All of our projects involve the development of prototype software tools for the extraction, processing and analysis of linguistic data from various sources. Many of these are available on the web as demonstration systems. These include:
WebCorp system - accesses the web as a corpus using commercial search engines
WebCorp Linguist's Search Engine - our own large-scale web search engine for linguists
SHARES document similarity system demo
APRIL neologism extraction and analysis system demo
SEAGULL automatic document summarisation / abridgement system demo