My research area is Computational Linguistics, and my research focus is on making information more accessible by exploiting results in Linguistics and Computer Science, including Information Retrieval and Machine Learning. My main interests are Natural Language Regeneration, where existing texts are automatically simplified and summarised to make the content more accessible, and Natural Language Generation, particularly generating engaging narratives from data (check out the Blogging Birds). My recent research also covers information extraction from scientific literature, citation analysis, multi-document and multilingual news summarization, text simplification, open-domain referring expression generation, anaphora resolution and the semantic annotation of multilingual corpora.
2012-2018. ``The Northern Temperament'' (with Isobel Cameron, Peter Davidson, Arnar Arnason, John Crawford, Thomas McKean, Ian Reid, Ian Russell and Justin Williams). 72 month project funded through the University of Aberdeen's research theme "The North".
2013-2014. ``Lexico-syntactic text simplification for improving information access'' 15 month EPSRC funded project (Grant Number EP/J018805/1).
2012-2015. ``An investigation of how patients, public and stakeholders perceive and interpret information about anti-depressants in UK newspapers.'' CSO Doctoral Fellowship awarded to Nooreen Akhtar (supervised by Isobel Cameron, Barbara Fennel, Margaret Maxwell and Advaith Siddharthan)
2013-2016. ``Developing Digital Tools for Citizen Science: Towards New Ways of Learning about the Natural Environment'' (Advaith Siddharthan, Rene van der Wal and Laura Colucci-Gray). Funded through the University of Aberdeen's research theme "Environment and Food Security".
2009-2010. ``Studying the appropriateness of different formulations of a discourse relation in context.'' (with Napoleon Katsos). 12 month ESRC funded project (Grant Number RES-000-22-3272).
Editorial Board of Computational Linguistics (MIT Press)