Natural Language Generation

1
Natural Language Generation

• Martin Hassel
• KTH NADA
• Royal Institute of Technology
• 100 44 Stockholm
• 46-8-790 66 34
• xmartin_at_nada.kth.se

2
What Is Natural Language Generation?

• A process of constructing a natural language
  output from non linguistic inputs that maps
  meaning to text.

3
Related Simple Text Generation

• Canned text
• Ouputs predefined text
• Template filling
• Outputs predefined text with predefined variable
  words/phrases

4
Areas of Use

• NLG techniques can be used to
• generate textual weather forecasts from
  representations of graphical weather maps
• summarize statistical data extracted from a
  database or spreadsheet
• explain medical info in a patient-friendly way
• describe a chain of reasoning carried out by an
  expert system
• paraphrase information in a diagram for
  inexperienced users

5
Goals of a NLG System

• To supply text that is
• correct and relevant information
• non redundant
• suiting the needs of the user
• in an understandable form
• in a correct form

6
Choices for NLG

• Content selection
• Lexical selection
• Sentence structure
• Aggregation
• Referring expressions
• Orthographic realisation
• Discourse structure

7
Example Architecture
8
Discourse Planner

• Text shemata
• Use consistent patterns of discourse structure
• Rhetorical Relations
• Uses the Rhetorical Structure Theory
• Used for varied generation tasks

9
Discourse Planner Text Schemata

• Augmented Transition Network (ATN)
• Uses a set of internal states and transitions
• Produces texts with a rigid structure
• i.e. recipes, directions, technical instructions

10
Discourse Planner Augmented Transition Network
11
Discourse Planner Augmented Transition Network

• Example output
• Save the document First, choose the save option
  from the file menu. This causes the system to
  display the Save-As dialog box. Next, choose the
  destination folder and type the filename.
  Finally, press the save button. This causes the
  system to save the document.

12
Discourse Planner Rhetorical Relations

• Rhetorical Structure Theory
• (Mann Thompson 1988)
• Nucleus
• Multi-nuclear
• Satellite

13
Discourse Planner Rhetorical Relations

• 23 rhetorical relations, among these
• Elaboration
• Contrast
• Condition
• Purpose
• Sequence
• Result

14
Discourse Planner Rhetorical Relations

• Rethorical annotation

15
Discourse Planner Rhetorical Relations

• The resulting RST tree corpus
• (SATELLITE(SPAN419)(REL2PAR
  ELABORATION-ADDITIONAL)
• (SATELLITE(SPAN47)(REL2PAR CIRCUMSTANCE)
• (NUCLEUS(LEAF4)(REL2PAR CONTRAST)
• (TEXT _!THE PACKAGE WAS TERMED EXCESSIVE BY
  THE BUSH ADMINISTRATION,_!))
• (NUCLEUS(SPAN57)(REL2PAR CONTRAST)
• (NUCLEUS(LEAF5)(REL2PAR SPAN)
• (TEXT _!BUT IT ALSO PROVOKED A STRUGGLE WITH
  INFLUENTIAL CALIFORNIA LAWMAKERS_!))

16
Surface Realisation

• Systemic Grammar
• Represents sentences as collections of functions
• Using functional categorization
• Functional Unification Grammar
• Builds generation grammar as a feature structure
• Using functional categorization

17
Surface Realisation Systemic Grammar

• Emphasises the functional organisation of
  language
• Surface forms are viewed as the consequences of
  selecting a set of abstract functional features
• Choices correspond to minimal grammatical
  alternatives
• The interpolation of an intermediate abstract
  representation allows the specification of the
  text to accumulate gradually

18
Surface Realisation Systemic Grammar

• Uses multiple layers
• Mood, Transivity, Theme
• Meta-functions
• Interpersonal meta-function (mood)
• Ideational meta-function (transivity)
• Textual meta-function (theme)
• Grammar represented as a system network
• Directed, acyclic and/or graph

19
Surface Realisation Systemic Grammar
Declarative
Interrogative
20
Surface Realisation Systemic Grammar

• Clause Choices
• Major indicative declarativeThe cat is on the
  mat.
• Major indicative declarative relativeHe didnt
  see the cat that chased the rat.
• Major indicative declarative boundIt only
  hurts when I laugh.
• Major indicative interrogative polarHas anybody
  seen my seagull?
• Major imperativeDont be ridiculous.
• Minor present-participleYoull enjoy having
  more free time.

21
Surface Realisation Functional Unification
Grammar

• Basic idea
• Input specification in the form of a FUNCTIONAL
  DESCRIPTION, a recursive ltattribute,valuegt matrix
• The grammar is a large functional description
  with alternations representing choice points
• Realisation is achieved by unifying the input FD
  with the grammar FD

22
Surface Realisation Functional Unification
Grammar

• ((cat clause)
• (process ((type composite)
• (relation possessive)
• (lex hand)))
• (participants ((agent ((cat pers_pro)
• (gender feminine)))
• ((affected ((cat np)
• (lex editor)))
• ((possessor ))
• ((possessed ((cat np)
• (lex draft)))))
• She hands the draft to the editor.

23
Microplanners 1

• Lexical selection
• Syntactic realization
• Morphological realization
• Orthographic realization

24
Microplanners 2Referring Expression Generation

• Referring expression generation is concerned with
  how we describe domain entities in such a way
  that the hearer will know what we are talking
  about
• Major issue is avoiding ambiguity
• Fluency pulls in the opposite direction

25
Kinds of Referring Expressions

• Proper names
• Aberdeen, Scotland
• Aberdeen
• Definite Descriptions
• the train that leaves at 10am
• the next train
• Pronouns
• she
• it

26
Microplanners 3Aggregation

• Some possibilities
• Simple conjunction
• Ellipsis
• Set introduction

27
Aggregation

• Without aggregation
• The next train is the Caledonian Express.
• It leaves at 10AM.
• With Simple Conjunction
• The next train is the Caledonian Express, and it
  leaves at 10AM.
• Without aggregation
• It leaves at 10AM.
• It arrives at 12.30PM.
• With ellipsis
• It leaves at 10AM, and Ø arrives at 12.30PM.

28
Aggregation

• Without aggregation
• It has a snack bar.
• It has a restaurant car.
• With set introduction
• It has a snack bar, a restaurant car.
• It has a snack bar and a restaurant car.
• Caution! Need to avoid changing the meaning
• John bought a TV and Bill bought a TV.
• John and Bill bought a TV.

29
Further Reading

• Siggen
• http//www.dynamicmultimedia.com.au/siggen/
• Allen 1995 Natural Language Understanding
• http//www.uni-giessen.de/g91062/Seminare/gk-cl/A
  llen95/al1995co.htm