US mini logoHome | A-Z Index | People | Reference | Contact us
University of Sussex
About | People | Projects | Doctoral Programme | Seminar Series | Resources

Weakly Supervised Learning for Hedge Classification in Scientific Literature

Speaker

Ben Medlock

Affilliation

Cambridge

Abstract

We investigate automatic classification of speculative language, or `hedging', in scientific literature from the biomedical domain using weakly-supervised learning. We discuss the task from both a human annotation and machine learning perspective and focus on aspects of the problem that set it apart from previous weakly-supervised ML research. We show how the problem can be tackled with a probabilistic formulation of the self-training paradigm, and present a theoretical and practical evaluation of our learning and classification models.

see also

Site maintained by: Jonathon Read Disclaimer | Feedback