school:

research institute and research group:

email:

position:

projects:

Computing

Institute for Artificial Intelligence and Biological Systems (I-AIBS);
Natural Language Processing Group

scscb@leeds.ac.uk

Senior Research Fellow

(1) EPSRC: Detecting Terrorist Activities - Making Sense
(2) JISC: e-Health GATEway to the Clouds

• Prosody and prosody modelling
• Psycholinguistic chunking
• Automated phrase break prediction
• Text Analytics (e.g. keyword extraction)
• Stylometry (e.g. algorithmic formulation of poetic and prose rhythm)
• Lexicography (e.g. symbolic representation of phonetic and rhythmic properties of words)
• Stress time (e.g. for English and Arabic)
• Speech and language technologies for video games, interactive story/drama, and conversational agents
• Digital Humanities
• Corpus Linguistics
• Applied Linguistics (e.g. TESOL and TAFL)

Making Sense Project: This is a consortium project in the field of Visual Analytics involving nine UK universities, with a remit to create an interactive, visualisation-based decision support assistant as an aid to intelligence analysts for stakeholders in the law enforcement, military intelligence, and security services sectors. My contribution at Leeds relates to the Text Extraction work package, where I am using keyword extraction to gist/summarise large quantities of non-standard text-based data as one of the modalities that needs to be integrated, prior to discovering links in fused data, and visualising results to support interactive query and search.

e-Health Project: Specification of guidelines plus algorithm design for anonymising the free text elements in electronic patient records.

Docorate: My PhD in the Computing sub-field of Natural Language Processing (NLP) is entitled: "Prosody Resources and Symbolic Prosodic Features for Automated Phrase Break Prediction." The focus is on: (i) the development of a lexicon and prosody and part-of-speech annotation tool for English; (ii) text mining and significance testing of symbolic/categorical prosodic correlates of phrase breaks or rhythmic juncture; (iii) evaluation of statistically significant features thus discovered via supervised machine learning experiments involving automatic binary classification of lexical items (or alternatively whitespaces) as breaks or non-breaks.