Details of Grant 

EPSRC Reference:	EP/D069548/1
Title:	Providing Lexical Adaptation Techniques for Language Processing
Principal Investigator:	Stevenson, Dr M
Other Investigators:
Researcher Co-Investigators:
Project Partners:
Department:	Computer Science
Organisation:	University of Sheffield
Scheme:	Advanced Fellowship
Starts:	01 September 2006	Ends:	31 August 2011	Value (£):	438,158
EPSRC Research Topic Classifications:	Comput./Corpus Linguistics Human Communication in ICT Information & Knowledge Mgmt
EPSRC Industrial Sector Classifications:	No relevance to Underpinning Sectors
Related Grants:
Panel History:	Panel Date Panel Name Outcome 25 Apr 2006 ICT Fellowships 2006 - Interview Panel Deferred 21 Mar 2006 ICT Fellowships 2006 - Sift Panel Deferred
Summary on Grant Application Form
It is difficult for computers to understand the languages people speak, for example English or Japanese. Computers often use dictionaries, similar to the ones people use, to tell them what words mean. These can be complicated to use since many words can mean several things; a bat could be something you use in cricket or a small nocturnal mammal. The meaning being used often depends upon the overall topic being discussed. So, in a book about sports you are more likely to read about cricket bats than flying animals. This project will help computers understand language by automatically transforming the dictionaries we have available now into ones which contain the information they need. These dictionaries will include details of the way words are used in the text the computer is processing. In addition, dictionaries may not contain all words in a language, for example they may miss out unusual words or slang. Our systems will automatically add these words to our dictionaries. It is not possible to evaluate a dictionary without some idea of what it is intended to do. In this project we shall make use of our dictionaries in computer systems which understand language. These systems carry out useful tasks such as finding important information in text or identifying documents which discuss a particular topic. We will compare these systems against ones which use other dictionaries (that have not been specially adapted for use with the computer). This will allow us to measure how successful our dictionaries are by how much these systems improve when they use them.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.shef.ac.uk