SNeRG Poster by 8963qQe


									                   SNeRG                                                                 The SNePS Research Group
                                                     Prof. Stuart C. Shapiro, Prof. William J. Rapaport
     Prof. Carl Alphonce, Prof. Josephine Anstey, Prof. Debra T. Burhans, Prof. Michelle L. Gregory, Prof. Jean-Pierre A. Koenig, Prof. David R. Pierce
    Graduate Students: Jonathan Bona, Trupti Devdas Nayak, Albert Goldfain, Frances L. Johnson, Michael Kandefer, John F. Santore, Lunarso Sutanto
                                             Undergraduate Students: Vikranth B. Rao, Isidore DingaMadou

                                                                      Semantic Network Processing System
     The long-term goal of The SNePS Research Group is the design and construction of a natural-language-using computerized cognitive agent, and carrying out the research in artificial intelligence,
     computational linguistics, and cognitive science necessary for that endeavor. The three-part focus of the group is on knowledge representation, reasoning, and natural-language understanding
     and generation. The group is widely known for its development of the SNePS knowledge representation/reasoning system, and Cassie, its computerized cognitive agent.

     Cassie the FEVAHR Agent
                                                                                         GLAIR Architecture
                                                              Grounded Layered Architecture with Integrated Reasoning                                                   A Plan for Detonating Unexploded
                                                                                                                                                                        Landmines (UXOs)
                                                                       Knowledge Level                                                                                   all(a)(Agent(a) =>
                                                                                                                                                NL                       ActPlan(Blowup(a, UXOs),
                                                                                             SNePS                                                                       Act(a,
                                                                       Perceptuo-Motor Level                                                                                   WithSome+(obj,
                                                                                                                                                                                  Near(a, obj),
                                                                                                                                                                                    WithNew({ch ex},
                                                                                                                                                                                          {Charge(ch), Explosion(ex)},
                                                                                                                                                                                             Possess(a, ch),
                                                                       Sensory-Actuator Level                                                   Vision                                          Cascade(Place(a, ch, obj),
     Natural Language Interaction with                                                                                                                                                                   Hide(a),
     FEVAHR (Foveal Extra-Vehicular                                                                                                             Sonar                                                    Waitfor(a, ex),
     Activity Helper-Retriever) Cassie                                                                                                                                                                   SearchforUxo(a))),
     : Who are you?                                                                                                                                                                                       goto(a, SafeZone))))))
      My name is `Cassie'
      and I am the SNePS cognitive agent.                                                                      Proprioception
     : Who did you talk to?                                                                                                                                                        Example SNePS Ontology
       I talked to Stu
     and I talked to Bill
     and I talked to Carl
     and I talked to David
     and I talked to Debbie
     and I talked to J.P.
     and I talked to Josephine
     and I talked to Michelle
     and I am talking to you.
     : Who did you see?                                                                                     The Trial The Trail is an
     I saw Stu                                                                                              interactive drama for an immersive
     and I saw Albert                                                                                       VR environment. Its intelligent agents
                                                                                                            are SNePS-driven.
     and I saw Fran
     and I saw John
     and I saw Jon
     and I saw Lunarso
     and I saw Michael
     and I saw Trupti
                                                                                                                           Contextual Vocabulary Acquisition:From Algorithm to Curriculum
     and I see you.
                 Belief Base Revision with Reconsideration                                                         PIs: William J. Rapaport (CSE & SNeRG) & Michael W. Kibby (Learning & Instruction Dept.)
                                                                                                                   • CVA = computing a meaning for unknown word from contextual clues & prior knowledge
      UAV                                Current Belief Base                                                       •“There came a white hart running into the hall with a white brachet next to him, and thirty couples of black hounds came running
                                                                                                                   after them. As the hart went by the sideboard, the white brachet bit him. The knight arose, took up the brachet and rode away
                    Time         UAV                 INTEL                  TROOPS
                                                                                                                   with the brachet. A lady came in and cried aloud to King Arthur, ‘Sire, the brachet is mine’. There was the white brachet which
                      T1      Red in D1,D2        Red in D1,D3                                     INTEL           bayed at him fast. The hart lay dead; a brachet was biting on his throat, and other hounds came behind.” [Morte D’Arthur]
                      T2      Red in D1,D2        Red in D1,D3,C3,Bridge-D                                         •Cassie learns what “brachet” means: From above text + prior knowledge about harts, animals, King Arthur, etc.; no info
                                                                                                                   about brachetsInput: SNePS version of simplified English narrative. Output: Definition frame (varies with context and prior
                      T3      Red in D1,D2        Red in D1,D3,C3,D4         Red in C3                             knowledge):
                                                                                                                   1.First Sentence:
                    Always      TROOPS > UAV > INTEL                                                                 • A hart runs into King Arthur’s hall.                        3. Full Story:
                                                                                                                         – In the story, B12 is a hart.                              A hart runs into King Arthur’s hall.
                    Always      TROOPS > INTEL > UAV
                                                                                                                         – In the story, B13 is a hall.                              A white brachet is next to the hart.
                                                                                                                         – In the story, B13 is King Arthur’s.                       The brachet bites the hart’s buttock.
  Asserting beliefs into the belief base (or KB) = Adding them to the KB = Stating them to
  be true.     T1: UAV & INTEL disagree on Red troop location => contradiction.                                          – In the story, B12 runs into B13                           The knight picks up the brachet.
  Consolidation makes a belief base consistent -- in this case by removing (or retracting)                           • A white brachet is next to the hart.                          The knight carries the brachet.
  INTEL’s statement. = Contracting the KB by INTEL’s statement. (UAV > INTEL)                      BLUE                  – In the story, B14 is a brachet.                           The lady says that she wants the brachet.
  T2: UAV & INTEL again disagree.                                                                 TROOPS                 – In the story, B14 has the property “white”.               The brachet bays at Sir Tor.
  At T3, BLUE TROOPS confirm an INTEL belief over that of UAV                                                             Therefore, brachets are physical objects.                     • + prior knowledge: only hunting dogs bay
  So, we reverse the INTEL/UAV credibility order. Thus, UAV is disbelieved.                                                    • deduced while reading, using…                       4.--> (defineNoun “brachet”)
  Reconsideration of the KB is defined as consolidation of all base beliefs (current, or not).                                 •…prior knowledge: only physical objects have color Definition of brachet:
  INTEL’s earlier beliefs are recaptured (= returned to the KB), and UAV’s are retracted.
                                                                                                                   2.--> (defineNoun “brachet”)                                       Class Inclusions: hound, dog,
                                                                                                                       Definition of brachet:                                         Possible Actions: bite buttock, bay, hunt,
                                                                                                                       Class Inclusions: phys obj,                                    Possible Properties: valuable, small, white,
                                                                                                                       Possible Properties: white,                                  5. OED: brachet: a kind of hound which hunts by scent
                                                                                                                   • Application: Development of classroom curriculum to teach CVA, based on our CVA algorithms
Identifying Perceptually Indistinguishable Objects:
Is that the same one you saw before?

Crystal Cassie’s view of the world showing two perceptually indistinguishable robots,            Robots used in human subjects’ and Crystal Cassie’s    What Crystal Cassie can see: a table with glasses and a computer lab with two people
one of whom she is following.                                                                    tasks

                                                                                       SNeRG website:

To top