Natural Language Agents

1
Natural Language Agents
Elaine Rich
2
What do they Need?
The linguistic facts A KR system that is rich
enough to encode everything we can talk
about Understanding Figuring out what the
speaker meant and what you should do about
it Generation Figuring out what to say to
achieve your goals
3
Turings Prediction
1950 Turing predicted that in about fifty years
"an average interrogator will not have more than
a 70 percent chance of making the right
identification after five minutes of
questioning".
4
Was Turing Right?
gtWhat's the best place to eat Chinese food?
ALICE My favorite places are California and
Maine. Holland is cool too. gtWhat do you like
about Maine? ALICE The special effects are the
best.
5
Another Application - MT
Austin Police are trying to find the person
responsible for robbing a bank in Downtown
Austin. El policía de Austin está intentando
encontrar a la persona responsable de robar un
banco en Austin céntrica. The police of Austin
is trying to find the responsible person to rob a
bank in centric Austin.
6
MT - The Limits
A Florida teen charged with hiring an undercover
policeman to shoot and kill his mother instructed
the purported hitman not to damage the family
television during the attack, police said on
Thursday. Un adolescente de la Florida cargado
con emplear a un policía de la cubierta interior
para tirar y para matar a su madre mandó a hitman
pretendida para no dañar la televisión de la
familia durante el ataque, limpia dicho el
jueves. An adolescent of Florida loaded with
using a police of the inner cover to throw and to
kill his mother commanded to hitman tried not to
damage the television of the family during the
attack, clean said Thursday.
7
MT - The Limits
http//www.shtick.org/Translation/translation47.ht
m
8
Going Both Ways

• Notice that both of these applications require
  that we process language in two directions
• Understanding
• Generation
• But also notice that it is possible to do a
  somewhat passable job without going through any
  meaning representation.

9
When Meaning is Critical
English Put the kids cereal on the bottom
shelves.
10
Java
import java.util.ArrayList public class
GroceryStore private int shelves
private ArrayList products public void
placeProducts(String productFile) FileReader
r new FileReader(productFile)
GroceryItemFactory factory new
GroceryItemFactory()
while(r.hasNext()) products.add(
factory.createItem(r.readNext()))
ThreeDLoc startLoc GroceryItem temp
for(itemNum 0 itemNum lt products.size()
itemNum) temp (GroceryItem)(products.get
(itemNum)) startLoc temp.getPlacement(this
) shelvesstartLoc.getX()startLoc.getY()
startLoc.getY() tempgetIDNum()

11
Java, Continued
public class ChildrensCereal extends
GroceryItem private static final int
PREFERRED_X -1 private static final int
PREFERRED_Y 0 private static final int
PREFERRED_Z 0 public ThreeDLoc
getPlacement(GroceryStore store)
ThreeDLoc result new ThreeDLoc()
result.setX(store.find(this))
result.setY(PREFERRED_Y)
result.setZ(PREFERRED_Z) return result

12
Its All about Mapping
13
What Are We Going to Map to?
English Do you know how much it rains in Austin?
The database
RainfallByStation
year
month
station
rainfall
Stations
station
City
Months
Month
Days
14
English What is the average rainfall, in Austin,
in months with 30 days?
SQL SELECT Avg(RainfallByStation.rainfall) AS
AvgOfrainfall FROM Stations INNER JOIN
(Months INNER JOIN RainfallByStation ON
Months.Month RainfallByStation.month) ON
Stations.station RainfallByStation.station HA
VING (((Stations.City)"Austin") AND
((Months.Days)30))
15
Designing a Mapping Function for NL Understanding

• Morphological Analysis and POS tagging
• The womans goed home.
• Syntactic Analysis (Parsing)
• Fishing went boys older
• Extracting Meaning
• Colorless green ideas sleep furiously.
• Sue cooked. The potatoes cooked.
• Sue and the potatoes cooked.
• Putting it All in Context
• My cat saw a bird out the window. It batted at
  it.
• What isnt Said
• Winnie doesnt like August.
• He doesnt like melted ice cream.

16
Ambiguity the Core Problem

• Time flies like an arrow.
• I hit the boy with the blue shirt (a bat).
• I saw the Grand Canyon (a Boeing 747)
• flying to New York.
• I know more beautiful women than Kylie.
• The boys may not come.
• I only want potatoes or rice and beans.
• Is there water in the fridge?
• Who cares?
• Have you finished writing your paper?
• Ive written the outline.

17
Morphological Analysis and POS Tagging
Morphological Analysis played play ed
play (V) PAST saw see (V)
PAST leaves
18
Morphological Analysis and POS Tagging
Morphological Analysis played play ed
play (V) PAST saw see (V) PAST leaves
leaf (N) PL leave (N) PL leave (V)
3rdS compute
19
Morphological Analysis and POS Tagging
Morphological Analysis played play ed
play (V) PAST saw see (V) PAST leaves
leaf (N) PL leave (N) PL leave (V)
3rdS compute computer
computerize computerization POS Tagging
I hit the bag.
20
Morphological Analysis Using a Finite State
Transducer
21
Stochastic POS Tagging
Naïve Bayes Classification Choose the POS tag
that is most likely for the current word given
its context. For example Secretariat expected
to race tomorrow.
Using Bayes Rule
We want to choose the tag tj with maximum
likelihood
22
The Importance of Parsing Even When Were Not
Doing Full Understanding
Find me all the Lawyers whose clients committed
fraud vs Lawyers who committed
fraud vs Clients whose lawyers committed fraud
23
Parsing - Building a Tree
S NP
VP N V NP
John hit DET N

the ball
John hit the ball.
(S (NP (N John)) (VP (V hit) (NP
(DET the)
(N ball))))
24
Grammar Rules
We can build such a parse tree using a grammar
with rules such as S ? NP VP NP ? N VP ? V NP
25
The Lexicon is Important
The cat with a furry tail purred a collar.
Mary imagined a cat with a furry tail. Mary
decided to go. Mary decided a cat with a furry
tail. Mary decided a cat with a furry tail
would be her next pet. Mary gave Lucy the
food. Mary decided Lucy the food. Mary asked
the cat. Mary demanded a raise. Mary asked
for a raise.
26
Parsing Dealing with Ambiguity
English
Water the flowers with the hose.
Water the flowers with brown leaves.
27
Using Domain Knowledge
(plant (isa living thing)) (flower (isa plant)
(has parts leaf)) (water (isa action)
(instrument mustbe container)) (hose
(isa container))
28
A Harder One
John saw a boy and a girl with a red wagon with
one blue and one white wheel dragging on the
ground under a tree with huge branches.
29
How Bad is the Ambiguity?

• Kim (1)
• Kim and Sue (1)
• Kim and Sue or Lee (2)
• Kim and Sue or Lee and Ann (5)
• Kim and Sue or Lee and Ann or Jon (14)
• Kim and Sue or Lee and Ann or Jon and Joe (42)
• Kim and Sue or Lee and Ann or Jon and Joe or Zak
  (132)
• Kim and Sue or Lee and Ann or Jon and Joe or Zak
  and Mel (469)
• Kim and Sue or Lee and Ann or Jon and Joe or Zak
  and Mel or Guy (1430)
• Kim and Sue or Lee and Ann or Jon and Joe or Zak
  and Mel or Guy and Jan (4862)
• The number of parses for an expression with n
  terms is the nth Catalan number

30
Parsing Gapping
English Who did you say Mary gave the ball to?
Sentences like this make specifying the grammar
difficult. They also make it hard to use a
simple, context-free parser.
31
Semantics The Meaning of Words
Getting it right for the target
application month ? RainfallByStation.month Dea
ling with ambiguity spring ? or
or stamp ?
or
32
Semantics The Meaning of Phrases
Semantics is (mostly) compositional.
Olive oil
(oil (made-from olives))
33
Occasionally It Isnt
Olive oil
34
But Usually It Is
Peanut oil
(oil (made-from peanuts))
35
Another One
Coconut oil
(oil (made-from coconut))
36
But What About This One?
Baby oil
37
But What About This One?
Baby oil
(oil (used-on baby))
38
And Another One
Cooking oil
(oil (used-for cooking))
39
And Another One
Riding jacket Leather jacket Letter
jacket Rain jacket
40
Idioms Dont Work This Way

• Im going to give her a piece of my mind.
• He bent over backwards to make the sale.
• Im going to brush up on my Spanish.

41
Putting Phrases Together
Bill cooked the potatoes. The potatoes cooked in
about an hour. The heat from the fire cooked the
potatoes in 30 minutes.
(cooking-event (agent )
(object
) (instrument
) (time-frame
) Bill and the potatoes cooked.
42
Language at its Most Straightforward
Propositional Content

• Bill Clinton was the 42nd president of the United
  States.
• Texas is in France.
• The Matrix is playing at the Dobie.
• Lunch is at noon.
• What time is it?

43
When Theres More - Presuppositions

• What is Clinton famous for?
• Wheres The Matrix playing?
• Who is the king of France?
• Have you started making it to your morning
  classes?
• Im going to check out all the five star
  restaurants in Cleveland on this trip.

44
Coherence
Winnie doesnt like melted ice cream. He always
dreads August. Winnie doesnt like melted ice
cream. He always dreads January. Winnie wanted
to go to the store. He went to find Christopher
Robin. Winnie wanted to go to the store. He
counted quickly to 10. Winnie walked into the
room. Christopher Robin looked up and smiled.
Winnie walked into the room. The earth rotates
around the sun.
45
We Cant Say it All
Christopher Robin and Winnie decided to go out
for lunch. They remembered that Cojis doesnt
have hot dogs on Saturdays, so they went to
Buzzys. They got their food, slathered on the
mustard, and walked home.
46
Conversational Postulates

• Grices maxims
• The Maxim of Quantity
• Be as informative as required.
• Dont be more so.
• The Maxim of Quality
• Do not say what you believe to be false.
• Do not say that for which you lack sufficient
  evidence.
• Maxim of relevance Be relevant
• Maxim of manner
• Avoid obscurity of expression
• Avoid ambiguity
• Be brief.
• Be orderly.

47
Conversational Postulates and Scalar Implicature

• A Have you done the first math assignment yet?
• B Im going to go buy the book tomorrow.

48
Another Example of Scalar Implicature

• A When did you get home last night?
• B I was in bed by midnight.

49
When Theres More Conversational Postulates and
Inference

• A Joe doesn't seem to have a girl-friend these
  days.
• B He's been going to Dallas a lot lately.

50
When Theres More Conversational Postulates and
Inference
A Lets go to the movies tonight. B I have to
study for an exam.
51
When Theres More Conversational Postulates and
Inference
Reviewer of new book It is well-bound and
free of typographical errors.
52
When Theres More Conversational Postulates and
Inference
A What do you think of my new dress? B Its
interesting.
53
When Theres More Conversational Postulates and
Illocutionary Force

• Do you know what time it is?

54
When Theres More Conversational Postulates and
Illocutionary Force

• Do you know what time it is?
• What time is it?

55
When Theres More Conversational Postulates and
Illocutionary Force

• Do you know what time it is?
• What time is it?
• Im freezing.

56
When Theres More Conversational Postulates and
Illocutionary Force

• Do you know what time it is?
• What time is it?
• Im freezing.
• Get up and go close the window.

57
When Theres More Conversational Postulates and
Illocutionary Force

• Do you know what time it is?
• What time is it?
• Im freezing.
• Get up and go close the window.
• Politeness

58
What About Applications Where Almost is OK?

• Searching the web
• Leaving some of the work for people
• Retrieval failures are ok
• www.google.com
• Snooping

59
Going the Other Way Generation
(c (isa cooking-event) (agent x )
(object y) (instrument z)
(time-frame )) (x (isa man)
(name Bill) (height 6')
(attire (head- covering h))
(born-location b))
(y (some-of potatoes) (type-of
Idaho)) (maturity new)) (z (isa
microwave) (brand Sharp)) (h (isa
gimme) (color red)) (gimme (subclass
hat)) (b (isa city) (name Austin))
60
One Problem - What is Reusable?

• Because were dealing with a mapping problem, we
  cant build a definitive, useful for all
  applications, NL interface. However, we can
  build
• Lexicons that contain morphological and POS
  information, as well as meanings given in terms
  of standard KBs such as Wordnet.
• Morphological analyzers
• Syntactic parsers that appeal to a statistical
  and/or semantic filter through a common interface
• Inference engines
• Dialogue management systems that handle
  linguistic-level issues and plug into
  domain-specific knowledge

61
Spoken Language - Understanding
62
Spoken Language - Generation

• The issues
• Figuring out what to say (same as for written
  language)
• Pronouncing words
• Linking them together
• Getting the prosody right

63
A Recent Loebner Prize Winner
gt Why do you think people want to go to the
moon? Jabberwacky You don't. Plastic and metal,
perhaps. No flesh. gt Can you imagine life before
plastic? Japperwacky Can you? Sure. Milk came
in glass bottles. Jabberwacy You can come here
whenever you want. Iwill welcome you.