Early Work

Masterman: 100 primitive concepts, 15,000

conceptsWilks: Natural Language system using semantic

networksShapiro: Propositional calculus based semantic

network

Quillian's network

Nodes correspond to word concepts with links to

other concepts used to define it.Organized into planes, each plane a graph that

defines a single meaning of a word.Links are associative and named, and may be multi-

arcs (ors)Use to find relationships between pairs of words

through graph search.

Schank's Conceptual Dependency

Four primitive conceptualizations: ACT (actions),

PP (objects – picture producers), AA (action

modifiers or aiders), PA (picture modifiers or

aiders)Fixed set of primitive actions: ATRANS, PTRANS,

PROPEL, MOVE, GRASP, INGEST, EXPEL,

INGEST, MTRANS, MBUILD, CONC, SPEAK,

ATTEND.

Schank (cont'd)

Different kind of links (multi-arcs): actor (agent),

attribute, object, recipient, donor, direction,

instrumental conceptualization, causality, state of

change, possessor, partClaim is that all knowledge can be broken down

into this primitive concepts.Used to create canonical forms of natural language

expressions.

Simmon's Case Based Represent.

Based on Filmore's case structure of verbs.Verbs are the main nodesHave actor, object, instrument, location, and timeCaptures deep structure of sentence

Scripts (Schank and Abelson)

Used to incorporate real-world, common-sense

default knowledge and to organize large amounts of

information.Incorporates expected actions and elements. The

actual situation may differ.Scripts have the following components: Entry

conditions, Results, Props, Roles, and Scenes.Each element is represented by conceptual dep.

Easy Example

Amy went out to lunch. She sat at a table and called a

waitress, who brought her a menu. She ordered a

sandwich.

Hard Example

John visited his favorite restaurant on the way to the

concert. he was pleased by the bill because he liked

Mozart.

Frames (Minsky)

Frames are structured entities with named slots and

attached values. Values may be procedural (think

objects).Frames are related to one another.Example slots: ID, relationship to other frames,

description of requirements, procedural

information, default information, new instance

information.Frames support class inheritance.

Conceptual Graphs (Sowa)

Two types of nodes: concepts and conceptual

relations.Arcs are not labeled – a conceptual relation node

appears between two concept nodes instead.Concept nodes may be concrete or abstract objects.Each graph represents a single proposition.A graph may be boxed and used as a node in

another graph.

Conceptual Graphs (cont'd)

Every concept is of a unique individual of a give

type.Each concept box is labeled with a type label. (:)A concept could be a specific, but unnamed

individual. (#)A name is different from the object (name

conceptual relation)A concept may be an unspecified individual (*).There is a type hierarchy.

Conceptual Graphs: Rules

The following rules may be used to modify graphs:An exact copy may be made (copy rule).A generic marker may be replaced by an individual

marker (restrict).A type may be replaced by a subtype as long as the

subtype is consistent with the referent (restrict).Two graphs may be joined by a common concept

(join).

Propositional Concepts

Graphs may be used to represent relations between

propositions (causality, time, etc.) A propositional

concept is indicated by a box around a conceptual

graph and may be used as a node in another graph.

Neg and conjunction are conceptual relations.

Conceptual graphs have the same expressive power

as the predicate calculus.

Subsumption Architecture (Brooks)

The idea is that intelligence emerges from the

interaction of architectures of simpler behaviors.Layered collection of task-handlers which interact

with neighboring layers.Each task-handler perceives (input from a lower

level), applies a simple set of condition-action

production rules, and produces action-orient output

(to a higher level).

Brooks (cont'd)

No global state.Some feedback to lower levels.Example: Machine robot: Three levels – Explore,

Wander, Avoid.