone, termination date, deal amount. Model consists of a cascaded series of transformer fine-tunings starting with a pre-trained BERT model. Solution greatly reduced manual annotation burden, formed the base model for new document types, and supported a tool for speech-driven querying of documents.


Technical Expertise

  • Python data stack: scikit-learn, pandas, numpy, Jupyter, others
  • Speech Processing
  • Recurrent Neural Networks
  • Machine Learning
  • Deep Learning Frameworks: Tensorflow, PyTorch, Keras