The amount of textual information available to us continues to grow at a breathtaking rate. Yet there are limits on how much information we can read, process, and remember. Techniques that are capable of automatically classifying, abstracting and organizing information in an intelligent way offer an opportunity to compensate for these limits.
A typical resource of information that has been fast growing over time is scientific literature. In this talk, I will detail some previous and ongoing work on automatic analysis of information structure in scientific literature - a technique that divides units (typically sentences) in a text document into categories that represent different types of information (e.g. discourse topics or functions). Applications of this technique in the context of real-world tasks will be covered towards the end of this talk.
Yufan Guo is a Research Associate in the Natural Language and Information Processing Group at the University of Cambridge. She is currently visiting the BioNLP group at the University of Washington. Her research has recently focused on statistical NLP and its applications in biomedicine. Dr. Guo holds a PhD in Computation, Cognition and Language and an MPhil in Computer Speech, Text and Internet Technology from the University of Cambridge.