Natural language processing supported transdisciplinary crowdsourcing
published: Aug. 6, 2013, recorded: April 2013, views: 2420
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
We outline a Web-based architecture that serves the construction of transdisciplinary knowledge and is supported by machine intelligence. At the heart of the architecture is the interaction between a repository of concepts and the machine intelligence. The repository is an ontology integrated with a Wiki; each concept in the ontology is grounded in the natural language text of the Wiki. The machine intelligence exploits structured sparse coding and helps users interact with the concept repository. Most importantly, it helps practitioners of different fields understand each other by explaining unknown terminology in the Wiki, and it facilitates creating and maintaining content. These two components evolve together: as the concept repository grows, the intelligence performs better. Furthermore, extending the concept repository semi-automatically becomes easier.
To support wide contribution and ensure the high quality of the accumulated knowledge, content is divided into two types: drafts and articles. Anyone who registers can create and edit drafts, but only drafts that pass a voting procedure and are approved by an Editorial Board can become articles. Articles are very similar to scientific papers: they undergo peer-review and contain verified knowledge. Two communities have already started using these portals in the domains of robotic surgery and education.
Download slides: machine_pinter_natural_language_01.pdf (3.2 MB)
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !
Write your own review or comment: