CBMM Memo No. 019
June 10, 2014
The Genesis Story Understanding and Story Telling System
A 21st Century Step toward Artificial Intelligence
by
Patrick Henry Winston
Abstract: Story understanding is an important differentiator of human intelligence, perhaps the most important
differentiator. The Genesis system was built to model and explore aspects of story understanding using simply
expressed, 20-100 sentence stories drawn from sources ranging from fairy tales to Shakespeare’s plays. I describe
Genesis at work as it reflects on its reading, searching for concepts, reads stories with controllable allegiances
and cultural biases, models personality traits, answers basic questions about why and when, notes concept onsets,
anticipating trouble, calculates similarity using concepts, models question-driven interpretation, aligns similar
stories for analogical reasoning, develops summaries, and tells and persuades using a reader model. I conclude with
thoughts on how Genesis would describe people in pictures and video, thus engaging with the CBMM challenge
problem.
This work was supported, in part, by the Center for Brains, Minds and
Machines (CBMM), funded by NSF STC award CCF - 1231216.
Vision: a distinguishing difference and a shared substrate
Marvin Minsky published Steps toward Artificial Intelligence a little more than 50 years ago (1961). Now, half a
century later, Deep Blue, Watson, and Siri amaze everyone and stand as testaments to engineering skill, but the
applications dreamed of in 1961 remain far from realized:
• No language system has the common sense required to understand what it is reading and the implications that
flow from common sense understanding.
• No vision system understands the visual world well enough to report instances of more than a handful of the 48
actions cited in DARPA’s 2010 Mind’s Eye BAA.
Why are there no such systems? I think it is because we remain ignorant of how our species is different from
others, and we remain ignorant of how the differences are enabled by a shared substrate.
In this white paper, I focus on story understanding, which I believe is the key difference between us and all other
primates, living and extinct. I catalog our work on story-understanding tools, describing some of the capabilities
of our Genesis story-understanding system.
Steps: Specify behavior, develop representations, build Genesis
It is evident that we learn a great deal about life from stories, which include fairy and folk tales, religious parables,
ethnic narratives, entertainment, news, history, literature, and experience. It is also evident that we learn a great
deal professionally from case studies in law, business, medicine, defense, diplomacy, science, and engineering.
To understand how we understand and learn from stories, I believe we must first specify the behavior we want
to model, then develop a suite of constraint exposing representations, then build our Genesis story understanding
system so as to test our ideas. I believe success will lead to understanding human intelligence and to paradigmshifting engineering practice built on that understanding.
What Genesis models
I have elaborated on our perspective in a trilogy: The Strong Story Hypothesis and the Directed Perception Hypothesis (2011) introduces two key hypotheses about human intelligence and ties story telling to directed perception;
The Right Way (2012b) emphasizes mythological steps; and The next 50 years: A personal view (2012a) focuses
on asking the right questions about how we are different from other primates and how we are the same.
My purpose here is to add to those previous papers an account of what the Genesis system now models by way
of reading, deliberating, reflecting, cultural bias, personality understanding, question answering, onset detection,
similarity measurement, similarity based retrieval, question driven interpretation, analogical interpretation, reader
aware story telling, persuasion, and summary.
Genesis reads stories, common sense rules, and concept descriptions
We of the Genesis Group spend a lot of time with a short summary of Macbeth. Shakespeare, in general, tells us
about the human condition, his plays constitute a good anvil for hammering out story understanding ideas.
Macbeth is a thane and Macduff is a thane. Lady Macbeth is evil and greedy. Duncan is the king, and
Macbeth is Duncan’s successor. Duncan is an enemy of Cawdor. Macduff is an enemy of Cawdor. Duncan
is Macduff’s friend. Macbeth defeated Cawdor. Duncan becomes happy because Macbeth defeated
Cawdor. Witches had visions and danced. Macbeth talks with Witches. Witches make predictions.
Witches astonish Macbeth. Macbeth becomes Thane of Cawdor. Duncan rewarded Macbeth because
Duncan became happy. Macbeth wants to become king because Lady Macbeth persuaded Macbeth to
want to become the king. Macbeth invites Duncan to dinner. Duncan goes to bed. Duncan’s guards
become drunk and sleep. Macbeth murders Duncan. Macbeth murders guards. Macbeth becomes king.
Malcolm and Donalbain flee. Macbeth’s murdering Duncan leads to Macduff’s fleeing to England. Then,
Macduff’s fleeing to England leads to Macbeth’s murdering Lady Macduff. Macbeth hallucinates at a
1
dinner. Lady Macbeth says he hallucinates often. Everyone leaves. Macbeth’s murdering Duncan leads
to Lady Macbeth’s becoming distraught. Lady Macbeth has bad dreams. Lady Macbeth thinks she has
blood on her hands. Lady Macbeth kills herself. Birham Wood is a forest. Burnham Wood goes to
Dunsinane. Macduff’s army attacks Macbeth’s castle. Macduff curses Macbeth. Macbeth refuses to
surrender. Macduff kills Macbeth. The end.
I noted early on that what works for Macbeth works also for other kinds of conflict. All of the infrastructure
and much of the knowledge developed to deal with Macbeth transferred over to our work on the Estonia-Russia
cyber war of 2007.
Estonia built Estonia’s computer networks. Estonia insulted Russia because Estonia relocated a war
memorial. Russia wanted to harm Estonia. Someone attacked Estonia’s computer networks after Estonia
harmed Russia. Russia attacked Estonia’s computer networks. The attack on Estonia’s computer networks
included the jamming of the web sites. The jamming of the sites showed that someone did not respect
Estonia. Estonia created a center to study computer security. Estonia believed other states would support
the center. The end.
The Estonia-Russia cyber war is much like other conflicts. Dealing, for example, with the Congo civil war in
a retrieval experiment introduced no challenges.
Genesis deploys common sense rules to develop basic understanding
07:46:09 EDT 13-Apr-2014
Demonstrate
||| Views
Read About
Controls Start viewer
Experts
Elaboration graph Inspector
Sources
Results Summary
Story
Macbeth/revenge
Rules: 39
Inferences: 64
Lady Macbeth
is Macbeth's
wife.
Macbeth is Lady
Macbeth's
husband.
Macbeth is Lady
Macbeth's
relation.
Lady Macbeth
is Macbeth's
friend.
Lady Macduff
is Macduff's
wife.
Macduff is Lady
Macduff's
husband.
Lady Macbeth
is Macbeth's
relation.
Macbeth is Lady
Macbeth's friend.
Macduff is
Cawdor's
enemy.
Macduff is
Duncan's
friend.
Macduff is Lady
Macduff's relation.
Lady Macduff
is Macduff's
friend.
Duncan is
Cawdor's
enemy.
Duncan is
Macduff's
friend.
Lady Macduff
is Macduff's
relation.
Macduff is Lady
Macduff's friend.
Duncan
is a king.
Lady Macbeth
is Macbeth's
relation.
Macbeth is Lady
Macbeth's friend.
Macbeth is
Duncan's
successor.
Macbeth is Lady
Macbeth's
relation.
Lady Macbeth
is Macbeth's
friend.
Macbeth
defeats
Cawdor.
Duncan
becomes
happy.
Duncan
rewards
Macbeth.
Lady Macbeth
persuades Macbeth
to want to become
king.
Macbeth
wants to
become king.
Macbeth
murders
Duncan.
Macbeth
harms
Macduff.
Macbeth
harms
Duncan.
Macbeth
harms Lady
Macduff.
Macbeth
becomes
king.
Duncan
becomes
dead.
Lady Macbeth
becomes
queen.
Macbeth
becomes
happy.
Macbeth
harms
Duncan.
Macbeth
angers
Macduff.
Lady Macbeth
kills herself.
Lady Macbeth
harms herself.
Lady Macbeth
harms herself.
Macbeth
becomes
unhappy.
Macbeth
harms
Macduff.
Lady Macduff
becomes
unhappy.
Macbeth
angers Lady
Macduff.
Macduff
becomes
unhappy.
Lady Macbeth
angers
Macbeth.
Macduff kills
Macbeth.
Macduff
harms
Macbeth.
Macduff
harms
Macbeth.
Concepts: 14
Discoveries: 9
Explicit elements: 43
Inferred elements: 38
Total elements: 81
Story reading time: 4.9 sec
Total time elapsed: 13.9 sec
Macbeth
angers
Macduff.
Lady Macduff
is Macduff's
relation.
Macduff is Lady
Macduff's friend.
Macduff is Lady
Macduff's relation.
Lady Macduff
is Macduff's
friend.
Macduff
flees to
England.
Lady Macbeth
becomes
distraught.
Macbeth
murders Lady
Macduff.
Macbeth
harms Lady
Macduff.
Macbeth
harms
Macduff.
Macbeth
harms Lady
Macduff.
Macduff
becomes
unhappy.
Macbeth
harms
Macduff.
Macbeth
harms
Duncan.
Lady Macbeth
harms
Macbeth.
Macduff
harms Lady
Macbeth.
Lady Macduff
becomes
dead.
Lady Macbeth
becomes
dead.
Macbeth
becomes
dead.
Analysis
Revenge
Success
Answered prayer
Mistake because unh...
Mistake because har...
Mistake because har...
Pyrrhic victory
Pyrrhic victory
Suicide
100%
Elaboration graph
Figure 1: Genesis produces elaboration graphs, as shown for a summary of Macbeth. Common sense rules connect explicit
and inferred elements of the story. (This figure is included at high resolution in the electronic version of this document.)
Genesis uses Boris Katz’s START (1997) system to translate Genesis English into an inner language of relations
and events. Genesis then uses common sense to build an elaboration graph as shown in figure 1. Elements in
yellow are established by inference rules as indicated by black connecting lines. The story itself supplies the
elements in white, orange, and blue.
Explanation rules tie elements in orange to other elements. In reading a story, we humans seek explanations,
and if none is offered, we assume connections that may hold, but not with sufficient regularity to be added by
2
inference rules. In Macbeth, the story itself supplies no explicit reason why Macbeth murders Duncan and no
inference rule supplies a reason, so an explanation rule connects the murder to Macbeth’s wanting to be king,
Macbeth’s being Duncan’s successor, and Duncan’s being king.
Leads-to expressions connect elements in blue to other elements. These are supplied by expressions in the
story, such as Macbeth’s murdering Duncan leads to Macduff’s fleeing to England. Such expressions indicate
when two elements are known to be connected but the exact causal path is not known, or at least not supplied.
Genesis reflects on its reading, searching for concepts
Once Genesis builds the elaboration graph, Genesis uses ordinary search to find instances of concept patterns.
In figure 2, Genesis notes a revenge pattern because Macbeth’s harming Macduff leads to Macduff’s harming
Macbeth. In figure 3, Genesis notes a Pyrrhic victory pattern because Macbeth’s actions at first make him happy,
but then lead to his own harm.
07:51:26 EDT 13-Apr-2014
Demonstrate
||| Views
Read About
Controls Start viewer
Experts
Elaboration graph Inspector
Macbeth
harms
Macduff.
Sources
Macbeth
angers
Macduff.
Results Summary
Story
Macduff
harms
Macbeth.
Macduff kills
Macbeth.
Inspector
||| Views
Controls Start viewer
Experts
Elaboration graph Inspector
Sources
Results Summary
Story
Macbeth/revenge
Rules: 39
Lady Macbeth
is Macbeth's
wife.
Macbeth is Lady
Macbeth's
husband.
Macbeth is Lady
Macbeth's relation.
Lady Macbeth
is Macbeth's
friend.
Lady Macduff
is Macduff's
wife.
Macduff is Lady
Macduff's
husband.
Lady Macbeth
is Macbeth's
relation.
Macbeth is Lady
Macbeth's friend.
Macduff is
Cawdor's
enemy.
Macduff is
Duncan's
friend.
Macduff is Lady
Macduff's relation.
Lady Macduff
is Macduff's
friend.
Duncan is
Cawdor's
enemy.
Duncan is
Macduff's
friend.
Lady Macduff
is Macduff's
relation.
Macduff is Lady
Macduff's friend.
Duncan
is a king.
Lady Macbeth
is Macbeth's
relation.
Macbeth is Lady
Macbeth's friend.
Macbeth is
Duncan's
successor.
Macbeth is Lady
Macbeth's relation.
Lady Macbeth
is Macbeth's
friend.
Macbeth
defeats
Cawdor.
Duncan
becomes
happy.
Duncan
rewards
Macbeth.
Lady Macbeth
persuades
Macbeth to want
to become king.
Macbeth wants to
become king.
Macbeth
murders
Duncan.
Macbeth
harms
Macduff.
Macbeth
harms
Duncan.
Macbeth
harms Lady
Macduff.
Macbeth
becomes
king.
Duncan
becomes
dead.
Lady Macbeth
becomes
queen.
Macbeth
becomes
happy.
Macbeth
harms
Duncan.
Macbeth
angers
Macduff.
Lady
Macbeth
kills herself.
Lady Macbeth
harms herself.
Lady Macbeth
harms herself.
Macbeth
becomes
unhappy.
Macbeth
harms
Macduff.
Lady Macduff
becomes
unhappy.
Macbeth
angers Lady
Macduff.
Macduff
becomes
unhappy.
Lady Macbeth
angers
Macbeth.
Macduff kills
Macbeth.
Macduff
harms
Macbeth.
Macduff
harms
Macbeth.
Inferences: 64
Concepts: 14
Discoveries: 9
Explicit elements: 43
Inferred elements: 38
Total elements: 81
Story reading time: 6.2 sec
Total time elapsed: 15.7 sec
Macbeth
angers
Macduff.
Lady Macduff
is Macduff's
relation.
Macduff is Lady
Macduff's friend.
Macduff is Lady
Macduff's relation.
Lady Macduff
is Macduff's
friend.
Macduff
flees to
England.
Lady Macbeth
becomes
distraught.
Macbeth
murders Lady
Macduff.
Macbeth
harms Lady
Macduff.
Macbeth
harms
Macduff.
Macbeth
harms Lady
Macduff.
Macduff
becomes
unhappy.
Macbeth
harms
Macduff.
Macbeth
harms
Duncan.
Lady Macbeth
harms
Macbeth.
Macduff
harms Lady
Macbeth.
Lady Macduff
becomes dead.
Lady Macbeth
becomes dead.
Macbeth
becomes
dead.
Analysis
Revenge
Success
Answered pra...
Mistake beca...
Mistake beca...
Mistake beca...
Pyrrhic victory
Pyrrhic victory
Suicide
100%
Elaboration graph
Figure 2: Genesis finds concept patterns by searching the elaboration graph. Here, Genesis shows revenge elements in green
in the Elaboration graph panel provides a close-up view in the Inspector panel.
Once Genesis builds the elaboration graph, Genesis uses ordinary search to find instances of concept patterns.
In figure 2, Genesis notes a revenge pattern because Macbeth’s harming Macduff leads to Macduff’s harming
Macbeth. In figure 3, Genesis notes a Pyrrhic victory pattern because Macbeth’s actions at first make him happy,
but then lead to his own harm.
Our first work on concept patterns appeared in the MEng thesis of David Nackoul (2010).
3
07:43:58 EDT 13-Apr-2014
Demonstrate
||| Views
Read About
Controls Start viewer
Experts
Elaboration graph Inspector
Sources
Macbeth
wants to
become king.
Macbeth
murders
Duncan.
Duncan
is a king.
Macbeth
becomes
king.
Results Summary
Macbeth
becomes
happy.
Story
Macduff
flees to
England.
Macbeth
murders Lady
Macduff.
Macbeth
harms Lady
Macduff.
Macbeth
harms
Macduff.
Macbeth
angers
Macduff.
Macduff kills
Macbeth.
Macduff
harms
Macbeth.
Macbeth is
Duncan's
successor.
Lady Macduff
is Macduff's
friend.
Inspector
||| Views
Controls Start viewer
Experts
Elaboration graph Inspector
Sources
Results Summary
Story
Macbeth/revenge
Rules: 39
Lady Macbeth is
Macbeth's wife.
Macbeth is Lady
Macbeth's husband.
Macbeth is Lady
Macbeth's relation.
Lady Macbeth is
Macbeth's friend.
Lady Macduff is
Macduff's wife.
Macduff is Lady
Macduff's husband.
Lady Macbeth is
Macbeth's relation.
Macbeth is Lady
Macbeth's friend.
Macduff is
Cawdor's
enemy.
Macduff is
Duncan's
friend.
Macduff is Lady
Macduff's relation.
Lady Macduff is
Macduff's friend.
Duncan is
Cawdor's
enemy.
Duncan is
Macduff's
friend.
Lady Macduff is
Macduff's relation.
Macduff is Lady
Macduff's friend.
Duncan is
a king.
Lady Macbeth is
Macbeth's relation.
Macbeth is Lady
Macbeth's friend.
Macbeth is
Duncan's
successor.
Macbeth is Lady
Macbeth's relation.
Lady Macbeth is
Macbeth's friend.
Lady Macduff is
Macduff's relation.
Macduff is Lady
Macduff's friend.
Macduff is Lady
Macduff's relation.
Lady Macduff is
Macduff's friend.
Macbeth
defeats
Cawdor.
Duncan
becomes
happy.
Duncan
rewards
Macbeth.
Lady Macbeth persuades
Macbeth to want to become king.
Inferences: 64
Macbeth
wants to
become king.
Macbeth
murders
Duncan.
Macbeth
harms
Macduff.
Macbeth
harms
Duncan.
Macbeth
harms Lady
Macduff.
Macbeth
becomes
king.
Duncan
becomes
dead.
Lady Macbeth
becomes queen.
Macbeth
becomes
happy.
Macbeth
harms
Duncan.
Macbeth
angers
Macduff.
Lady Macbeth
kills herself.
Lady Macbeth
harms herself.
Lady Macbeth
harms herself.
Macbeth
becomes
unhappy.
Macbeth
harms
Macduff.
Lady Macduff
becomes
unhappy.
Lady Macbeth
angers Macbeth.
Macduff kills
Macbeth.
Macbeth
angers Lady
Macduff.
Macduff
becomes
unhappy.
Macduff
harms
Macbeth.
Macduff
harms
Macbeth.
Concepts: 14
Discoveries: 9
Explicit elements: 43
Inferred elements: 38
Total elements: 81
Story reading time: 4.9 sec
Total time elapsed: 13.9 sec
Macbeth
angers
Macduff.
Macduff flees to
England.
Lady Macbeth
becomes
distraught.
Macbeth murders Lady Macduff.
Macbeth
harms
Macduff.
Macbeth
harms Lady
Macduff.
Macbeth
harms
Macduff.
Macbeth
harms Lady
Macduff.
Macduff
becomes
unhappy.
Macbeth
harms
Duncan.
Lady Macbeth
harms Macbeth.
Macduff
harms Lady
Macbeth.
Lady Macduff
becomes dead.
Lady Macbeth
becomes dead.
Macbeth
becomes
dead.
Analysis
Revenge
Success
Answered prayer
Mistake because unh...
Mistake because har...
Mistake because har...
Pyrrhic victory
Pyrrhic victory
Suicide
100%
Elaboration graph
Figure 3: Genesis extracts the pyrrhic victory elements from the full elaboration graph.
Genesis reads stories with controllable allegiances and cultural biases
Genesis’s interpretation depends on the common sense rules, concept patterns supplied, and biases of the reader.
In figure 4, the 2007 cyber war between Estonia and Russia is viewed as misguided revenge buy a reader friendly
to Estonia; the same cyber war is viewed as teaching Estonia a lesson by a reader friendly to Russia.
Similarly, in figure 5, an Eastern reader of Macbeth is more likely than a Western reader to see Macduff’s
killing of Macbeth situationally, as a consequence of the situation Macduff is in; a Western reader is more like to
see the same killing dispositionally, as a consequence of insanity.
The most ambitious examples of cultural influence appear in the MEng thesis of Wolfgang Victor Yarlott
(2014), who demonstrated Genesis at work on selected folktales from Native American Crow culture.
Genesis models personality traits
Genesis notes what various sorts of people do, which enables Genesis to infer personality traits on the basis of
what people do, which enables Genesis to use personality traits to explain acts.
In figure 6, Genesis notes early in the Macbeth story that Macduff assaults someone, a characteristic of vicious
people, leading Genesis to consider Macduff to be vicious. Then, thinking that Macduff is vicious, Genesis explains
Macduff’s killing of Macbeth as a consequence of anger and Macduff’s vicious nature.
Our first work on personality traits appeared in the MEng thesis of Susan Song (2012).
Genesis answers basic questions about why and when
Genesis answers questions on various levels. As shown in figure 7, Genesis answers questions about cyber war by
reciting elaboration graph elements connected to the target event and by noting how target events are embedded
in concepts. Additionally, as shown in figure 8, Genesis answers questions using personality traits associated with
the target event.
Genesis notes concept onsets, anticipating trouble
Concepts generally involve leads-to relations. Noting the first part of a leads-to relation provides early warning of
possible evolutions. As shown in figure 9, the potential for revenge, misguided retaliation, and mistake are noted
4
07:54:08 EDT 13-Apr-2014
Demonstrate
||| Views
Read About
Controls Start viewer
Experts
Elaboration graph Inspector
Estonia doesn't
respect Russia.
Russia wants
to harm
Estonia.
Russia wants to
damage
computer
networks.
Russia attacks
computer
networks.
Estonia
angers
Russia.
Estonia believes
computer
networks are
valuable.
Someone attacks
computer networks.
Estonia owns
computer
networks.
Russia
attacks
Estonia.
Sources
Results Summary
Russia
harms
Estonia.
Story
Estonia doesn't
respect Russia.
Russia wants
to harm
Estonia.
Russia wants to
damage
computer
networks.
Russia attacks
computer
networks.
Estonia
angers
Russia.
Estonia believes
computer
networks are
valuable.
Someone attacks
computer networks.
Estonia owns
computer
networks.
Russia
attacks
Estonia.
Russia
harms
Estonia.
Russia is
my friend.
Estonia is
my friend.
Inspector
||| Views
Controls Start viewer
Experts
Elaboration graph Inspector
Sources
Results Summary
Story
Estonia/revenge
Estonia/lesson
Rules: 33
Rules: 33
Estonia believes
computer networks
are valuable.
Estonia builds
computer networks.
Inferences: 19
Concepts: 14
Estonia owns
computer
networks.
Estonia
relocates war
memorial.
Estonia insults
Russia.
Estonia harms
Russia.
Estonia angers
Russia.
Estonia doesn't
respect Russia.
Russia wants
to harm
Estonia.
Estonia is
my friend.
Discoveries: 5
Russia wants to
damage computer
networks.
Russia attacks
computer networks.
Someone attacks
computer networks.
Russia wants to
attack computer
networks.
Estonia builds
computer
networks.
Inferences: 19
Estonia owns
computer
networks.
Estonia believes
computer networks
are valuable.
Estonia
relocates war
memorial.
Estonia insults
Russia.
Estonia harms
Russia.
Estonia
harms me.
Estonia angers
Russia.
Russia is
my friend.
Concepts: 14
Estonia doesn't
respect Russia.
Russia wants to
damage computer
networks.
Russia wants to harm Estonia.
Someone attacks
computer networks.
Discoveries: 5
Russia
becomes
unhappy.
Explicit elements: 18
Russia
becomes
unhappy.
Explicit elements: 18
Inferred elements: 18
Inferred elements: 18
Total elements: 36
Someone
harms Estonia.
Russia attacks
Estonia.
Russia
harms me.
Russia angers
Estonia.
Russia
becomes
happy.
Estonia
becomes
unhappy.
Russia harms
Estonia.
Estonia creates
center.
Total elements: 36
Estonia studies
computer security.
Story reading time: 1.3 sec
Russia attacks
computer networks.
Someone
harms Estonia.
Russia attacks
Estonia.
Russia angers
Estonia.
Russia
becomes
happy.
Estonia
becomes
unhappy.
Russia harms
Estonia.
Estonia creates
center.
Russia is a
country.
Estonia is
a country.
Computer
networks are
artifacts.
Someone attacks
computer networks
after Estonia's
harming Russia.
Computer networks
include web sites'
jamming.
Estonia studies
computer security.
Story reading time: 1.4 sec
Russia wants to
attack computer
networks.
Russia harms
Estonia.
Total time elapsed: 4.9 sec
Russia harms
Estonia.
Total time elapsed: 5.0 sec
Russia is a
character.
I am Estonia's friend.
Estonia is a
character.
Russia is
a country.
Estonia is a
country.
Computer
networks are
artifacts.
Someone attacks
computer networks
after Estonia's
harming Russia.
For sites to jam shows that
Computer networks include
someone doesn't respect
web sites' jamming.
Estonia.
Someone doesn't
respect Estonia.
Estonia believes
states support
center.
States support
center.
Analysis
I am Russia's
friend.
Russia is a
character.
States support
center.
Estonia believes
states support
center.
Estonia is a
character.
For sites to jam shows that
someone doesn't respect
Estonia.
Someone doesn't
respect Estonia.
Analysis
Revenge
Success
Answered p...
Mistake be...
Misguided r...
Revenge
Success
Answered p...
100%
Mistake be...
Teaching a l...
100%
Elaboration graph
Figure 4: Genesis views the 2007 cyber war between Estonia and Russia from the perspective of a friend of Estonia on the
left and from the perspective of a friend of Russia on the right. One sees misguided revenge; the other, teaching a lesson.
07:55:57 EDT 13-Apr-2014
Demonstrate
||| Views
Read About
Controls
Start viewer
Experts
Macbeth
harms
Macduff.
Elaboration graph Inspector
Macbeth
angers
Macduff.
Sources
Results Summary
Macduff
kills
Macbeth.
Story
Macduff
harms
Macbeth.
Macduff
isn't sane.
Macduff
kills
Macbeth.
Inspector
||| Views
Controls Start viewer
Experts
Elaboration graph Inspector
Sources
Results Summary
Story
Macbeth/eastern
Macbeth/western
Rules: 38
Rules: 38
Lady Macbeth is
Macbeth's wife.
Macbeth is Lady
Macbeth's husband.
Macbeth is Lady
Macbeth's relation.
Lady Macbeth is
Macbeth's friend.
Lady Macduff is
Macduff's wife.
Macduff is Lady
Macduff's husband.
Lady Macbeth is
Macbeth's relation.
Macbeth is Lady
Macbeth's friend.
Macbeth defeats
Cawdor.
Inferences: 57
Concepts: 14
Duncan
becomes happy.
Duncan rewards
Macbeth.
Lady Macbeth persuades
Macbeth to want to become
king.
Macbeth wants
to become king.
Macbeth
becomes king.
Macbeth
murders
Duncan.
Lady Macbeth
becomes queen.
Duncan
becomes dead.
Macbeth harms
Duncan.
Macbeth harms
Macduff.
Lady Macduff
becomes
unhappy.
Macbeth angers Lady Macduff.
Macduff
becomes
unhappy.
Discoveries: 9
Duncan is
Macduff's friend.
Macduff is Lady
Macduff's relation.
Lady Macduff is
Macduff's friend.
Macbeth harms
Lady Macduff.
Lady Macbeth is
Macbeth's relation.
Lady Macduff is
Macduff's relation.
Macduff is Lady
Macduff's friend.
Macbeth
becomes happy.
Duncan
is a king.
Macbeth is Lady
Macbeth's relation.
Macbeth is Lady
Macbeth's friend.
Macbeth is
Duncan's
successor.
Lady Macduff is
Macduff's relation.
Lady Macbeth is
Macbeth's friend.
Macduff is Lady
Macduff's relation.
Macduff is Lady
Macduff's friend.
Explicit elements: 44
Explicit elements: 43
Inferred elements: 35
Total elements: 79
Lady Macbeth is
Macbeth's friend.
Lady Macduff is
Macduff's wife.
Macduff is Lady
Macduff's husband.
Lady Macbeth is
Macbeth's relation.
Macbeth is Lady
Macbeth's friend.
Duncan
is a king.
Lady Macbeth is
Macbeth's relation.
Macduff is Lady
Macduff's relation.
Lady Macduff is
Macduff's friend.
Macbeth is
Duncan's
successor.
Macbeth is Lady
Macbeth's relation.
Lady Macduff is
Macduff's relation.
Macduff is Lady
Macduff's friend.
Duncan is
Macduff's friend.
Lady Macduff is
Macduff's relation.
Macbeth is Lady
Macbeth's friend.
Macbeth
isn't sane.
Macduff is Lady
Macduff's relation.
Lady Macbeth is
Macbeth's friend.
Macbeth defeats
Cawdor.
Duncan
becomes happy.
Duncan rewards
Macbeth.
Lady Macbeth persuades
Macbeth to want to become
king.
Macbeth wants
to become king.
Macbeth
murders
Duncan.
Duncan
becomes dead.
Lady Macbeth
becomes queen.
Macbeth
becomes happy.
Macbeth
becomes king.
Macbeth harms
Duncan.
Macbeth harms
Macduff.
Lady Macduff
becomes
unhappy.
Macduff kills
Macbeth.
Macduff harms
Macbeth.
Macbeth angers Lady Macduff.
Macbeth harms
Macduff.
Macbeth harms
Lady Macduff.
Inferred elements: 38
Total elements: 81
Story reading time: 4.1 sec
Total time elapsed: 9.6 sec
Macbeth is Lady
Macbeth's relation.
Inferences: 57
Discoveries: 4
Duncan is
Cawdor's
enemy.
Macbeth is Lady
Macbeth's husband.
Concepts: 14
Macbeth harms
Macduff.
Macduff is
Cawdor's
enemy.
Lady Macbeth is
Macbeth's wife.
Story reading time: 4.2 sec
Total time elapsed: 9.8 sec
Macbeth
isn't sane.
Macduff is Lady
Macduff's friend.
Lady Macbeth
isn't sane.
Lady Macduff is
Macduff's friend.
Lady Macduff is
Macduff's friend.
Macduff
isn't sane.
Macbeth angers
Macduff.
Macduff flees
to England.
Lady Macbeth
becomes
distraught.
Macbeth
murders Lady
Macduff.
Macbeth harms
Lady Macduff.
Macbeth harms
Lady Macduff.
Macduff
becomes
unhappy.
Macbeth angers
Macduff.
Lady Macbeth
kills herself.
Lady Macbeth
harms herself.
Lady Macbeth
harms herself.
Macbeth
becomes
unhappy.
Lady Macbeth
angers Macbeth.
Macduff kills
Macbeth.
Macduff harms
Macbeth.
Macduff harms
Macbeth.
Macduff
becomes
unhappy.
Macbeth harms
Macduff.
Lady Macbeth
harms Macbeth.
Macduff harms
Lady Macbeth.
Lady Macduff
becomes dead.
Lady Macbeth
becomes dead.
Macbeth
becomes dead.
Analysis
Revenge
Macbeth angers
Macduff.
Macduff flees
to England.
Lady Macbeth
becomes
distraught.
Macbeth
murders Lady
Macduff.
Macbeth harms
Lady Macduff.
Macbeth harms
Lady Macduff.
Macduff
becomes
unhappy.
Macbeth angers
Macduff.
Lady Macbeth
kills herself.
Lady Macbeth
harms herself.
Lady Macbeth
harms herself.
Macbeth
becomes
unhappy.
Lady Macbeth
angers Macbeth.
Macbeth harms
Macduff.
Lady Macbeth
harms Macbeth.
Macduff harms
Lady Macbeth.
Lady Macduff
becomes dead.
Lady Macbeth
becomes dead.
Macbeth
becomes dead.
Macduff harms
Macbeth.
Analysis
Success
Answer...
Mistake ...
Mistake ...
Mistake ...
Pyrrhic ...
Pyrrhic ...
Suicide
Insane violence
100%
Insane violence
Insane violence
Suicide
100%
Elaboration graph
Figure 5: Genesis views the killing of Macbeth from Eastern and Western points of view. One the left, the Eastern view, the
killing is situational; on the right, the Western view, dispositional.
early. All three eventually ensue, as shown in figure 10.
5
08:00:14 EDT 13-Apr-2014
Demonstrate
||| Views
Read About
Controls Start viewer
Personality analysis
Experts
Predictions
Elaboration graph Inspector
Sources
Results Summary Story
||| Views Controls Start viewer Experts Elaboration graph Inspector Sources
Concept analysis
ambitious
evil
crazy
machiavellian
Results Summary Story
vicious
Vicious person's characteristics
Macduff seems to be vicious because Macduff assaults someone.
Rules: 3
Macduff kills Macbeth because Macduff is vicious.
greedy
Inferences: 0
Concepts: 1
Macbeth
angers
Macduff.
Macduff
kills
Macbeth.
Discoveries: 0
Explicit elements: 5
Macduff is
vicious.
Inferred elements: 0
Total elements: 5
Story reading time: 4.3 sec
Total time elapsed: 4.9 sec
Macduff
wants to kill
Macbeth.
Analysis
Results
Mental Models
Figure 6: Genesis notes early in the Macbeth story that Macduff has done a vicious act, which leads Genesis to use rules
associated with visciousness further along in understanding the story.
08:24:17 EDT 13-Apr-2014
Demonstrate
||| Views
Read About
Controls Start viewer
Predictions
Concept analysis
Experts
Answers
Elaboration graph Inspector
Sources
Results Summary Story
Speech
On a commonsense level
It looks like Dr. Jekyll thinks Russia attacks computer networks, probably because Russia wants to damage computer networks
and Someone attacks computer networks.
On a concept level
It looks like Dr. Jekyll thinksRussia attacks computer networks is part of acts of Revenge, Success, Answered prayer, Mistake
because harmed, and Misguided retaliation.
Results
Why did Russia attack Estonia's computer networks?
Figure 7: Genesis answers a question about the Russia-Estonia cyber war on several levels.
08:23:02 EDT 13-Apr-2014
Demonstrate
||| Views
Read About
Controls Start viewer
Personality analysis
Predictions
Experts
Elaboration graph Inspector
Concept analysis
Answers
Sources
Results Summary Story
Speech
From a personality perspective
It looks like Dr. Jekyll thinks Macduff kills Macbeth because he is vicious.
On a commonsense level
It looks like Dr. Jekyll thinks Macduff kills Macbeth, probably because Macduff wants to kill Macbeth and Macduff is vicious.
On a concept level
It looks like Dr. Jekyll thinksMacduff kills Macbeth is part of acts of Revenge, Answered prayer, Mistake because harmed,
Pyrrhic victory, and Tragic greed.
Results
Why did Macduff kill Macbeth?
Figure 8: Genesis answers a question about Macbeth on several levels including a personality-focused level.
Genesis calculates similarity using concepts
Genesis judges similarity in multiple ways. One way is by using word vectors; another is by using concept vectors.
Using concept vectors enables Genesis to see similarities not evident in the words. Two stories may involve, for
example, revenge, even though neither uses the word. The comparisons shown in figure 11 are on pairs of short
descriptions of conflicts.
The example appears in the MEng thesis of Cary Krakauer (2012).
Genesis models question-driven interpretation
After reading a story, a question may stimulate further analysis and expose new conclusions. The example here is
from an Eastern-Western story understanding experiment.
As shown in figure 12, a student murders a professor and another student. The Eastern reader has no opinion
on why Lu killed Shan until asked if it was because America is individualistic. Then, as shown in figure 13, the
Eastern reader, on being asked a question, recalls that he thinks so, which leads to adding that recalled belief to the
6
10:34:40 EDT 13-Apr-2014
Demonstrate
Read About
||| Views Controls Start viewe Experts Elaboration gra Inspecto Sources Results Summary Story
||| Views
Controls Start viewer
Experts
Elaboration graph Inspector
Sources
Results Summary
Story
Cyber war
Misguided retaliation
1
Rules: 33
Inferences: 6
Estonia builds
computer
networks.
Estonia believes
computer
networks are
valuable.
Estonia owns
computer
networks.
Estonia
relocates war
memorial.
Estonia
insults
Russia.
Estonia
harms
Russia.
Estonia
angers
Russia.
Russia
becomes
unhappy.
Concepts: 14
Discoveries: 0
Explicit elements: 9
Revenge
1
Inferred elements: 6
Total elements: 15
Story reading time: 0.5 sec
Total time elapsed: 2.2 sec
Mistake because harmed
1
Analysis
94%
Onsets
Elaboration graph
Figure 9: Genesis notes the onset of three possible concepts midstream in Estonia-Russia cyber war.
10:37:58 EDT 13-Apr-2014
Demonstrate
Read About
13:57:45 EDT 13-Oct-2013
||| Views Controls Start viewe Experts Elaboration gra Inspecto Sources Results Summary Story
Demonstrate
Read About
Misguided retaliation
||| Views
||| Views
Controls Start viewer
Experts
Elaboration graph Inspector
Controls Start viewer
Experts
Elaboration graph Sources
Results Story
Similarity panel Dictionary
Estonia builds
computer
networks.
Rules: 33
4
Results Summary
Story
Cyber war
1
Revenge
Sources
Estonia believes
computer
networks are
valuable.
Estonia owns
computer
networks.
Estonia
relocates war
memorial.
Estonia insults
Russia.
Estonia harms
Russia.
Estonia angers
Russia.
Estonia doesn't
respect Russia.
Russia wants to damage computer networks.
Russia attacks
computer
networks.
It looks like the Dr. Jeckl reader ofLu murder story/eastern, on reflection, believes
America is individualistic whichenables him to believe Lu kills shan because
America is individualistic
Inferences: 19
Mistake because harmed
4
Answered prayer
3
Mistake because unhappy
3
Russia wants
to harm
Estonia.
Estonia is
my friend.
Concepts: 14
Discoveries: 5
Someone attacks
computer
networks.
Russia wants to
attack computer
networks.
Russia
becomes
unhappy.
Explicit elements: 18
Inferred elements: 18
Total elements: 36
Someone
harms
Estonia.
Russia attacks
Estonia.
Russia angers
Estonia.
Russia
harms me.
Russia
becomes
happy.
Estonia
becomes
unhappy.
Russia harms
Estonia.
Estonia
creates center.
Estonia studies
computer security.
Story reading time: 130.6 sec
It looks like the Mr. Hyde reader ofLu murder story/western does not believe
America is individualistic and thereforecannot believe that Lu kills shan because
America is individualistic
Total time elapsed: 132.3 sec
Pyrrhic victory
6
Teaching a lesson
1
Russia harms
Estonia.
Analysis
Revenge
Success
Answered prayer
Mistake because har...
Misguided retaliation
100%
Onsets
Elaboration graph
Causal view
Figure 10: Genesis concludes that all three of the anticipated concepts eventually become realized.
||| Views
Controls Start viewer
Concept Pattern Matchers
Keyword Grid
Defined Grid
Defined Grid
Elaboration graph Sources
2
Generated Grid
StdDev error: 5.73
1
1: American revolution
2: Afghanistan-civil-war
3: American civil war
4: Nigerian civil war
5: Cambodia-vietnam invasion
6: China border war with india
7: China border war with ussr
8: Chad-libyan war
9: China invasion of tibet
10: Cuba bay of pigs invasion
11: Czechoslovakia-soviet invasion
12: Persian gulf war
13: China war with vietnam
14: Romania and ceausescu
15: Congo civil conflict
Results Story
Similarity panel Dictionary
Special
Generated Grid
StdDev error: 5.54
1
1: American revolution
2: Afghanistan-civil-war
3: American civil war
4: Nigerian civil war
5: Cambodia-vietnam invasion
6: China border war with india
7: China border war with ussr
8: Chad-libyan war
9: China invasion of tibet
10: Cuba bay of pigs invasion
11: Czechoslovakia-soviet invasion
12: Persian gulf war
13: China war with vietnam
14: Romania and ceausescu
15: Congo civil conflict
Keyword Grid
Experts
Concept grids
2
Genterated Grid - VectorMatch
3
4
Human Grid
5
Genterated Grid - VectorMatch
3
4
Human Grid
5
In-Order Grid
6
7
In-Order Grid
6
7
Generated In-Order Grid
8
9
10
11
12
13
14
15
10
11
12
13
14
15
Generated In-Order Grid
8
9
Similarity panel
Figure 11: Genesis performs concept-based similarity measurements. Concept-based measurements are shown above and
word-based similarity measurements below. White means most similar.
story, when enables connection to the murder. The Western reader has no such belief, so fails to follow the same
line of reasoning.
The example appears in the MEng thesis of Hiba Awad (2013).
Genesis aligns similar stories for analogical reasoning
Genesis aligns stories, in preparation for analogical reasoning, using the Needleman-Wunch algorithm borrowed
from molecular biology. In figure 14, Genesis aligns the Tet Offensive from the Vietnam war with the Arab Israeli
7
10:06:51 EDT 18-May-2014
Demonstrate
||| Views
Read Record About
Controls Start viewer
Experts
Elaboration graph Inspector
Sources
Results Summary Story
Lu murder story/eastern
Lu fails
dissertation
defense.
Rules: 35
Goertz is
lu's advisor.
Inferences: 52
Concepts: 15
Goertz fails to help lu.
Discoveries: 5
Lu feels
Goertz
dishonored. angers lu.
America is
corrupt.
Lu goes
to USA.
(rel do (ent
lu-76257) (ent
phd-76845))
Lu becomes
suicidal.
Lu doesn't
find job.
Lu becomes
lab assistant.
Lu becomes
suicidal.
Shan
graduates
with lu.
Shan is
successful
than lu.
Lu feels
frustrated.
Lu becomes
angry.
Lu murder story/western
Lu contests
faculty
decision.
Shan receives
national award.
Lu envies
shan.
Lu feels
victimized.
Lu isn't
American.
Lu doesn't receive national
award.
Lu receives
national
award.
Lu feels
honored.
Lu feels
victimized.
Lu becomes
suicidal.
Faculty rejects
appeal.
Lu feels
victimized.
Lu is
violent.
Lu becomes
angry.
Lu shoots
goertz.
Rules: 30
Lu feels
frustrated.
Lu becomes
suicidal.
Inferences: 35
Concepts: 17
Shan feels
honored.
Discoveries: 1
Lu is
Chinese.
Explicit elements: 41
Explicit elements: 38
Lu is
lonely.
Inferred elements: 26
Inferred elements: 25
Lu fails
dissertation
defense.
Lu feels
dishonored.
Goertz
angers lu.
Lu becomes
Lu goes to USA.
angry.
(rel do (ent
lu-76257) (ent
phd-76845))
Lu doesn't find job.
Lu becomes lab assistant.
Lu feels
frustrated.
Shan graduates with lu.
Shan is successful than lu.
Story reading time: 11.2 sec
Total elements: 63
Story reading time: 8.9 sec
America is
individualistic.
Total time elapsed: 12.5 sec
Total time elapsed: 10.2 sec
Goertz is a
person.
Lu contests
Shan receives
faculty decision.
national award.
Lu envies
shan.
Goertz is lu's
advisor.
Shan is younger
than lu.
Total elements: 67
Goertz fails to
help lu.
Lu doesn't receive national award.
Lu feels
victimized.
Lu feels
victimized.
Faculty rejects
appeal.
Lu feels
victimized.
Lu feels
frustrated.
Lu becomes
Lu feels
honored.
Lu receives
national award.
angry.
Lu shoots
goertz.
Lu kills
goertz.
Lu becomes
violent.
Lu harms
goertz.
Lu shoots
associate
professor.
Lu isn't
American.
Lu kills associate professor.
Lu is
violent.
Lu harms
associate
professor.
Lu shoots
shan.
Lu kills
shan.
Lu is
violent.
Lu harms
shan.
Lu shoots
him.
Lu kills
itself.
Lu is
violent.
Lu harms
itself.
Lu is
violent.
Shan feels
honored.
Lu is
Chinese.
Shan is younger than lu.
Lu is
insane.
Lu is
insane.
Associate
professor is a
person.
Lu is
insane.
Shan is a
student.
Lu is
American.
Lu is
insane.
Shan is a
person.
Lu is
insane.
Lu is a
student.
Lu is
insane.
Lu is a
person.
Lu kills
goertz.
Lu harms
goertz.
Lu shoots
associate
professor.
Lu kills
associate
professor.
Lu is
violent.
Lu harms
associate
professor.
Lu kills
shan.
Lu shoots
shan.
Lu is
violent.
Lu harms
shan.
Lu shoots
him.
Lu kills
itself.
Lu becomes
corrupt.
Lu becomes
murderous.
Lu inhabits
America.
Lu is
violent.
Lu harms
itself.
Lu becomes
murderous.
Lu becomes
murderous.
Lu becomes
murderous.
Lu becomes
murderous.
Lu owns
gun.
Lu becomes
murderous.
Lu becomes
murderous.
Lu becomes
murderous.
Analysis
Analysis
Suicide
Murderous influence
Murderous influence
Murderous influence
Murderous influence
Suicide
100%
100%
Elaboration graph
Figure 12: Genesis interprets the Shan murder. The basic interpretation does not connect the murder with America.
10:08:30 EDT 18-May-2014
Demonstrate
||| Views
Read Record About
Controls Start viewer
Experts
Elaboration graph Inspector
Sources
Results Summary Story
||| Views
Controls Start viewer
It looks like the Dr. Jekyll reader of Lu murder story/eastern, on
reflection, believes America is individualistic which enables him
to believe Lu kills shan because America is individualistic
Experts
Elaboration graph Inspector
America
America is
individualistic. is corrupt.
Shan is a
student.
It looks like the Mr. Hyde reader of Lu murder story/western does
not believe America is individualistic and therefore cannot believe
that Lu kills shan because America is individualistic
Lu inhabits
America.
Shan is a
person.
Causal view
Sources
Lu becomes
corrupt.
Results Summary Story
Lu becomes
murderous.
Lu kills
shan.
Lu becomes
angry.
Lu feels
honored.
Inspector
Did Lu kill Shan because America is individualistic.
Figure 13: Genesis, stimulated by a question, connects the murder with America’s supposed individualistic nature.
war. Such alignment helps see how precedents apply to current events.
13:09:29 EDT 30-Mar-2014
Demonstrate
||| Views
Read About
Controls
Story Alignment
Start viewer
Experts
Reflection Alignment
Story
Elaboration graph Inspector
Bindings
Match Tree
Element 0
Sources
Results
Summary
Story
Control Panel
Element 1
Element 2
Story B Score: 6.0
Israelis know that Egyptians
are preparing to attack them.
Egyptians are preparing to
attack Israelis.
Story A Score: 6.0
USA knows that Viet Cong is
preparing to attack it.
Viet Cong is preparing to attack USA defeats Viet Cong.
USA.
Element 3
Israelis defeat Egyptians.
Israelis know to defeat
Egyptians.
Element 4
Israelis know that Egyptians
know they defeat Egyptians.
USA knows to defeat Viet Cong. Gapfilled, USA knows Viet
Cong knows it defeats Viet
Cong.
Element 5
Element 6
Element 7
Element 8
Egyptians know that Israelis
defeat them.
Egyptians don't attack Israelis. Israelis believe that Egyptians Gapfilled, Egyptians attack
don't attack them.
Israelis.
Gapfilled, Viet Cong knows
USA defeats it.
Viet Cong doesn't attack USA.
USA believes Viet Cong doesn'tViet Cong attacks USA.
attack it.
Alignment Viewer
Figure 14: Genesis aligns elements in two wars enabling gaps on both sides to be filled.
The example appears in the MEng thesis of Matthew Fay (2012).
Genesis develops summaries
Because Genesis understands stories, Genesis can construct intelligent summaries, such as the one shown in figure 15 for Macbeth, which represents considerable compression relative to the version of the story provided.
14:52:28 EDT 05-Jun-2014
Demonstrations Read Record About
||| Views
Random
Controls Start viewer
Unabridged
Experts
Connected
Elaboration graph Inspector
Concept centered
Sources
Results Summary
Dominant concept centered
Retelling
Answered prayer
Unresolved questions
Table
The story is about Pyrrhic victory.
Lady macduff is Macduff's wife. Macbeth wants to become king because Lady Macbeth persuades that
Macbeth wants to become king. Macbeth murders Duncan, probably because Duncan is a king and Macbeth is
Duncan's successor. Macduff flees to England. Macbeth murders lady macduff. Macduff kills Macbeth,
probably because Macbeth angers Macduff.
Summary contains 13 of 81 elements in the story or 16.0%.
Summary
Figure 15: Genesis composes summaries.
Genesis tells and persuades using a reader model
Using a model of what a story reader knows, Genesis can tailor telling to cover gaps in the reader’s knowledge, by
simple spoon feeding, by more elaborate explanation, or by helpfully supplying principles.
8
In figure 16, Genesis supplies principles to a reader that knows very little in the beginning, but is taught that,
for example, you become king if the present king dies and you are his successor.
12:50:59 EDT 01-Apr-2014
Demonstrate
||| Views
Read About
Controls Start viewer
Story teller
Predictions
Experts
Elaboration graph Inspector
Sources
Results Summary
Story
Concept analysis
Start story titled "Macbeth/Insanity". Macbeth, Macduff, Lady Macbeth, Lady Macduff, Cawdor, and Duncan are characters. Macbeth, Macduff,
Lady Macbeth, Lady Macduff, Cawdor, and Duncan are persons. A king is a kind of noble. A thane is a kind of noble. England is a country.
Dunsinane is a castle and Burnham Wood is a forest. Lady Macbeth is Macbeth's wife.Macbeth is Lady Macbeth's husbandbecause Person
xx is person yy's husband whenever Person yy is person xx's wife.Lady Macduff is Macduff's wife. Macbeth is Lady Macbeth's husband.
Macduff is Lady Macduff's husband. Macbeth is a thane and Macduff is a thane. Lady Macbeth is evil and greedy. Duncan is the king, and
Macbeth is Duncan's successor. Duncan is an enemy of Cawdor. Macduff is an enemy of Cawdor. Duncan is Macduff's friend. Macbeth
defeated Cawdor. Duncan becomes happy because Macbeth defeated Cawdor. Macbeth talks with Witches who had visions. Duncan
rewarded Macbeth because Duncan became happy. Macbeth wants to become king because Lady Macbeth persuaded Macbeth to want to
become the king. Macbeth murders Duncan.Duncan becomes deadbecause Person yy becomes dead whenever Person xx kills person yy.
Macbeth becomes kingbecause Person ww becomes king whenever Person xx is a king, Person ww is person xx's successor, and Person xx
becomes dead.Lady Macbeth becomes queenbecause Person zz becomes queen whenever Person xx becomes king and Person zz is
person xx's wife.Macbeth becomes happybecause Person yy becomes happy whenever Person yy becomes king and Person yy wants to
become king. Macbeth harms Duncanbecause Person yy harms person ww whenever Person yy kills person ww.Macbeth harms Macduff
because Person yy harms person ww whenever Person yy harms person xx and Person xx is person ww's friend.Macduff becomes unhappy
because Person ww becomes unhappy whenever Person yy harms person ww.Macbeth angers Macduffbecause Person yy angers person
ww whenever Person yy harms person ww.Mabeth becomes king. Malcolm and Donalbain flee. Macbeth's murdering Duncan leads to
Macduff's fleeing to England. Macbeth murders Lady Macduff. Macbeth's murdering Duncan leads to Lady Macbeth's becoming distraught.
Lady Macbeth kills herself.Lady Macbeth kills herselfbecause Entity xx kills itself may be a consequence of Person xx becomes distraught.
Witches predicted that Burnam Wood would go to Dunsinane. Burnham Wood goes to Dunsinane. Macduff's army attacks Macbeth's castle.
Macduff kills Macbeth.
Story
Figure 16: Genesis uses a reader model to determine what and how much to say. Here, Genesis says a lot, because Genesis’s
model of the reader suggests that the reader does not know much.
Similarly, Genesis can tailor what is said to shape reader opinion. In figure 17, for example, some sentences
are emphasized, while others are deleted, so as to make the Woodcutter look good, and everyone else look bad, in
Genesis’s version of Hansel and Gretel.
The teaching and persuasion examples appear in the MEng thesis of Sila Sayan (2014).
Genesis operates on all of Minsky’s six levels
In The Emotion Machine (2006), Minsky describes six levels of thinking: instinctive reactions, learned reactions,
deliberative thinking, reflective thinking, self-reflective thinking, and self-conscious reflection.
Here are some correspondences between Minsky’s levels and Genesis competences:
• Inference rules, the basic rules that produce the basic elaboration graph, are much like instinctive reactions and
learned reactions.
• Explanation rules do a kind of deliberative thinking driven by a desire to find ways to produce a more connected
elaboration graph.
• Concept patterns examine the elaboration graph and thus perform a kind of reflective thinking.
• Mental models offer some of the capabilities found in Minsky’s discussion of self-reflective thinking and selfconscious reflection.
Evidently, Genesis operates on all of Minsky’s levels, although not yet performing all the functions described in
Minsky’s book.
Next steps
Turing concluded his Computing Machinery and Intelligence paper (1950) with: “We can only see a short distance
ahead, but we can see plenty there that needs to be done.” Still true.
Work underway
Genesis is under development by students at various levels, from class projects to PhD theses. The following are
representative systems under development:
• A system that composes original stories from precedents.
9
14:43:13 EDT 05-Jun-2014
Demonstrations Read Record About
||| Views
Version 1
Controls Start viewer
Version 2
Experts
Elaboration graph Inspector
Sources
Results Summary
Retelling
Version 3
A story about likable
This is as story that demonstrates that the_woodcutter is likable. Humans are a character. The witch is a character. The wife's baby is a character. The
woodcutter's first wife is a character. Gretel is a character. Hansel is a character. The wife is a character. The woodcutter is a character. Hansel and gretel is a
character. Humans are a person. The witch is a person. The wife's baby is a person. The woodcutter's first wife is a person. Gretel is a person. Hansel is a
person. The wife is a person. The woodcutter is a person. Hansel and gretel is a person. The woodcutter is the wife's husband. The woodcutter's first wife leaves
the woodcutter because The woodcutter is poor. The woodcutter becomes unhappy. Hansel and gretel is the woodcutter's child. The woodcutter is hansel and
gretel's parent. Hansel and gretel is the wife's stepchild. The wife is hansel and gretel's stepparent. Hansel is the woodcutter's child. Hansel is the wife's stepchild.
Gretel is the woodcutter's child. Gretel is the wife's stepchild. The woodcutter is hansel's parent. The woodcutter is gretel's parent. The wife is hansel's stepparent.
The wife is gretel's stepparent. The wife is the wife's baby's parent. The woodcutter is the wife's baby's parent. Koy is a place. The woodcutter lives in koy. The
wife lives in koy. Hansel lives in koy. Gretel lives in koy. The woodcutter is hungry. The wife is poor. The wife is hungry. The woodcutter works for long hours.
The woodcutter doesn't have enough food for whole family. The wife becomes pregnant. The wife needs enough food for the wife's baby. The woodcutter
wants to give enough food to hansel and gretel. The wife worries because The wife doesn't have enough food for the wife's baby. The wife becomes afraid
because The wife doesn't want to starve. The wife pressures the woodcutter to provide more food. The woodcutter becomes ashamed because The woodcutter
is a bad provider. The woodcutter becomes afraid because The woodcutter doesn't want the wife to leave it. The wife doesn't want to share more food because
The wife wants to give more food to the wife's baby. The wife persuades that the woodcutter abandons hansel and gretel in forest. Hansel learns about plan. In
order to survive, hansel makes plan. Hansel marks route back to koy. In order to lead hansel and gretel into forest, the woodcutter lies. The woodcutter wants
hansel and gretel to survive. The woodcutter helps hansel and gretel. Hansel remembers path back to koy. The woodcutter abandons hansel and gretel. Gretel
becomes afraid because The woodcutter abandons gretel. Hansel reassures gretel. Hansel and gretel returns to koy. The wife discovers hansel and gretel in
house. The woodcutter discovers hansel and gretel in house. The wife becomes shocked. The woodcutter becomes shocked. The woodcutter becomes
relieved because Hansel and gretel is safe. The wife becomes relieved because Hansel and gretel is safe. The wife becomes angry because The wife
shares more food with hansel and gretel. The wife doesn't want to harm hansel and gretel. The wife wants to ensure safety. The wife cries because The wife
doesn't know solution to problem. The woodcutter doesn't suggest solutions. The wife feels lonely because The woodcutter doesn't help the wife. The wife
reprimands the woodcutter because The wife becomes angry. The woodcutter doesn't want to harm hansel and gretel. The woodcutter doesn't want to disobey the
wife because The woodcutter is afraid. The woodcutter cries because The woodcutter doesn't know solution to problem. The wife wants to get rid of hansel and
gretel. The wife locks hansel and gretel in room. The wife starves hansel and gretel. The wife admits fault. The woodcutter becomes angry because The wife
mistreats hansel and gretel. The woodcutter wants to help hansel and gretel. The woodcutter frees hansel and gretel. The wooodcutter plans to leave
hansel and gretel in forest because The woodcutter believes that forest is safe. The woodcutter leads hansel and gretel to forest. The woodcutter tells truth to
hansel and gretel about plan. The woodcutter abandons hansel and gretel in forest. Hansel and gretel becomes angry with the woodcutter. There is appear in
forest. Hansel and gretel becomes afraid. Hansel and gretel becomes cold. Hansel cries. Gretel cries. Hansel helps gretel. Cottage is secluded because Humans
exile the witch. The witch has different appearance. The witch has different language. The witch doesn't want to harm humans. The witch wants to help
humans. The witch helps humans. Humans don't trust the witch because Humans are prejudiced. Humans attack the witch because Humans hate the witch.
Humans harm the witch. The witch becomes afraid. The witch becomes unhappy. The witch becomes confused. The witch escapes into forest. The witch wants
friends because The witch becomes lonely. In order to attract friends, the witch builds candy cottage. Humans found candy cottage. Humans steal from the
witch. The witch becomes angry. The witch becomes cannibal. In order to survive, the witch needs to eat humans. Hansel and gretel is starving. Hansel
and gretel finds cottage in forest. Hansel and gretel eats candy. The witch wants to eat hansel and gretel because The witch is hungry. The witch tricks hansel
and gretel. The witch traps hansel in cage. The witch traps gretel in cage. Hansel and gretel begs the witch for freedom. The witch doesn't trust hansel
and gretel because The witch doesn't trust humans. The witch believes that hansel and gretel is evil. The witch doesn't free hansel and gretel. The witch wants to
cook hansel and gretel in oven. Gretel wants to murder the witch because Gretel wants to survive. Gretel makes plan. Gretel escapes from cage. Gretel murders
the witch. Gretel burns the witch. The witch screams. Hansel and gretel escapes from cottage. Hansel and gretel finds the woodcutter in forest. The woodcutter
becomes happy because Hansel and gretel is alive. Hansel and gretel returns home. The woodcutter returns home. The wife becomes remorseful because The
wife harms hansel and gretel. The wife becomes happy because Hansel and gretel is alive.
Retelling
Make The_Woodcutter be likable.
Figure 17: Genesis uses a reader model to determine what and how much to say so as to shape the reader’s opinion. Here,
Genesis makes one character look good, and emphasizes that goodness, by making the other characters look bad.
• A system that mines literature for actions associated with personality traits.
• A system that tells stories with metaphorical reference to precedents.
• A system that uses story understanding apparatus to plan.
• A system that uses accumulated knowledge to disambiguate verbs.
The CBMM challenge
The central CBMM challenge problem is to understand pictures and video computationally, developmentally,
neurobiologically, and socially. Story understanding and telling play a role, of course, because pictures and videos
tell stories. One interesting step was taken by Virginia Chiu in an undergraduate research project in 2012. Her focus
was on how people describe people. She noted, as expected, that people prefer features that distinguish individuals
from other individuals in context, and she noted, as expected, that people prefer features that change slowly,
such as physical description, to features that change rapidly, such as location. In a pilot experiment involving 41
descriptions collected from four individuals, she found:
• 31 contained a clothing description, as in The man with sunglasses wearing a striped blue shirt.
• 27 contained a physical description, as in The Asian woman with her hair tied back.
• 16 contained a location description, as in The man on the right.
• 12 contained a manner/action description, as in The woman who walked past the door to the library.
Fortunately, from a story telling point of view, Genesis uses Boris Katz’s START (1997) to generate English, and
START can generate richly descriptive sentences, including sentences with subordinate clauses.
10
Contributions
What benefits will follow from successful work on story understanding? At least these:
• For CBMM in particular, we will handle stories told in pictures and video.
• For science in general, we will have a better understanding of the key differentiator of our intelligence.
• For applications, our progress on the science side will surely constitute steps toward applications on higher level
than we can hope for with today’s technology.
11
References
Hiba Awad. Culturally based story understanding. Master’s thesis, Electrical Engineering and Computer Science
Department, MIT, Cambridge, MA, 2013.
Matthew Paul Fay. Enabling imagination through story alignment. Master’s thesis, Electrical Engineering and
Computer Science Department, MIT, Cambridge, MA, 2012.
Boris Katz. Annotating the World Wide Web using natural language. In Proceedings of the 5th RIAO Conference
on Computer Assisted Information Searching on the Internet, pages 136–159, 1997.
Caryn Krakauer. Story retrieval and comparison using concept patterns. Master’s thesis, Electrical Engineering
and Computer Science Department, MIT, Cambridge, MA, 2012.
Marvin Minsky. Steps toward artificial intelligence. In E. A. Feigenbaum and J. Feldman, editors, Computers and
Thought. MIT Press, Cambridge, MA, 1961.
Marvin Minsky. The Emotion Machine. Simon and Schuster, New York, NY, 2006.
David Nackoul. Text to text: Plot unit searches generated from English. Master’s thesis, Electrical Engineering
and Computer Science Department, MIT, Cambridge, MA, 2010.
Sila Sayan. Audience aware computational discourse generation for instruction and persuasion. Master’s thesis,
Electrical Engineering and Computer Science Department, MIT, Cambridge, MA, 2014.
Susan S. Song. Of intent and action: Implementing personality traits for storytelling through concept patterns.
Master’s thesis, Electrical Engineering and Computer Science Department, MIT, Cambridge, MA, 2012.
Alan M. Turing. Computing machinery and intelligence. Mind, 59(236):433–460, 1950.
Patrick Henry Winston. The strong story hypothesis and the directed perception hypothesis. In Pat Langley, editor,
Technical Report FS-11-01, Papers from the AAAI Fall Symposium, pages 345–352, Menlo Park, CA, 2011.
AAAI Press.
Patrick Henry Winston. The next 50 years: a personal view. Biologically Inspired Cognitive Architectures, 1, 2012.
Patrick Henry Winston. The right way. Advances in Cognitive Systems, 1:23–36, 2012.
Wolfgang Victor Hayden Yarlott. Old man coyote stories: Cross-cultural story understanding in the genesis story
understanding system. Master’s thesis, Electrical Engineering and Computer Science Department, MIT, Cambridge, MA, 2014.
12