Pragmatics%20I:%20Reference%20resolution

1
Pragmatics I Reference resolution

• Ling 571
• Fei Xia
• Week 7 11/8/05

2
Outline

• Discourse a related group of sentences
• Ex articles, dialogue, .
• Pragmatics the study of the relation between
  language and context-of-use
• Reference resolution
• Discourse structure

3
Reference resolution
4
Reference resolution

• Some terms referents, referring expression
• Discourse model
• Types of referring expression
• Types of referents
• Constraints and preference for reference
  resolution
• Some algorithms for reference resolution

5
Some terms

• Ex John bought a book yesterday. He thought it
  was cheap.
• Referring expression the expression used to
  refer to an entity
• Ex John, a book, he, it
• Referent an entity that is referred to.

6
Some Terms (cont)

• Co-reference two or more referring expressions
  refer to the same entity e.g., John and he.
• Antecedents a referring expression that licenses
  the use of others. Ex. John
• Anaphora reference to an entity that has been
  previous introduced. Ex he

7
Discourse Model

• A discourse model stores the representations of
  entities that have been referred to in the
  discourse and the relationships in which they
  participate.
• Two operations
• Evoke first mention
• Access subsequence mention

8
Refer (evoke)
Refer (access)
He
John
Corefer
9
Five types of referring expressions

• Indefinite NPs a car
• Definite NPs the car
• Pronouns it
• Demonstratives this, that
• One-anaphora one

10
Indefinite NPs

• Introduce entities that are new to the hearer
• The entity may or may not be identifiable to the
  speaker
• I saw an Acura today. (Specific reading)
• I am going to the dealership to buy an Acura
  today. (specific or non-specific)
• I hope that they still have it. (Specific)
• I hope that they have a car I like.
  (non-specific)

11
Definite NPs

• Identifiable to the hearer
• I saw an Acura today. The Acura
• (explicitly mentioned before in the context)
• The Eagles .
• (the hearers knowledge about the world)
• The largest company in Seattle announced
  (inherently unique)

12
Pronouns

• Pronouns refer to something that is identifiable
  to the hearer.
• The referent must have a high degree of salience
  in the discourse model.
• Pronouns can participate in cataphora, in which
  they appear before their referents.
• Ex Before he bought it, John checked over the
  Acura very carefully.

13
Demonstratives

• Demonstratives refer to something that is
  identifiable to the hearer.
• They are used alone or as a determiner
• Ex I want this. I want this car.
• this indicating closeness, that signaling
  distance spatial/temporal distance.

14
One-anaphora

• One ? One of them
• It selects a member from a set that is
  identifiable to the hearer.
• Ex
• He had a BMW before, now he got another one.
• Is he the one?
• You like this one, or that one?
• John has two BMWs, but I have only one.
• One should not pay more than 20K for a Camry.

15
Five types of referring expressions

• Indefinite NPs a car
• Definite NPs the car
• Pronouns it
• Demonstratives this, that
• One-anaphora one
• Next question what do a referring expression
  refers to?

16
Types of referents

• Ex According to John, Bob bought Sue a BMW, and
  Sue bought Bob a Honda.
• But that turned out to be a lie. (speech act)
• But that was false. (proposition)
• That caused Bob to become rather poor. (event)
• That caused them both to become rather poor.
  (combination of events)

17
Inferrables

• Explicitly evoked in the text John bought a car.
• Inferrables inferrentially related to an evoked
  entity.
• Whole-part I almost bought a BMW today, but a
  door had a dent and the engine seemed noisy.
• The results of action Mix the flour and water,
  kneed the dough until smooth.

18
Discontinuous sets

• Plural references may refer to entities that have
  been evoked separately.
• Ex
• John has an Acura, and Mary has a Mazda. They
  drive them all the time. (pairwise reading)

19
Generics

• Generic references individual ? generic
• Ex I saw six BMWs today. They are the coolest
  cars.

20
Refer (evoke)
Refer (access)
He
John
Corefer
21
Constraints and preferences for reference
resolution

• Constraints (filters)
• Agreement number, person, gender
• Syntax reflexives
• Semantics selectional restrictions
• Preferences
• Salience
• Parallelism
• Verb semantics

22
Agreement

• Number
• (1) John bought a BMW.
• (2a) It is great.
• (2b) They are great.
• (2c) ??They are red.
• Person
• (1) John and I have BMWs.
• (2a) We love them.
• (2b) They love them.

23
Agreement (cont)

• Gender she, he, it.
• (1) John looked at the new ship.
• (2) She was beautiful.
• (1) Mary looked at the new ship.
• (2) She was beautiful.

24
Syntactic constraints

• Reflexives and personal pronouns.
• John bought himself a car.
• John bought him a car.
• John wrapped a blanket around himself.
• John wrapped a blanket around him.

25
Semantic constraints

• Selectional restrictions
• (1) John parked his car in the garage.
• (2a) He had driven it around for hours.
• (2b) It is very messy, with old bike and car
  parts lying around everywhere.
• (1) John parked his Acura in downtown Beverly
  Hills.
• (2) It is very messy, with old bikes and car
  parts lying around everywhere.

26
Preferences in pronoun interpretation

• Saliency
• Recency
• Grammatical role
• Repeated Mention
• Parallelism
• Verb semantics

27
Saliency

• Recency
• John has an Integra. Bill has a BMW. Mary likes
  to drive it.
• Grammatical role
• John went the dealership with Bill. He bought a
  car.
• Repeated mention
• John needed a car. He decided to get a BMW. Bill
  went to the dealership with him. He bought one.

28
Parallelism

• Mary went with Sue to the Acura dealership. Sally
  went with her to the Mazda dealership.

29
Verb semantics

• John telephoned Bill. He lost the pamphlet on
  BMWs.
• John seized the pamphlet to Bill. He loves
  reading about cars.
• The car dealer admired John. He knows
  Acuras inside and out.
• ?Thematic roles or world knowledge?

criticized
passed
impressed
30
Constraints and preferences for reference
resolution

• Hard-and-fast constraints (filters)
• Agreement number, person, case, gender
• Syntax reflexives
• Semantics selectional restrictions
• Preferences
• Saliency recency, thematic roles, repeated
  mention
• Parallelism
• Verb semantics thematic roles or world knowledge

31
Algorithms for pronoun resolution

• Heuristics approaches
• Lappin Leass (1994)
• Hobbs (1978)
• Centering Theory (Grosz, Joshi, Weinstein 1995,
  and various)
• Machine learning approaches

32
Lappin Leass 1994

• A heuristic approach.
• Use agreement and syntactic constraints.
• Represent preferences (saliency, parallelism)
  with weights.
• Not using selectional restrictions, verb
  semantics, world knowledge.

33
Salience factors and weights

• Sentence recency 100
• Subject
  80
• Existential position 70
• There is a car .
• Direct object
  50
• Indirect object
  40
• Non-adv
  50
• Inside his car, John ..
• Head noun of max NP 80
• The manual for the car is

34
The algorithm

• Start with an empty set of referents.
• Process each sentence
• For each referring expression
• Calculate the salience value of the expression.
• If it could be merged with existing referents
• then choose the referent with the highest
  saliency value
• else add it as a new referent.
• Update the value of the corresponding referent.
• Cut the values of all the referents by half.

35
An example

• John saw a beautiful Acura at the dealership.

Rec Subj Obj Non-adv Head noun Total
John 100 80 50 80 310
Acura 100 50 50 80 280
dealership 100 50 80 230
36
Before moving on to the 2nd sentence
Referent Referring expressions Value
John John 155
Acura Acura 140
dealership dealership 115
37
Handling He

• He showed it to Bob.
• The value of He is 310

Referent Referring expressions Value
John John 155
Acura Acura 140
dealership dealership 115
38
After adding he

• He showed it to Bob.

Referent Referring expressions Value
John John, he 465
Acura Acura 140
dealership dealership 115
39
Handling it

• He showed it to Bob.
• The salience value of it is 280.
• Two new factors
• Role parallelism 35
• Cataphora (??) -175

Referent Expressions Value
John John, he 465
Acura Acura 140
dealership dealership 115
40
After adding it

• He showed it to Bob.
• The salience value of it is 280.
• Two new factors
• Role parallelism 35
• Cataphora (??) -175

Referent Expressions Value
John John, he 465
Acura Acura, it 14028035455
dealership dealership 115
41
Handling Bob

• He showed it to Bob.
• The salience value of Bob is 270.

Referent Expressions Value
John John, he 465
Acura Acura, it 455
dealership dealership 115
42
After adding Bob

• He showed it to Bob.
• The salience value of Bob is 270.

Referent Expressions value
John John, he 465
Acura Acura, it 455
Bob Bob 270
dealership dealership 115
43
Moving on to the 3rd sentence

• He bought it.

Referent Expressions value
John John, he 232.5
Acura Acura, it 227.5
Bob Bob 135
dealership dealership 57.5
? He (John) bought it (Acura).
44
Core of the algorithm

• For each referring expression
• Calculate the saliency value, x.
• Collect all the referents that comply with
  agreement and syntactic constraints.
• If the set is not empty, choose the one with the
  highest salience value, and increase the
  reference value by x.
• If the set is empty, add a new referent to the
  discourse model, and set its value to x.

45
Algorithms for reference resolution

• Heuristics approaches
• Lappin Leass (1994)
• Hobbs (1978)
• Centering Theory (Grosz, Joshi, Weinstein 1995,
  and various)
• Machine learning approaches

46
Summary of reference resolution

• Some terms referents, referring expression
• Discourse model
• Types of referring expression
• Types of referents
• Constraints and preference for reference
  resolution
• Some algorithms for reference resolution