CS544: Lecture 5: Reference and Other Problems

CS544: Lecture 5:Reference and Other Problems

Jerry R. Hobbs

USC/ISI

Marina del Rey, CA

February 18, 2010

Logical Form

Pat asked Chris to leave early.

Pat(x) & Past(e1) & ask’(e1,x,y,e2) & Chris(y) & leave’(e2,y) & early(e2)

e2

e2, y

y

x

The x in Pat(x) and ask’(e1,x,y,e2) are

the same.

Now what?

The y in Chris(y) and ask’(e1,x,y,e2) are

the same.

The y and e2 in leave’(e2,y) and ask’(e1,x,y,e2) are

the same.

The e2 in leave’(e2,y) and early(e2) are

the same.

Is There Systematicity?

The basic unit of information is the predication:

p(x,y)What is p? predicate

strengtheningWhat are x and y?

coreference

What’s 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)

What’s the relation between these two predications?intraclausal coherence, discourse coherence

(predicate strengthening on sentence adjacency)

What is the Predicate?

Interpreting compound nominals: pension fund => pension(y) & nn(y,x) & fund(x) fire fight, prairie storms, Saturnian system

Interpreting possessives: the nation’s biggest pension fund, Afghanistan’s 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.

What is the Argument?Coreference

Pronouns: CalPERS’ efforts this year to boost its financial performance John can open Bill’s safe. He knows the combination.

Definite noun phrases: Anaphoric: I bought a new car, but the brakes sometimes don’t 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?

Why this Predicate with this Argument?

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 q(x) where p(x) --> q(x)

p(x) interpreted as p(f(x))

Clause-Internal Coherence

Relations that go beyond the predicate-argument relations conveyed by syntactic structure:

“The nation’s biggest public pension fund, which has lost more than a quarter of its value in the last seven months, is planning to rally biginvestors nationwide to demand changes in the way Wall Streetoperates.”

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

Discourse Coherence

Relations between successive segments of discourse are typically varieties of rephrasing/elaboration: John can open Bill’s 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 florist’s. 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.

One Variety of Inference:Abduction

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.

HearerSpeaker MB

Utt

Uniform frameworkfor syntax, semantics,and pragmatics

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.

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) --> rel(x,y)

in(O,B), Boston(B)

in(y,z) --> nn(z,y)

Syntax : Parse Tree :: Interpretation : Proof Graph

New Information

DefiniteReference

Metonymy

Compound Nominal

“Local Pragmatics” problems solved as a by-product

Is There Systematicity?

The basic unit of information is the predication:

p(x,y)What is p? predicate

strengtheningWhat are x and y?

coreference

What’s 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)

What’s the relation between these two predications?intraclausal coherence, discourse coherence

(predicate strengthening on sentence adjacency)

Reference and Coreference

Language: ......... x ................. y .............

World: A

x refers to A; y refers to A; x and y corefer; y is coreferential with xThe 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

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

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 Afghanistan’s Uruzgan Valley were engulfed in a ferocious fire fight with the Taliban. Only after six hours, andsupporting 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 wouldn’t 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.

An Algorithm for Pronoun Resolution

The network system divides data into small blocks called packets, which it sendsindividually.

S

NPFrom pronoun:1. Skip reflexive level2. Go up to next NP or S3. Breadth-first search for candidate NPs4. Rule out if selectional, number or gender conflict5. Pick the first candidate

80-90% accuracy

VP

The networksystem

divides

sendsit

which

packets

called

smallblocks

into

NP PP

NP

SBAR

S

NP VP

data

VP

NP

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”.

He hadn’t planned to toss her here.

He had hoped to do it earlier in the voyage, between Nassau and San Juan.

CONTRASTCONTRAST

the Voyager 2 spacecraft sped through the Saturnian system

it came within 90,000 kilometers of the moon Enceladus

First and Second Person Pronouns

I, me, my: “.... I ....,” Person Verb[say] ...

OR the speaker/writer: “I would momentarily forget where I was”

we, us, our: “ .... we ....,” Verb[say] 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

“the” and “a”Conventional notation:

A car arrives. ==> (E x)[car(x) & arrive(x)]

The car arrives. ==> 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 ==> the(x,e) & man’(e,x) a man ==> a(x,e) & man’(e,x)

Highly idiosyncratic

Definite NPs

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 car’s 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”

Heuristic: Person resolves to last Person, etc.

No good heuristics; there are efforts to learn common associations, e.g., part-of relations

Anaphoric

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)

Resolving Definite NPs with Inference

... a car ... ... the car ...

... Prius ... ... the car ...

... acity ... ... the streets ...

Prius(x) --> car(x)

city(x) --> (E s,y) street(y) & in(y,x) & Plural(y,s)

Prove the existence of:

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.

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?

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?

tougher regulation by federal agencies.

suppporting air strikes

The work was tougher in such weather

The interest generated by Voyager’s 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?

of what?

by whom and against whom?

than what?

in what and by whom?

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) --> with(f,t)

If y accompanies t in event e, then e is with t: accompany(y,t,e) & arg(y,e) --> with(e,t)

Constrainedcoreference

problem

Is There Systematicity?

The basic unit of information is the predication:

p(x,y)What is p? predicate

strengtheningWhat are x and y?

coreference

What’s 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)

What’s the relation between these two predications?intraclausal coherence, discourse coherence

(predicate strengthening on sentence adjacency)

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

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)

fund(y1) --> provide(y1,x2) & payment(x2)

payment(x2) & for(x2,e3) & retire’(e3,z) --> pension(x2)

x1=x2

Other Vague Predicates

Possessive: CalPERS’ efforts: efforts by CalPERS Afghanistan’s 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)

Lexical Ambiguity

The plane taxied to the terminal.

plane(x) & taxi(x,y) & terminal(y)

KB:

airplane(x) --> plane(x)

move-on-ground(x,y) & airplane(x) --> taxi(x,y)

airport-terminal(y) --> terminal(y)

airport(z) --> airplane(x) & airport-terminal(y)

wood-smoother(x) --> plane(x)

ride-in-cab(x,y) & person(x) --> taxi(x,y)

computer-terminal(y) --> terminal(y)

LF:

Specializationsof the vague

predicate “plane”

Lexical Ambiguity

The plane taxied to the terminal.

plane(x) & taxi(x,y) & terminal(y)

KB:

airplane(x) --> plane(x)

move-on-ground(x,y) & airplane(x) --> taxi(x,y)

airport-terminal(y) --> terminal(y)

airport(z) --> airplane(x) & airport-terminal(y)

wood-smoother(x) --> plane(x)

ride-in-cab(x,y) & person(x) --> taxi(x,y)

computer-terminal(y) --> terminal(y)

LF:

Lexical Ambiguity

John wanted a loan. He went to the bank.

LF: . . . & loan(l) & . . . . . . & bank(y) & . . .

KB:loan(x) --> financial-institution(y) & issue(y,x)

financial-institution(y) & etc4(y) --> bank1(y)

bank1(y) --> bank(y)

river(z) --> bank2(y) & borders(y,z)

bank2(y) --> bank(y)

Is There Systematicity?

The basic unit of information is the predication:

p(x,y)What is p? predicate

strengtheningWhat are x and y?

coreference

What’s 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)

What’s the relation between these two predications?intraclausal coherence, discourse coherence

(predicate strengthening on sentence adjacency)

Are the Predicate and Argument“Congruent”?

p(x)

The predicate reallymeans something else,

e.g., metaphor

The argument reallyrefers to something else:

metonymy

John is an elephant==> John is big / clumsy / has a good memory / ...

I like to read Shakespeare==> I like to read the plays written by Shakespeare

This restaurant takes American Express==> This restaurant takes credit cards issued by American Express

What about -- America believes in democracy.

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.

In a World Without Metonymy

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

Government

Organization

Person

rulesisa member-of

More generally, prove there is a relation between the apparent referentand something satisfying the requirements, in the most economical way.

read Shakespeare

text wrote plays

coercion relation

See Katja Markertand Udo Hahn,

Artificial IntelligenceJournal, 2003

e.g., France criticized American policy in Iraq.

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

Metaphor

John is an elephant ==> John is heavy

A metaphor explicitly conveys one thing, but is intended to convey something implied by what is explicit.

elephant’(e1,x) --> 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 John’s being an elephant to John’s being heavy.

LF: Assert(e2) & rel(e1,e2) & elephant’(e1,x)

Interp: heavy’(e2,x) & imply(e1,e2)