1. Introduction to Computational Linguistics
Eleni Miltsakaki
AUTH
Fall 2005-Lecture 8

2. What’s the plan for today?
Discourse models
Rhetorical Structure Theory
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
Nuclear:Satellite (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 N+S combination: R’s comprehending S increases R’s belief of N
The effect: R’s 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 N+S combination: R’s comprehending S increases R’s readiness to accept W’s right to present N
The effect: R’s readiness to accept W’s 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 N+S 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 R’s positive regard for the situation presented in N
The effect: R’s 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 doesn’t hold
Constraints on the N+S combination: W acknowledges a potential or apparent incompatibility between the situations presented in N and S; recognizing the incompatibility increases R’s positive regard for the situation presented in N
The effect: R’s 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 writer’s purpse than the other

22. RST annotated corpus Released via LDC (Language Data Consortium)
Information, samples of the corpus plus the RST annotation tool available at

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