Search Meetup Cambridge - Challenges of Unstructured Data

Our first talk this time is from Dean Yearsley of Pingar on "Unstructured & Inaccessible Data: A Practical Technological Solution" - he'll be talking about how to search, sort, analyse and extract knowledge from scanned and OCR'd documents. Pingar have some very interesting semantic search and NLP technology developed originally in New Zealand.

Our second speaker is Jordan Hrycaj of 7Safe/PA Consulting on "Techniques for ad-hoc locating particular data objects in unknown data space" - this looks fascinating, covering the use of specialised light-weight search tools for tasks related to security and legal applications, such as searching for PANs (credit card numbers).

Accompanied by the usual nibbles, beer and networking - when you arrive there should be a bar tab for 'the Search event' so do please get a drink before you come upstairs.

Talks will start at 7.15pm (ish).