CS544: Lecture 5: Reference and Other Problems - PowerPoint PPT Presentation

1 / 39
About This Presentation
Title:

CS544: Lecture 5: Reference and Other Problems

Description:

Clause-Internal Coherence Discourse Coherence One Variety of Inference: Abduction Example The Example Interpreted Is There Systematicity? ... – PowerPoint PPT presentation

Number of Views:53
Avg rating:3.0/5.0
Slides: 40
Provided by: JerryR96
Learn more at: https://www.isi.edu
Category:

less

Transcript and Presenter's Notes

Title: CS544: Lecture 5: Reference and Other Problems


1
CS544 Lecture 5Reference and Other Problems
February 18, 2010
  • Jerry R. Hobbs
  • USC/ISI
  • Marina del Rey, CA

2
Logical Form
The x in Pat(x) and ask(e1,x,y,e2) are the
same.
x
The y and e2 in leave(e2,y) and ask(e1,x,y,e2)
are the same.
e2, y
The y in Chris(y) and ask(e1,x,y,e2) are the
same.
e2
y
The e2 in leave(e2,y) and early(e2) are the
same.
Pat asked Chris to leave early.
Pat(x) Past(e1) ask(e1,x,y,e2) Chris(y)
leave(e2,y) early(e2)
Now what?
3
Is There Systematicity?
The basic unit of information is the
predication
p(x,y)
What is p? predicate strengthening
What are x and y? coreference
Whats the relation between p and x, p and y? In
what way is it appropriate for p to describe x?
y? metonymy, metaphor, ...
p(x,y) q(y,z)
Whats the relation between these two
predications? intraclausal coherence, discourse
coherence (predicate strengthening on sentence
adjacency)
4
What is the Predicate?
Interpreting compound nominals pension fund
gt pension(y) nn(y,x) fund(x) fire
fight, prairie storms, Saturnian system
Interpreting possessives the nations
biggest pension fund, Afghanistans Uruzgan
Valley Interpreting of the cracks of my
car, a handful of images, the practice of
parsing Interpreting other prepositions
stricter rules on investment-rating groups,
regularity of chunks over different
sentences Interpreting other underspecified
predicates they had no agenda, everyone had
a cautionary tale Lexical disambiguation
as bright as snow vs. as bright as Einstein Text
gives us general predicates that we understand
specifically.
5
What is the Argument?Coreference
Pronouns CalPERS efforts this year to
boost its financial performance John can
open Bills safe. He knows the
combination. Definite noun phrases
Anaphoric I bought a new car, but the brakes
sometimes dont work.
Determinative the top of the table
Generic The USC CS student is truly
exceptional. Implicit arguments other
state pension funds other than what? Syntactic
ambiguity engulfed in a fire fight with the
Taliban engulfed with the Taliban, or
fight with the Taliban with(x,Taliban)
x engulfed or x fight?
6
Why this Predicate with this Argument?
p(x) interpreted as q(x) where p(x) --gt q(x)
Finding relevant aspect of predicate the
city turned monochrome what part of a
city can be monochrome? Metaphor
interpretation a handful of images
what aspect of hands is relevant
here? Metonymy interpretation The pension
fund, which has lost a quarter of its value, is
planning ... fund as amount of money
vs. fund as organization
p(x) interpreted as p(f(x))
7
Clause-Internal Coherence
Relations that go beyond the predicate-argument
relations conveyed by syntactic
structure The nations biggest public pension
fund, which has lost more than a quarter of its
value in the last seven months, is planning to
rally big investors nationwide to demand changes
in the way Wall Street operates. losing
is a cause of planning A jogger was hit by a car
last night. vs. A professor was hit by a
car last night. jogging played a causal
role in the accident
8
Discourse Coherence
Relations between successive segments of
discourse are typically varieties of
rephrasing/elaboration John can open
Bills safe. He knows the combination.
similarity and contrast, generalization and
examplification John went to Paris.
Bill flew to London. Mary is graceful.
John is an elephant. successive changes of
state, occasion Pat drove to the
florists. He bought a dozen roses.
causality, enablement, violated causality or
implication There has been
considerable work on grammar induction.
Grammar induction techniques are well understood.
9
One Variety of InferenceAbduction
1. Represent the content as predications (the
logical form). 2. Prove them, using
the axioms in the knowledge base. 3.
Allow assumptions in the proof, at a cost. 4.
Pick the lowest cost proof.
Speaker
Hearer
MB
Utt
Uniform framework for syntax, semantics, and
pragmatics
10
Example
The Boston office called. Local
Pragmatics Problems illustrated 1. Definite
Reference What does the Boston office
refer to? 2. Interpreting compound nominals
What is the implicit relation between
Boston and office? 3. Metonymy Coerce from
the Boston office to someone at the
Boston office.
11
The Example Interpreted
The Boston office called. LF
call'(e,x) person(x) rel(x,y)
office(y) Boston(z)

nn(z,y) KB person(J)
work-for(J,O), office(O)
work-for(x,y) --gt rel(x,y) in(O,B),
Boston(B) in(y,z) --gt nn(z,y)
New Information
Definite Reference
Metonymy
Compound Nominal
Local Pragmatics problems solved as a
by-product
Syntax Parse Tree Interpretation
Proof Graph
12
Is There Systematicity?
The basic unit of information is the
predication
p(x,y)
What is p? predicate strengthening
What are x and y? coreference
Whats the relation between p and x, p and y? In
what way is it appropriate for p to describe x?
y? metonymy, metaphor, ...
p(x,y) q(y,z)
Whats the relation between these two
predications? intraclausal coherence, discourse
coherence (predicate strengthening on sentence
adjacency)
13
Reference and Coreference
Language ......... x .................
y .............
World
A
x refers to A y refers to A x and y corefer
y is coreferential with x The more general
expressions (pronouns, definite NPs) are
called anaphoric expressions, or anaphora
Varieties of coreference Pronouns
Definite NPs Other anaphora, e.g. other
anaphora Implicit arguments Many
syntactic/attachment ambiguities
14
Coreference
Coreference should not be thought of as a
relation among words and phrases A
man in his own house is happy. A man in (a
man in his own house)s own house is happy.
A man in (a man in (a man in his own house)s own
house)s own house is happy. Rather it is an
identity relation among variables ...
man(x1) in(x1,h1) he(x2) Poss(x2,h1)
house(h1) ... ? x1 x2
15
Third Person Pronouns
CalPERS, an acknowledged pioneer in pushing
companies it invests in to improve their
internal governance, is ready to take the tactic
to a new level. In May 2006 a unit of American
soldiers in Afghanistans Uruzgan Valley were
engulfed in a ferocious fire fight with the
Taliban. Only after six hours, and supporting
air strikes, could they extricate themselves from
the valley. Attendance at evening meetings
became more sporadic people called at the last
minute to say they had the flu or their car
wouldnt start. When the Voyager 2 spacecraft
sped through the Saturnian system more than a
quarter of a century ago, it came within 90,000
kilometers of the moon Enceladus. There has been
considerable work on grammar induction, because
it is exploring the empiricist question of how
to learn structure from unannotated textual
input, but we will not cover it here.
16
An Algorithm for Pronoun Resolution
S
  • From pronoun
  • 1. Skip reflexive level
  • 2. Go up to next NP or S
  • 3. Breadth-first search for
  • candidate NPs
  • 4. Rule out if selectional,
  • number or gender conflict
  • 5. Pick the first candidate

NP
VP
The network system
NP
PP
divides
into
NP
data
small blocks
SBAR
VP
called
NP
which
S
packets
NP
VP
80-90 accuracy
sends
it
The network system divides data into small blocks
called packets, which it sends individually.
17
If We Understood the Text ...
Pronouns are used because the context and the
rest of the text makes a more descriptive NP
unnecessary. If we understood the context and
the rest of the text, pronoun resolution
would simply fall out.
the Voyager 2 spacecraft sped through the
Saturnian system it came within 90,000
kilometers of the moon Enceladus
He hadnt planned to toss her here. He
had hoped to do it earlier in the voyage,
between Nassau and San Juan.
CONTRAST
CONTRAST
18
First and Second Person Pronouns
I, me, my .... I ...., Person Verbsay
... OR the speaker/writer I would
momentarily forget where I was we, us, our
.... we ...., Verbsay Person of Org
OR the reader and/or writer We will not
cover it here OR the relevent everyone
We had no idea what we had missed you, your
... you ..., Person said. Person(s)
being addressed in a quote / some nearby Person
not coreferential with speaker
OR the reader/listener OR anyone /
impersonal
19
the and a
Conventional notation A car arrives. gt
(E x)car(x) arrive(x) The car arrives.
gt arrive( ? x car(x))
iota operator the x such that car(x)
But the and a convey information the
the entity referred to by the NP is mutually
identifiable in context via the
property conveyed by the rest of the NP.
The car is in the driveway. Known
entity a the entity referred to by the
NP is not mutually identifiable in context via
the property conveyed by the rest of
the NP. A car is in the driveway.
New entity Arnold Schwarzenegger
is a short man. New
property My approach the man gt the(x,e)
man(e,x) a man gt
a(x,e) man(e,x)
Highly idiosyncratic
20
Definite NPs
Heuristic Person resolves to last Person, etc.
Several cases Refers to something explicit in
previous text I saw Bill Russell on a
plane. The man is very tall. I bought a
Prius. The cars failures worry me. Refers to
something implied by something explicit in
previous text The city was all quiet. The
streets were covered in snow. ...
shaking my car across the lane dividers

Anaphoric
No good heuristics there are efforts to learn
common associations, e.g., part-of relations
21
Definite NPs
Definite description is self-contained
(determinative definite NP), because It refers
to something unique in the world the
world It refers to something uniquely
associated with a syntactically related entity
the way Wall Street operates, the
top of a table the student who scored the
best on the test Superlatives the most
momentous thing ... Refers to something unique
in the context the city turned
monochrome Generic refers to the
representative element of the set of all things
of that description the dollar
fell yesterday dollars
Heuristic If there is a superlative or right
modifier
Bad heuristic if there is no antecedent in the
previous text (determinatives far more frequent)
22
Resolving Definite NPs with Inference
Prove the existence of
... a car ...
... the car ... ... Prius ...

... the car ... ... acity ...
... the
streets ...
Prius(x) --gt car(x)
city(x) --gt (E s,y) street(y) in(y,x)
Plural(y,s)
To resolve a definite NP reference, find the most
economical proof of the existence of an
entity of that description. Problem Requires
very large knowledge base.
23
Demonstratives and Deictics
Demonstratives (this, that, these, those) It is
not well understood how these function,
other than being definites. Attendance at
meetings became more sporadic. Those who did
come looked damp and resentful.
Enceladus is very strange. Something happened
to this body in the past. What
regularities are there in allowable expressions?
This is the problem of grammar
induction. Deictics (relative to some anchor in
the world) .... a report showed Friday
a quarter of a century ago ....
the last seven months
of what week?
relative to when?
24
Implicit Arguments
Often the underlying predicate has more arguments
than the text provides how do we resolve
the implicit arguments, and when do we need to?
of what?
tougher regulation by federal agencies.
by whom and against whom?
suppporting air strikes
than what?
The work was tougher in such weather
in what and by whom?
The interest generated by Voyagers visit made a
comprehensive examination of Enceladus a
cardinal goal of the Cassini mission to Saturn.
The practice of parsing can be considered ....
parsing what?
25
Syntactic Ambiguity
A unit of American soldiers were engulfed in a
fight with the Taliban. unit(u1) of(u1,s1)
American(y1) soldier(y1) Plural(y1,s1) engulf
(e1,z1,y1) in(e1,f1) fight(f1,y2,t2)
with(x,t1) Taliban(t1) x f1 v x
e1 Axioms The third argument of the predicate
fight is realized with with
fight(f,y,t) --gt with(f,t) If y accompanies t in
event e, then e is with t accompany(y,t,e)
arg(y,e) --gt with(e,t)
Constrained coreference problem
26
Is There Systematicity?
The basic unit of information is the
predication
p(x,y)
What is p? predicate strengthening
What are x and y? coreference
Whats the relation between p and x, p and y? In
what way is it appropriate for p to describe x?
y? metonymy, metaphor, ...
p(x,y) q(y,z)
Whats the relation between these two
predications? intraclausal coherence, discourse
coherence (predicate strengthening on sentence
adjacency)
27
Pragmatic Strengthening of Vague Predicates
Some words/predicates convey little information
on their own, but we understand them much
more specifically.
Compound nominals pension fund fund that
provides pensions air strike strike
originating from the air prairie storms
storms located on a prairie Voyager 2
spacecraft space craft named Voyager 2
lobster salad salad containing meat of
lobster grammar induction induction
inducing a grammar
In general, the relation between the two nouns
can be anything. Heuristic Predicate-argument
if selectionally possible. Otherwise, one of
the dozen most common (part-of, in, made-of,
etc.) determined by semantic type of
the two nouns
28
Resolving Compound Nominalswith Inference
Prove the nn relation between the two nouns in
the most economical way.
pension fund fund(y1) nn(x1,y1)
pension(x1)
x1x2
fund(y1) --gt provide(y1,x2) payment(x2)
payment(x2) for(x2,e3) retire(e3,z) --gt
pension(x2)
29
Other Vague Predicates
Possessive CalPERS efforts efforts by
CalPERS Afghanistans Uruzgan Valley
Uruzgan Valley that is part of Afghanistan of
prepositional phrase mounds of fine white
powder mounds consisting of fine white powder
extensive plains of smooth terrain plains
that are smooth terrain a straightforward
implementation of the idea
predicate-argument relation implement(x,
idea) have They had no dreams of global
jihad predicate-argument dream(x,jihad)
i.e., to have a dream is to dream
Everyone had a cautionary tale
predicate-argument tell(x,tale)


30
Lexical Ambiguity
The plane taxied to the terminal.
LF
plane(x) taxi(x,y) terminal(y)
KB
airplane(x) --gt plane(x)
move-on-ground(x,y) airplane(x) --gt taxi(x,y)
Specializations of the vague predicate plane
airport-terminal(y) --gt terminal(y)
airport(z) --gt airplane(x) airport-terminal(y)
wood-smoother(x) --gt plane(x)
ride-in-cab(x,y) person(x) --gt taxi(x,y)
computer-terminal(y) --gt terminal(y)
31
Lexical Ambiguity
The plane taxied to the terminal.
LF
plane(x) taxi(x,y) terminal(y)
KB
airplane(x) --gt plane(x)
move-on-ground(x,y) airplane(x) --gt taxi(x,y)
airport-terminal(y) --gt terminal(y)
airport(z) --gt airplane(x) airport-terminal(y)
wood-smoother(x) --gt plane(x)
ride-in-cab(x,y) person(x) --gt taxi(x,y)
computer-terminal(y) --gt terminal(y)
32
Lexical Ambiguity
John wanted a loan. He went to
the bank. LF . . . loan(l) . . .
. . . bank(y) . . . KB loan(x)
--gt financial-institution(y)
issue(y,x) financial-institution
(y) etc4(y) --gt bank1(y)

bank1(y) --gt bank(y) river(z) --gt bank2(y)
borders(y,z) bank2(y) --gt bank(y)
33
Is There Systematicity?
The basic unit of information is the
predication
p(x,y)
What is p? predicate strengthening
What are x and y? coreference
Whats the relation between p and x, p and y? In
what way is it appropriate for p to describe x?
y? metonymy, metaphor, ...
p(x,y) q(y,z)
Whats the relation between these two
predications? intraclausal coherence, discourse
coherence (predicate strengthening on sentence
adjacency)
34
Are the Predicate and ArgumentCongruent?
p(x)
The predicate really means something else, e.g.,
metaphor
The argument really refers to something
else metonymy
I like to read Shakespeare gt I like to read
the plays written by Shakespeare This
restaurant takes American Express gt This
restaurant takes credit cards issued by
American Express
John is an elephant gt John is big / clumsy /
has a good memory / ...
What about -- America believes in democracy.
35
Metonymy
Metonymy referring to something by referring to
something related to it. We have to coerce
the apparent referent into the actual referent
via some coercion function.
Common coercions Entity into part of entity
... researchers excavating a cave
... Organization into person The White
House said in its report that .... Container
into contained She had consumed three
glasses.
36
In a World Without Metonymy
37
Resolving Metonymy
For a particular domain, you can have a graph of
the principal types of entities, where the
links between nodes are the possible relations
between them. To resolve metonymy, find the
shortest path from the node of the apparent
referent to a node matching the required type.
Country
Organization
See Katja Markert and Udo Hahn, Artificial
Intelligence Journal, 2003
isa
member-of
rules
Government
Person
e.g., France criticized American policy in Iraq.
More generally, prove there is a relation between
the apparent referent and something satisfying
the requirements, in the most economical way.
coercion relation
read Shakespeare
wrote plays
text
38
Metaphor
Metaphor a predicate appropriate in one domain
is used in another abstract properties of
that predicate are intended to be conveyed
sometimes large scale frameworks are enlisted
(Lakoff Johnson)
Holding/Having is Perceiving returned a
handful of images Influence as Physical
Force CalPERS pushed companies to improve
their governance. tougher regulation by
federal agencies Knowledge as Visibility/Seeing
greater openness in the way companies are
run delve into some controversial investments
39
Metaphor
John is an elephant gt John is heavy A
metaphor explicitly conveys one thing, but is
intended to convey something implied by
what is explicit. elephant(e1,x) --gt
heavy(e2,x) imply(e1,e2) Make the
implication relation explicit in the axiom, then
use that as the coercion relation. The
assertion is coerced from Johns being an
elephant to Johns being heavy. LF
Assert(e2) rel(e1,e2) elephant(e1,x) Interp
heavy(e2,x) imply(e1,e2)
Write a Comment
User Comments (0)
About PowerShow.com