Discourse processing in scientific articles and social media
I will present an overview of work of mine on automatic generation of scientific discourse annotations (Hypothesis, Results, etc.) and how these have been used in a number of tasks including automatic summarisation and fine-grained querying of publications. I will also discuss our work on recognising rumours in conversation threads on social media and analysing target specific sentiment on Twitter.
Speaker bio
Maria Liakata is Assistant Professor at the Department of Computer Science
at the University of Warwick and Exchange Assistant Professor at the Centre
for Urban Science and Progress (CUSP) at New York University (NYU) since
January 2013.
She holds an IBM Faculty Award for studying “Emotion sensing using
heterogeneous mobile phone data” and she is a co-investigator on the EU
Project PHEME. Previously she held an Early Career Fellowship from the
Leverhulme Trust (2010-2013) on reasoning with scientific articles, hosted
at the European Bioinformatics Institute, Cambridge where she remains a
visiting fellow. She has a natural language processing background and a
DPhil from the University of Oxford on the topic of inducing domain theories
from text. Her research interests include knowledge discovery from text,
natural language processing for social media, sentiment analysis and emotion
recognition from text, biomedical text mining and natural language
processing for health and social good.