Introduction%20to%20Computational%20Linguistics

1
Introduction to Computational Linguistics

• Eleni Miltsakaki
• AUTH
• Fall 2005-Lecture 8

2
Whats the plan for today?

• Discourse models
• Rhetorical Structure Theory
• http//www.sfu.ca/rst/
• Next time The DLTAG approach

3
What is RST?

• A descriptive theory of discourse organization,
  characterizing text mostly in terms of relations
  that hold between parts of text.

4
History

• RST was developed as part of a project on
  computer-based generation of text by Bill Mann,
  Sandy Thompson and Christian Matthiessen
• RST is based on studies of carefully written text
  of a variety of sources
• RST is intended to describe texts (not processes
  of producing or understanding them)
• RST gives an account of coherence in text

5
Elements of RST

• Relations
• Schemas
• Schema applications
• Structures

6
Relations

• Relations hold between two non-overlapping text
  spans
• NuclearSatellite (denoted by N and S)
• Multi-nuclear relations

7
Example
8
RST tree
9
Definition of relations

• Constraints on nucleus
• Constraints on satellite
• Constraints on the combination of nucleus and
  satellite
• The effect

10
RST schemas

• Schemas define the structural constituency
  arrangement of text.

11
RST schema applications

• Unordered spans the schemas do not constrain the
  order of nucleus or satellites in the text span
  in which the schema is applied
• Optional relations for multi-relations schemas,
  all individual relations are optional, but at
  least one if the relations must hold
• Repeated relations a relation that is part of a
  schema can be applied any number of times in the
  application of that schema

12
Basic RST relations
13
Evidence

• Relation name EVIDENCE
• Constraints on N R might not believe N to a
  degree satisfactory to W(riter)
• Constraints on S The reader believes S or will
  find it credible
• Constraints on the NS combination Rs
  comprehending S increases Rs belief of N
• The effect Rs belief of N is increased
• Locus of the effect N

14
Example

• The program as published for calendar year 1980
  really works.
• In only a few minutes, I entered all the figures
  from my 1980 tax return
• And got a result which agreed with my hand
  calculations to the penny.
• 2-3 EVIDENCE for 1

15
Justify

• Relation name JUSTIFY
• Constraints on N none
• Constraints on S none
• Constraints on NS combination Rs comprehending
  S increases Rs readiness to accept Ws right to
  present N
• The effect Rs readiness to accept Ws right to
  present N is increased
• Locus of the effect N

16
Antithesis

• Relation name ANTITHESIS
• Constraints on N W has positive regard for the
  situation presented in N
• Constraints on S none
• Constraints on NS combination the situation
  presented in N and S are in contrast. Because of
  the incompatibility that arises from contrast,
  one cannot have positive regard for both
  situations presented in N and S comprehending S
  and the incompatibility between the situations
  presented in N and S increases Rs positive
  regard for the situation presented in N
• The effect Rs positive regard for N is
  increased
• Locus of effect N

17
Concession

• Relation name CONCESSION
• Constraints on N W has positive regard for the
  situation presented in N
• Constraints on S W is not claiming that the
  situation presented in S doesnt hold
• Constraints on the NS combination W
  acknowledges a potential or apparent
  incompatibility between the situations presented
  in N and S recognizing the incompatibility
  increases Rs positive regard for the situation
  presented in N
• The effect Rs positive regard for the situation
  presented in N is increased
• Locus of effect N and S

18
Example

• Concern that this material is harmful to health
  or the environment may be misplaced.
• Although it is toxic to certain animals,
• Evidence is lacking that it has any serious
  long-term effect on human beings.
• 2 CONCESSION to 3
• 2-3 ELABORATION to 1

19
Span order
20
Distinctions among relations

• Subject matter (semantic)
• Two parts of the text are understood as causally
  related in the subject matter
• E.g. VOLITIONAL CAUSE
• Presentational (pragmatic)
• Facilitate presentation process
• E.g. JUSTIFY

21
What is nuclearity?

• Relations are mostly asymmetric
• E.g. If A is evidence for B, then B is not
  evidence for A
• Diagnostics for nuclearity
• One member is independent of the other but not
  vice versa
• One member is more suitable for substitution that
  the other. An EVIDENCE satellite can be replaced
  by entirely different evidence
• One member is more essential to the writers
  purpse than the other

22
RST annotated corpus

• Released via LDC (Language Data Consortium)
• www.ldc.upenn.edu
• Information, samples of the corpus plus the RST
  annotation tool available at
• www.isi.edu/marcu/discourse

23
RST-based discourse parsing

• An unsupervised approach to recognizing
  discourse relations (2002) by D. Marcu and A.
  Echihabi
• The rhetorical parsing of unrestricted texts A
  surface-based approach (2000) by D. Marcu