Information retrieval, extraction and summarisation

Summary form only given. The talk distinguishes information detection or retrieval (IR) from information extraction (IE) and describes recent advances in using IE technology for fast access to very large amounts of textual information in, for example, the world wide web and its extraction to a browsable database. This technology is now becoming available commercially and I describe a number of Language Engineering projects incorporating IE technology. It is argued that multilingual applications in IE/IR make the distinction between these information processing technologies and machine translation and automatic question answering and summarisation less clear than before, and they can now be combined in original ways to optimise information access via electronic text. Promising applications are mentioned in security, publishing, communications, finance, science, patents etc. The problems in advancing the field rapidly are described, particularly an appropriate interface, the modelling of the users needs and automatic adaptation of such systems to new domains. Summarisation used to be a traditional linguistic task, tackled by a range of techniques, but is now seen almost exclusively as a by produced of IR or IE technology, creating a text from the set of sentences containing the most improbable terms or by generating text from the content of IE templates