I'm a professor in the School of Informatics at the University of Edinburgh. I'm affiliated with the Institute for Communicating and Collaborative Systems and the Edinburgh Natural Language Processing Group.

My research focuses on computational models for the representation, extraction, and generation of semantic information from structured and unstructured data, involving text and other modalities such as images, video, and large scale knowledge bases. I have worked on a variety of applied NLP tasks such as semantic parsing and semantic role labeling, discourse coherence, summarization, text simplification, concept-to-text generation, and question answering. I have also used computational models (drawing mainly on probabilistic generative models) to explore aspects of human cognition such as learning concepts, judging similarity, forming perceptual representations, and learning word meanings. The overarching goal of my research is to enable computers to understand requests and act on them, process and aggregate large amounts of data, and convey information based on them. Critical for all these tasks are models for extracting and representing meaning from natural language text, storing meanings internally, and working with stored meanings to derive further consequences.