Language Technology is a term for technologies that interpret or produce natural language. This includes:

• Document summarisation
• Document analysis
• Document classification
• Voice recognition
• Synthetic speech

The CMCRC employs language technology in a number of ways in order to improve capital markets technologies.

• Highly specialised document classification for the detection of financial scams in the Internet
• Document summarisation for the extraction of key elements from company news announcements
• Document analysis and summarisation for the automated analysis of company annual reports, analysts’ reports, and IPO prospectuses.

The above points are a number of examples of research work which the CMCRC hopes will contribute to an integration of the analysis of text as unstructured data with the analysis of structured trading data, for future capital markets information systems.