2. Things I Dont Have to Talk About Theres lots of text in the world Most of the worlds knowledge is in text You should stop ignoring it If youre going to work with text it needs structure
3. Today Going to cover three things The text problem in one slide What is OpenCalais? What does it do? A few examples of how people are and could use it Sorry no pretty visualizations
4. The Text Problem (aka Why OpenCalais?) Target areas where: The economics dont support metadata creation The value of metadata is potentially high The value of aggregated metadata is potentially extremely high Seconds Years Seconds Years Tweets New Gen News Legacy News Scient. Pubs Great Novels Latency Shelf Life
6. Calais progress to date Launched in late January, 2008 15,000+ developers have joined OpenCalais.com 3-5 million content transactions per day Delivered six major update releases Free (as in free) for commercial or non-commercial use
7. OpenCalais 101 John Doe, the CEO of Acme Corporation, announced today the appointment of Jane Doe as the companys Chief Financial Officer. Person {John Doe} Person {Jane Doe} Company {Acme Corp} Person:Position {Person: John Doe} {Position: CEO} {Company: Acme Corp} JobChange {Person: JaneDoe} {Position: CFO} {Company: Acme Corp} {Status: Entering} Business Finance 97% Entities Facts Events Category
8. Unstructured Text Calais extracts entities, facts and events Metadata returned to the user with keys Keys provide access to the Calais Linked Data cloud Which provides information and other Linked Data pointers To a range of open and partner Linked data assets, including Thomson Reuters 1 2 3 4 5 6
12. Unification of Diverse Content Assets News1 OpenCalais Common Coding / Ontology Press Releases News2 Give me documents where John Doe is mentioned in relationship to an M&A event