Upload
demi
View
22
Download
0
Tags:
Embed Size (px)
DESCRIPTION
Analyzer:. Discourse & Situational Context. Lectures I. Overview 2. Simulation Semantics 3. ECG and Best-fit Analysis 4. Compositionality 5. Simulation, Counterfactuals, and Inference. Constructions. Utterance. incremental, competition-based, psychologically plausible. - PowerPoint PPT Presentation
Citation preview
LecturesI. Overview2. Simulation Semantics3. ECG and Best-fit Analysis4. Compositionality5. Simulation, Counterfactuals, and Inference
Constructions
Simulation
Utterance Discourse & Situational Context
Semantic Specification:
image schemas, bindings, action schemas
Analyzer:
incremental,competition-based,
psychologically plausible
Evidence for Simulation Semantics• BASIC ASSUMPTION: SAME REPRESENTATION
FOR PLANNING AND SIMULATIVE INFERENCE– Evidence for common mechanisms for recognition and action
(mirror neurons) in the F5 area (Rizzolatti et al (1996), Gallese 96, Boccino 2002) and from motor imagery (Jeannerod 1996)
• IMPLEMENTATION: – x-schemas affect each other by enabling, disabling or modifying
execution trajectories. Whenever the CONTROLLER schema makes a transition it may set, get, or modify state leading to triggering or modification of other x-schemas. State is completely distributed (a graph marking) over the network.
• RESULT: INTERPRETATION IS IMAGINATIVE SIMULATION!
Active representations• Many inferences about actions derive from what we know
about executing them• X-net representation based on stochastic Petri nets
captures dynamic, parameterized nature of actions• Used for acting, recognition, planning, and language
Walking: bound to a specific walker with a direction or goal
consumes resources (e.g., energy)
may have termination condition(e.g., walker at goal)
ongoing, iterative actionwalker=Harry
goal=home
energy
walker at goal
Task• Interpret simple discourse fragments/blurbs
– France fell into recession. Pulled out by Germany– Economy moving at the pace of a Clinton jog.– US Economy on the verge of falling back into recession
after moving forward on an anemic recovery.– Indian Government stumbling in implementing
Liberalization plan.– Moving forward on all fronts, we are going to be ongoing
and relentless as we tighten the net of justice.– The Government is taking bold new steps. We are
loosening the stranglehold on business, slashing tariffs and removing obstacles to international trade.
Basic Result• A neurally plausible, computational model and an
implementation that is able to cash out the observation that motion, manipulation and spatial concepts are used to convey important and subtle information about abstract domains such as International Economics.– In 1991, India set out on a path of Liberalization. After
making rapid strides in the first few years, the Government policy hit a first of a series of roadblocks in 1995. By 1998, the new BJP Government had reoriented the Government’s policy ..
I/O as Feature Structures• Indian Government stumbling in implementing
liberalization plan
Basic Primitives
• An fine-grained executing model of action and events (X-schemas)
• A factorized representation of state (DBN’s)
• A model of metaphor maps that project bindings from source to target domains.
Features of Representation• Inherently action based, with fine grained
distinctions in resource usage, and temporal evolutions.
• Can deal with concurrent actions, durations, hierarchical action sets, and stochastic actions (selection and effects).
• Highly responsive to a changing environment with uncertain evolutions.
• Can model complex domain constraints in a factorized representation that can compute complex ramifications as well as prior beliefs and possible predictions.
The Target Domain
• Simple knowledge about Economics– Factual (US is a market economy)– Correlational (High Growth => High Inflation)
• Key Requirement:– Must combine background knowledge of economics with inherent
structure and constraints of the target domain with inferential products of metaphoric (and other) projections from multiple source domains.
– Must be able to compute the global impact of new observations (from direct input as well as metaphoric inferences)
Metaphor Maps
• Static Structures that project bindings from source domain f- struct to target domain Belief net nodes by setting evidence on the target network.
• Different types of maps– PMAPS project X- schema Parameters to abstract
domains– OMAPS connect roles between source and target domain– SMAPS connect schemas from source to target domains.
• ASPECT is an invariant in projection.
Results• Model was implemented and tested on discourse fragments from a
database of 30 newspaper stories in international economics from standard sources such as WSJ, NYT, and the Economist. Results show that motion terms are often the most effective method to provide the following types of information about abstract plans and actions.– Information about uncertain events and dynamic changes in goals and
resources. (sluggish, fall, off-track, no steam)– Information about evaluations of policies and economic actors and
communicative intent (strangle-hold, bleed).– Communicating complex, context-sensitive and dynamic economic scenarios
(stumble, slide, slippery slope).– Commincating complex event structure and aspectual information (on the verge
of, sidestep, giant leap, small steps, ready, set out, back on track).
• ALL THESE BINDINGS RESULT FROM REFLEX, AUTOMATIC INFERENCES PROVIDED BY X-SCHEMA BASED INFERENCES.
States are DBN
• Dynamic Bayesian Networks (D(T)BNs) are an extension of Bayesian networks for modeling dynamic systems. – In a DBN, the state at time t is represented by a set of random
variables. The state at time t is dependent on the states at previous time steps.
– Typically, we assume that each state only depends on the immediately preceding state (first-order Markovian), and thus we need to represent the transition distribution P(Zt+1 | Zt).
• This can be done using a two-time-slice Bayesian network fragment (2-TBN) Bt+1, – variables from Zt+1 whose parents are variables from Zt and/or
Zt+1, and variables from Zt without any parents. – Typically, we also assume that the process is stationary, i.e.,
the transition models for all time slices are identical:
An Active Model of Events
• Computationally, actions and events are coded in active representations called x-schemas which are extensions to Stochastic Petri nets.
• x-schemas are fine-grained action and event representations that can be used for monitoring and control as well as for inference.
Preconditions, resources, fine control structure are important aspects of events
X-schema Extensions to Petri Nets
A Walk X-schema
Logical Action Theories• Connection to ARD (or other Action Languages):
– The representation can be used to encode a causal model for a domain description D (in the Syntax of ARD) in that it satisfies all the causal laws in D. Furthermore, a value proposition of the form C after A is entailed by D iff all the terms in C are in Si; the state that results after running the projection algorithm on the action set A. (IJCAI 99)
• Executing representation, – frame axioms are encoded in the topology of the network and
transition firing rules respect them.• Planning as backward reachability or computing
downward closure (IJCAI 99, WWW2002) • Links to linear logic. Perhaps a model of stochastic
linear logic? (SRI CSL TR 2001).
Event Structure in Language
• Fine-grained
• Rich Notion of Contingency Relationships.– Phenomena: Aspect, Tense, Force-dynamics,
Modals, Counterfactuals
• Event Structure Metaphor:– Phenomena: Abstract Actions are
conceptualized in Motion and Manipulation terms. Invariants in projection.
A Climb X-schema
A Schema Controller
• An active controller that sends signals to the embedded schema and transitions based on signals from the embedded schema.• Useful for higher level coordination of actions.
Ready DoneStart Process Finish
SuspendCancel
interrupt resume
iterate
A Generic Process Schema
• Part of Conceptual Structure. • Generalizes over actions and events. Has internal state and models evolution of processes.
Ready DoneStart Process Finish
SuspendCancel
interrupt resume
iterate
About to + (Climb) (Prospective)
Ready DoneStart Process Finish
SuspendCancel
interruptresume
Iterate
EnergyReady
StandingOn top
HoldFind hold
Pull(self)Stabilize
BINDINGS
Be + (Climb)-ING (Progressive)
Ready DoneStart Process Finish
SuspendCancel
interruptresume
Iterate
EnergyReady
StandingOn top
HoldFind hold
Pull(self)Stabilize
BINDINGS
Have + (Climb)-ed (Perfect)
EnergyReady
StandingOn top
HoldFind hold
Pull(self)Stabilize
Ready DoneStart Process Finish
SuspendCancel
interruptresume
Iterate
BINDINGS
Phasal Aspect Maps to the Controller
Ready DoneStart Process Finish
SuspendCancel
interrupt resume
IterateInceptive (start, begin) Iterative (repeat)
Completive (finish, end)Resumptive(resume)
A Precise Notion of Contingency Relations
Activation:Executing one schema causes the enabling, start or continued execution of another schema. Concurrent and sequential activation.
Inhibition:Inhibitory links prevent execution of the inhibited x-schema by activating an inhibitory arc. The model distinguishes between concurrent and sequential inhibition, mutual inhibition and aperiodicity.
Modification:The modifying x-schema results in control transition of the modified xschema. The execution of the modifying x-schema could result in theinterruption, termination, resumption of the modified x-schema.
Connectionist model of knowledge representation and reasoning-- and a useful modeling framework.
1. Representation via focal clusters
2. Temporal synchrony variable binding
SHRUTI: a connectionist cognitive architecture
relational predicate
entity
type
Resources and actions
Basic Features
• Fine grained model of actions and events– Interruption, hierarchy, concurrency,
synchronization, iteration
• Models resources, preconditions, state changes
• Active representation
• Feedback loops– Forward and backward
– Extensions allow hybrid system models
Probabilistic Relation Inference• Scalable Representation of
– States, domain knowledge, ontologies• (Avi Pfeffer 2000, Koller et al. 2001)
• Merges relational database technolgy with Probabilistic reasoning based on Graphical Models.– Domain entities and relational entities– Inter-entity relations are probabilistic functions– Can capture complex dependencies with both simple
and composite slot (chains).• Inference exploits structure of the domain
States
• Factorized Representation of State uses Dynamic Belief Nets (DBN’s)– Probabilistic Semantics– Structured Representation
SHRUTI• SHRUTI does inference
by connections between simple computation nodes
• Nodes are small groups of neurons
• Nodes firing in sync reference the same object