atom ate it
play

ATOM ate It! End-user Context-Sensitive Automation using - PowerPoint PPT Presentation

ATOM ate It! End-user Context-Sensitive Automation using Heterogeneous Information Sources on the Web Max Van Kleek, Brennan Moore, David Karger Max Van Kleek, Paul Andr, mc schraefel MIT CSAIL enAKTing ECS, University of Southampton {


  1. ATOM ate It! End-user Context-Sensitive Automation using Heterogeneous Information Sources on the Web Max Van Kleek, Brennan Moore, David Karger Max Van Kleek, Paul André, mc schraefel MIT CSAIL enAKTing ECS, University of Southampton { emax, zamiang, karger } @ csail.mit.edu { emax, pa2, mc+www } @ ecs.soton.ac.uk Friday, May 7, 2010

  2. ATOM ate It! End-user Context-Sensitive Automation using How to regain some of the time Heterogeneous Information Sources on the Web that Web 2.0 took away Max Van Kleek, Brennan Moore, David Karger Max Van Kleek, Paul André, mc schraefel MIT CSAIL enAKTing ECS, University of Southampton { emax, zamiang, karger } @ csail.mit.edu { emax, pa2, mc+www } @ ecs.soton.ac.uk Friday, May 7, 2010

  3. 1. motivation - can we beat overload by delegating to machines? 2. atomate - reactive automation driven by web feeds 3. study 4. related work 5. next steps Friday, May 7, 2010

  4. 1. motivation Friday, May 7, 2010

  5. "...in an information-rich world, the wealth of information means a dearth of something else: a scarcity of [ ... ] the attention of its recipients. Hence a wealth of information creates a poverty of attention and a need to allocate that attention efficiently among the overabundance of information sources that might consume it" (Simon 1971, p. 40-41) Friday, May 7, 2010

  6. In 2010: Friday, May 7, 2010

  7. In 2010: peer/friend/citizen-produced content Friday, May 7, 2010

  8. In 2010: peer/friend/citizen-produced content socially and algorithmically recommended Friday, May 7, 2010

  9. In 2010: peer/friend/citizen-produced content socially and algorithmically recommended more interesting content produced every day than we could possibly consume Friday, May 7, 2010

  10. In 2010: peer/friend/citizen-produced content socially and algorithmically recommended more interesting content produced every day than we could possibly consume ‘social maintenance’ - updating friends Friday, May 7, 2010

  11. In 2010: peer/friend/citizen-produced content socially and algorithmically recommended more interesting content produced every day than we could possibly consume ‘social maintenance’ - updating friends keeping on top of the world Friday, May 7, 2010

  12. In 2010: peer/friend/citizen-produced content socially and algorithmically recommended more interesting content produced every day than we could possibly consume ‘social maintenance’ - updating friends keeping on top of the world responding to others’ needs Friday, May 7, 2010

  13. In 2010: peer/friend/citizen-produced content socially and algorithmically recommended more interesting content produced every day than we could possibly consume ‘social maintenance’ - updating friends keeping on top of the world more responsibilities -- professional, personal, social responding to others’ needs than we could possibly perform Friday, May 7, 2010

  14. P. Maes, “Agents the Reduce Work and Information Overload” Communications of the ACM Volume 37 , Issue 7 (July 1994) Friday, May 7, 2010

  15. Friday, May 7, 2010

  16. physical locations desktop activity messages sleep travels friends/enemies music listened to running events documents Friday, May 7, 2010

  17. wouldn’t it be great if computers could use all this information to do stuff for us? Friday, May 7, 2010

  18. for example: • remind me to take out the trash when I get home on Tuesdays... • bug my friend who hasn’t replied to me in 2 days... • send me my grocery shopping list when I arrive at the grocery store • remind friends about an event I am going to attend • text me important emails when I am traveling ...how do we get there? Friday, May 7, 2010

  19. what we need Friday, May 7, 2010

  20. what we need 1. a way for users to express: what they want to happen, and when , in terms of predicates relating the states and properties of people , places + things in their world. Friday, May 7, 2010

  21. what we need 1. a way for users to express: what they want to happen, actions and when , in terms of predicates relating the states and properties of people , places + things in their world. Friday, May 7, 2010

  22. what we need 1. a way for users to express: what they want to happen, actions and when , conditions in terms of predicates relating the states and properties of people , places + things in their world. Friday, May 7, 2010

  23. what we need 1. a way for users to express: what they want to happen, actions and when , conditions in terms of predicates relating predicates the states and properties of people , places + things in their world. Friday, May 7, 2010

  24. what we need 1. a way for users to express: what they want to happen, actions and when , conditions in terms of predicates relating predicates the states and properties of properties people , places + things in their world. Friday, May 7, 2010

  25. what we need 1. a way for users to express: what they want to happen, actions and when , conditions in terms of predicates relating predicates the states and properties of properties people , places + things entities in their world. Friday, May 7, 2010

  26. what we need 1. a way for users to express: what they want to happen, actions and when , conditions in terms of predicates relating predicates the states and properties of properties people , places + things entities in their world. Controlled Natural Language Interface (CNLI) for Rules Friday, May 7, 2010

  27. what we need 1. a way for users to express: what they want to happen, actions and when , conditions in terms of predicates relating predicates the states and properties of properties people , places + things entities in their world. Controlled Natural Language Interface (CNLI) for Rules 2. a way to retrieve and interpret data from our many heterogeneous web sources as descriptions of these familiar people , places and things. Friday, May 7, 2010

  28. what we need 1. a way for users to express: what they want to happen, actions and when , conditions in terms of predicates relating predicates the states and properties of properties people , places + things entities in their world. Controlled Natural Language Interface (CNLI) for Rules 2. a way to retrieve and interpret data from our many heterogeneous web sources as descriptions of these familiar people , places and things. ATOM/RSS/REST APIs, End-user mashups + RDF Friday, May 7, 2010

  29. Controlled/Constrained Natural Language Interface previous work: for the construction of RDF KBs and queries: Abraham Bernstein and Esther Kaufmann and Christian Kaiser and Christoph Kiefer, Ginseng: A Guided Input Natural Language Search Engine for Querying Ontologies , Jena User Conference, 2008. Friday, May 7, 2010

  30. Controlled/Constrained Natural Language Interface previous work: for the construction of RDF KBs and queries: Abraham Bernstein and Esther Kaufmann and Christian Kaiser and Christoph Kiefer, Ginseng: A Guided Input Natural Language Search Engine for Querying Ontologies , Jena User Conference, 2008. express behaviors as rules when <something happens> do <action> Friday, May 7, 2010

  31. Controlled/Constrained Natural Language Interface previous work: for the construction of RDF KBs and queries: Abraham Bernstein and Esther Kaufmann and Christian Kaiser and Christoph Kiefer, Ginseng: A Guided Input Natural Language Search Engine for Querying Ontologies , Jena User Conference, 2008. express behaviors as rules when <something happens> do <action> query Friday, May 7, 2010

  32. Controlled/Constrained Natural Language Interface previous work: for the construction of RDF KBs and queries: Abraham Bernstein and Esther Kaufmann and Christian Kaiser and Christoph Kiefer, Ginseng: A Guided Input Natural Language Search Engine for Querying Ontologies , Jena User Conference, 2008. express behaviors as rules when <something happens> do <action> query statement Friday, May 7, 2010

  33. Data streams: ATOM/RSS/REST APIs, End-user mashup for alignment + RDF Friday, May 7, 2010

  34. Data streams: ATOM/RSS/REST APIs, End-user mashup for alignment + RDF Friday, May 7, 2010

  35. Data streams: ATOM/RSS/REST APIs, End-user mashup for alignment + RDF ATOM FBAPI ATOM RSS0.95 RSS0.95 GDATA RSS0.95 RSS0.95 RSS0.95 Friday, May 7, 2010

  36. Data streams: ATOM/RSS/REST APIs, End-user mashup for alignment + RDF places people ATOM FBAPI www2010 ballroom david karger www2010 302 ATOM max van kleek RSS0.95 starbucks brennan moore RSS0.95 home paul andré GDATA office RSS0.95 photos messages RSS0.95 RSS0.95 emails web pages texts IMs events ??? Friday, May 7, 2010

  37. Data streams: ATOM/RSS/REST APIs, End-user mashup for alignment + RDF places people ATOM FBAPI www2010 ballroom david karger www2010 302 ATOM max van kleek RSS0.95 starbucks brennan moore RSS0.95 home from paul andré GDATA office RSS0.95 photos messages RSS0.95 RSS0.95 emails web pages texts IMs events ??? Friday, May 7, 2010

  38. Data streams: ATOM/RSS/REST APIs, End-user mashup for alignment + RDF places people ATOM currently ! located ! at FBAPI www2010 ballroom david karger www2010 302 ATOM max van kleek RSS0.95 starbucks brennan moore RSS0.95 home from paul andré GDATA office RSS0.95 photos messages RSS0.95 RSS0.95 emails web pages texts IMs events ??? Friday, May 7, 2010

Recommend


More recommend