Giving
Computers
Common Sense

Machines are good
at specialized tasks

Computers are still no good at thinking about “ordinary” things

Today’s topics

Why is giving computers common sense hard?

“Fred told the waiter he wanted some chips”

Deep understanding requires enormous amounts of knowledge

Applications with common sense

What do these applications
need to know?

The kinds of things we need
to teach our computers

How much do people know?

How can we build databases of commonsense knowledge?

A problem of great scale

Collecting Commonsense from the General Public

Open Mind Common Sense

Collecting common sense
from the general public

Quality of collected knowledge

Open Mind 1001 Questions

Open Mind Word Expert

Lessons learned from Open Mind

Challenging issues

Putting the Open Mind
Knowledge to Use

Three large-scale knowledge bases
extracted from Open Mind

ConceptNet:
A Semantic Network Mined from Open Mind Common Sense

ConceptNet:
a giant semantic network

Generating semantic networks

Lexico-Syntactic
Pattern Matching Rules

Ontology cleaning

Slide 29

Semantics still quite fuzzy

The ConceptNet Toolkit

Browsing ConceptNet

ConceptNet:
Putting Common Sense
to Practical Use

Using ConceptNet in Applications

Reasoning by linking related concepts

EmpathyBuddy:
Inferring emotion of text

EmpathyBuddy:
Inferring emotion of text

Goal-oriented web search

Slide 39

Affective Color

ARIA: An Adaptive Photo Agent

MAKEBELIEVE: Story Generation

Topic spotting in noisy transcriptions

LifeNet:
A Probabilistic Approach to Commonsense Reasoning

Propositional Common Sense

LifeNet:
 a dynamic model of human activity

LifeNet is a
Dynamic Markov Network

LifeNet supports multiple
 types of inference

Inferring context from speech

Inferring context
from sensory input

Generating LifeNet from ConceptNet

Generating LifeNet propositions

Generating LifeNet links

Generating rule plausibilities

LifeNet quality

Growing LifeNet

Future LifeNet Work

StoryNet:
Treating Common Sense as a Huge Network of Story-Scripts

Stories are powerful way to organize knowledge

Others reasons for turning to stories

Reasoning with stories by analogy

Collecting Commonsense Experiences

Slide 63

OMEX Activities

Contribute a story

Explain a story

Judge—Evaluate stories

Template Design

Motivation and Competition

Current Plot Units

Evaluation of collected knowledge

StoryNet: collecting stories

Putting these systems together

Integrating these networks

Challenging issues

An Architecture for Commonsense Thinking

A Reflective Reasoning Architecture

Integrating these reasoning systems

Common Sense Mini-Scenarios

The many Common Sense realms

Spatial-physical realms

Social-psychological realms

A Matrix of Layers & Realms

Conclusions

Commonsense reasoning
about human life:
a powerful new technology

Applying the Open Mind data

Conclusions