Discourse Analysis

1
Discourse Analysis

• David M. Cassel
• Natural Language Processing
• Villanova University
• April 21st, 2005

2
Discourse Analysis

• Discourse collocated, related groups of
  sentences (from book)

3
Discourse Analysis

• Discourse Model -- a model to represent the
  entities mentioned in the discourse
• Coreference or Anaphora Resolution -- determining
  which entity a referring expression refers to
• Coherence -- modeling the logical flow of the
  discourse
• The book also discusses Psycholinguistic Studies
  of Reference and Coherence

4
Anaphora Resolution

• Before the game, manager Charlie Manuel said
  Gavin Floyd's performance would not affect
  whether he remains with the team when Vicente
  Padilla comes off the disabled list Tuesday.
• Then Floyd went out and had a nightmarish first
  inning four walks, one wild pitch, one hit, four
  runs.
• After the game, Manuel said Floyd's disastrous
  outing had not changed his mind. The righthander
  will remain with the club and be used in relief.
• "The pitcher we saw in St. Louis is a pitcher who
  has the ability to be a very good major-league
  pitcher," he said. "He didn't have command of his
  fastball and couldn't get his breaking ball over
  tonight... . Maybe the cold was affecting his
  breaking ball, because he was bouncing a lot of
  them."
• -- Sam Carchidi, Philadelphia Inquirer, 4/16/05

5
Discourse Model
evoke (introduce)
refer
he Floyd The righthander The pitcher we saw in
St. Louis his
corefer
Gavin Floyd
Adapted from Figure 18.1, Speech Language
Processing
6
Types of Anaphoric References

• Indefinite noun phrases
• A baseball player like that should do well.
• Definite noun phrases
• The righthander will remain with the club.
• Pronouns
• He had a bad game.
• Demostratives
• This player has a bright future.
• One-anaphora
• I saw no less than 6 Acura Integras today. Now I
  want one. (from book)

7
Reference Constraints

• Number Agreement
• Floyd pitched 6 innings. They went well.
• Person and Case
• He didnt have command of his fastball.
• Gender Agreement
• Floyd took his glove with him. It fit well.
• Syntactic Contraints
• Floyd threw him the ball.
• Selectional Restrictions
• Floyd stepped onto the mound with the ball. He
  threw it really fast.

8
Preferences

• Recency
• Floyd threw the ball. Lieberthal picked it up. He
  put the ball in his pocket.
• Grammatical Role
• Floyd threw the ball to Lieberthal. His arm was
  getting tired.
• Repeated Mention
• (See article)
• Parallelism
• Floyd threw a ball to Lieberthal. Wagner threw a
  ball to him, too.
• Verb Semantics
• John telephoned Bill. He lost the pamphlet on
  Acuras.
• John criticized Bill. He lost the pamphlet on
  Acuras.

9
Pronoun Resolution Algorithms

• Traditional
• Carter shallow parsing
• Rich, LuperFoy distributed architecture
• Carbonell, Brown multi-strategy
• Rico Pérez scalar product
• Mitkov combination of linguistic, statistical
  (high 80s)
• Lappin, Leass syntax-based (86)
• Hobbs Tree Search Algorithm (91.7)
• Grosz, Joshi, Weinstein Centering Algorithm
  (77.6)
• Hobbs Coherence

• Alternative
• Nasukawa knowledge-independent (93.8)
• Dagan, Itai statistical, corpus processing (87
  for genuine it)
• Connolly, Burger, Day machine learning
• Aone, Bennett machine learning (close to 90)
• Mitkov uncertainty reasoning
• Mitkov 2-engine (90)
• Tin, Akman situational semantics
• Say, Vakman

10
Lappin Leass

• Book presents a slightly modified algorithm for
  nonreflexive, 3rd person pronouns. Two parts
• Update discourse model with salience value
• Resolve pronouns
• Lets apply this to some text
• In the afternoon, Gavin Floyd played baseball at
  the park. Then he went to a bar with Mike
  Lieberthal. He enjoyed a beer.

11
Salience Factors
12
Pronoun Salience
13
LL Algorithm

• Collect the potential referents (up to four
  sentences back).
• Remove potential referents that do not agree in
  number or gender with the pronoun.
• Remove potential referents that do not pass
  intrasentential syntactic coreference
  constraints.
• Compute the total salience value of the referent
  by adding any applicable values to existing
  salience value.
• Select the referent with the highest salience
  value. In case of ties, select closest referent
  in terms of string position.

14
Example
In the afternoon, Gavin Floyd played baseball at
the park. Then he went to a bar with Mike
Lieberthal. He enjoyed a beer.
15
Example
In the afternoon, Gavin Floyd played baseball at
the park. Then he went to a bar with Mike
Lieberthal. He enjoyed a beer.
16
Example
In the afternoon, Gavin Floyd played baseball at
the park. Then he went to a bar with Mike
Lieberthal. He enjoyed a beer.
17
Example
In the afternoon, Gavin Floyd played baseball at
the park. Then he went to a bar with Mike
Lieberthal. He enjoyed a beer.
Gavin Floyd gets 35 point for Role Parallelism.
Mike Lieberthal does not. Floyd gt 265
points Lieberthal gt 75 points We pick Floyd as
the antecedent of He.
18
Summary

• Discourse Analysis requires processing more text
  than POS tagging or finding entities.
• Part of tracing the flow of discourse is
  resolving anaphora.
• That resolution lets us capture more
  relationships and other information than we could
  otherwise.