Jan 2004CSA3050: NLG21 CSA3050: Natural Language Generation 2 Surface Realisation Systemic Grammar Functional Unification Grammar see J&M Chapter 20.3.

Jan 2004 CSA3050: NLG2 1

CSA3050: Natural Language Generation 2

Surface RealisationSystemic GrammarFunctional Unification Grammarsee J&M Chapter 20.3

Jan 2004 CSA3050: NLG2 2

Surface Realisation within NLG

Jan 2004 CSA3050: NLG2 3

Revealing Quotations

• Language understanding is somewhat like counting from one to infinity; language generation is like counting from infinity back to one. [Y. Wilks, 1988]

• Generation from what?! [C. Longuet-Higgins]

• Moral: there is no consensus about the level of representation we start from. This applies in particular to surface realisation.

Jan 2004 CSA3050: NLG2 4

Surface Realisation

• There is, however, some agreement that output should be specified in terms of function rather than syntactic form

• Consider the case of voice (syntactic form)The system will save the document vs.The document will be saved by the system

• Output of a discourse planner is not in terms of voice, active v. passive.

• More likely in terms of notions like topic, focus etc. whose surface realisation is left to a subsequent processing stage.

Jan 2004 CSA3050: NLG2 5

Two Approaches toSurface Realisation

• Systemic Grammar (Halliday 1985)– Systemic Functional Linguistics– Language as a resource for expressing meaning in

context.– Sentences are regarded collections of functions that

are mapped to grammatical forms.• Functional Unification Grammar (Kay 1979)

– Grammar is a "feature structure" (recursive attribute/value pairs).

– Input specification is another feature structure– Realisation viewed as further specification of input to

yield output sentence via fundamental operation of functional unification.

Jan 2004 CSA3050: NLG2 6

Systemic Grammar: Multi-Layered Sentence Analysis

the system will save the document

Mood subject finite predicator object

Transitivity actor process goal

Theme theme rheme

• Mood layer defines interaction between reader and writer: telling v. asking v. ordering• Transitivity layer expresses propositional content • Theme layer deals with topic (highlighting function)

Jan 2004 CSA3050: NLG2 7

Systemic Grammar

• Grammar is represented as a graph called a system network. This comprises

• and systems (curly braces) – conjunctive features in boldface

• or systems (straight vertical lines) – disjunctive features in normal face

• realisation statements (in italic).– specify how disjunctive features are realised

Jan 2004 CSA3050: NLG2 8

Jan 2004 CSA3050: NLG2 9

Realisation Statements

• +X: insert the function X+predicator

• X=Y: conflate the functions X and Y goal = subject

• X>Y: order X somewhere before Ysubject > predicator

• X/A: function X has grammatical feature Ysubject/noun phrase

• X!L assign function X to lexical item Lpassive!be

Jan 2004 CSA3050: NLG2 10

Generation Procedure

1. Traverse network from left to right, choosing the appropriate features and collecting the appropriate realisation statements.

2. Build an intermediate expression that obeys the constraints set by the realisation statements.

3. Recurse back through the grammar at a lower level for functions not fully specified.

Jan 2004 CSA3050: NLG2 11

Example Input

( :process save-1 :actor system-1 :goal document-1 :speechact assertion :tense future)• N.B. This specification resembles that used by

PENMAN system (Mann 1983) based on KL-ONE knowledge base.

Jan 2004 CSA3050: NLG2 12

Generation 1

• Start with clause feature– insert predicator and classify as verb

• Proceed to mood subsystem

• after interrogating input specification (assertion is specified) choose indicative and declarative features.

• Insert subject and finite functions with ordering subject > finite > predicator

Jan 2004 CSA3050: NLG2 13

Output of Mood System

Mood subject finite predicator

Jan 2004 CSA3050: NLG2 14

Generation 2

• Proceed to Transitivity subsystem.

• Assuming save-1 is a material process (from KB)– Insert goal and process functions– Conflate process with (finite, predicator) pair– Proceed to Voice subsystem– Choose Active feature and obey realisation

statements.

Jan 2004 CSA3050: NLG2 15

Output of Transitivity System

Mood subject finite predicator object

Transitivity actor process goal

Jan 2004 CSA3050: NLG2 16

Generation 3

• Proceed to Theme subsystem

• Since there is no thematic specification in the input, choose Unmarked Theme– Insert theme and rheme functions– Conflate theme with subject and rheme with

predicator,object

Jan 2004 CSA3050: NLG2 17

Output of Mood Subsystem

Mood subject finite predicator object

Transitivity actor process goal

Theme theme rheme

Jan 2004 CSA3050: NLG2 18

Generation 4

• Generation now recursively enters the grammar at lower levels to fully specify– the phrases (noun phrase network, auxiliary

network – not shown here)– lexical items (usually through entries in the

knowledge base)– and possibly morphological choices

Jan 2004 CSA3050: NLG2 19

Result of Generation

the system will save the document

Mood subject finite predicator object

Transitivity actor process goal

Theme theme rheme

Jan 2004 CSA3050: NLG2 20

Functional Unification Grammar

• Build the generation grammar as a feature structure (FS)

• Build input specification as an FS

• Unify the two together (functional unification operation).

• Linearize result.

Jan 2004 CSA3050: NLG2 21

Feature Structures

• Feature structures are essentially sets of attribute value pairs

attribute1 value1attribute2 value2:attribute3 value3

Jan 2004 CSA3050: NLG2 22

Feature Structure 2

• These can be used to express facts of different kinds

name mikeheight 156:eyes green

number singgender masc:case nom

human facts agreement facts

Jan 2004 CSA3050: NLG2 23

Feature Structures 3

• Furthermore, values can themselves be feature structures

number singgender masccase nom

cat NPagreement

Jan 2004 CSA3050: NLG2 24

Functional Unification

• The information in feature structures can be combined together by means of the functional unification () operation.

name mikeheight 156

eyes green

name mikeheight 156eyes green

=

25

Grammar as a Feature Structure

Jan 2004 CSA3050: NLG2 26

Input Specification –as a Feature Structure

cat S

actor head lex system

process head lex savetense future

goal head lex document

27

Partial Result

cat S

actor cat NPhead lex system

process cat VPnumber {actor number}head lex savetense future

goal cat NPhead lex document

pattern (actor process goal)

28

Full Result