RIILP brings together two complementary and interdisciplinary research teams, the Statistical Cybermetrics Research Group and the Research Group in Computational Linguistics, which explore the potential of advanced computing technologies for ‘understanding’ human language and social sciences, respectively. The results from Research Assessment Exercise 2008 confirm RIILP as one of the top performers in UK research. Both groups which form the institute are among the UK's leading groups in their fields.
- 'Energy of the nation project' - illumination of the London Eye during the Olympic Games based on the positivity or negativity of the nation as expressed on Twitter - watch a video on Big Data about the research which made this project possible
- Innovative new technology is being developed by Dr Victoria Yaneva to help people with autism read and understand text better. New web tool AUTOR relies on eye tracking technology to measure the accessibility of texts and pinpoint particular areas of difficulty in the text. Watch Victoria discuss AUTOR and her research.
- Coordinator of the EXPERT project (EXPloiting Empirical appRoaches to Translation) which aimed to train young researchers, namely Early Stage Researchers (ESRs) and Experienced Researchers (ERs), to promote the research, development and use of hybrid language translation technologies. The project ran for four years from October 2012 until September 2016 and was made up of a consortium consisting of 6 academic partners, 3 commercial partners and 2 associated partners. Visit the EXPERT project website.
This Institute conducts research in a number of areas at the interface of computers and human language, including the problems that computers have in coping with the complex and intuitive system that is human language.
It is also active in developing software and methodologies to exploit internet-based data sources for social sciences research – including link analysis, cybermetrics and webometrics.
Particular specialisms include:
- anaphora resolution
- named entity recognition
- corpus development and exploitation
- hyperlink and web text analysis
- internet-based quantitative methods