1 / 15

COMP 4060 Natural Language Processing

COMP 4060 Natural Language Processing. Flakey A Communicating Agent. Flakey - A Communicating Agent. Flakey as Communicating Agent Case Frame Representation Concrete and Generic Actions Effects of Actions Inference / Reasoning Two Types of Questions. Intelligent Agent - Flakey.

tara-nelson
Download Presentation

COMP 4060 Natural Language Processing

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. COMP 4060 Natural Language Processing Flakey A Communicating Agent

  2. Flakey - A Communicating Agent • Flakey as Communicating Agent • Case Frame Representation • Concrete and Generic Actions • Effects of Actions • Inference / Reasoning • Two Types of Questions

  3. Intelligent Agent - Flakey • Flakey is a mobile robot at Stanford Research Institute (SRI) • can navigate and plan its path • has visual perception • understands speech and language • does complex reasoning • its "Master" is Kurt Konolige

  4. Flakey's Back Flakey's Front Flakey

  5. runb.mpeg Flakey in Action

  6. Flakey as Communicating Agent "Flakey, bringthis fileto Karen." verbdeterminer nounpreposition noun Noun Phrase Prepositional Phrase inf-VNP PP listenerheaddirect objectindirect object agent actionpatiens recipient

  7. Case Frames for Representing NL "Flakey, bringthis fileto Karen.” headdirect objectindirect object case frame action: bring head-verb patiens: file-1 direct object recipient: Karen indirect object

  8. Mapping Case Frames to Actions case frame agent: Flakey action: bringhead patiens: file-1 direct object recipient: Karen indirect object robot action precondition: have (Flakey, file1) action: bring(Flakey, file1,Karen) effect: not (have (Flakey, file1)) and have (Karen, file1)

  9. Concrete and Generic Actions generic "bring" action (stored concept) precondition: have (agent, object) action: give(agent, object,recipient) effect: not (have (agent, object)) and (have (recipient, object)) concrete "bring" action (generated instance) precondition: have (Flakey, file1) action: give(Flakey, file1,Karen) effect: not (have (Flakey, file1)) and have (Karen, file1)

  10. Effects of Actions - Change KB Preconditions and effects specify world states. World states are stored in the knowledge base (KB). concrete action: bring(Flakey, file1,Karen) precondition: have (Flakey, file1) effect: not (have (Flakey, file1)) and have (Karen, file1) effect of this action delete fromKBhave (Flakey, file1) add to KBhave (Karen, file1)

  11. Flakey - Reasoning, Inference Integrate General Rules (Axioms; Theory) Axiom x y loc: (have(x, y)  (at (x, loc)  at (y, loc))) Reasoning / Inference have (Flakey, object)  at (Flakey, here)  at (object, here) have (Karen, file1)  at (Karen, Karen's-office)  at (file1, Karen's-office)

  12. Flakey - Question Answering I “Flakey, where did you bringthe file.” case frame action: bring patiens: file1 destination: ? Compare to stored case frames: case frame action: bring patiens: file1 destination: Karen Conclusion and answer:“I brought the file to Karen.”

  13. Flakey - Question Answering II Q: “Flakey, where isthe file.” case frame action/status: is subject: the file identify with file1 location: ? refers to loc of file1 Access dynamic KB (world state) Stored from effect of bring-action or pre-stored: ... at (file1, Karen), ... have (Karen,file1), ... A:“The fileisat Karen.” or "Karen hasthe file."

  14. Conclusion • Artificial Intelligence and Agents • Flakey - Example • Natural Language Processing • Reasoning

  15. References • Christel Kemke, COMP 4190 Artificial Intelligence, http://www.cs.umanitoba.ca/~comp4190 • Stuart Russell and Peter Norvig, Artificial Intelligence – A Modern Approach, Prentice Hall, 1995 & 2003 • SRI Video Archives, http://www.ai.sri.com/videos/ • PBS Video on Flakey, http://vvi.onstreammedia.com/cgi-bin/visearch?user=pbs-saf&template=template.html&query=flakey&category=0&viKeyword=flakey&submit=Search

More Related