Natural Language Generation Language Technology Meaning Natural Language Understanding Natural Language Generation Text Text Speech Recognition Speech Synthesis Speech Speech

Natural Language Generation Language Technology Meaning Natural Language Understanding Natural Language Generation Text Text Speech Recognition Speech Synthesis Speech Speech

What is NLG? Natural language generation is the process of deliberately constructing a natural language text in order to meet specified communicative goals. [McDonald 1992]

Example System: FoG Function: Input: User: Developer: Status: Produces textual weather reports in English and French Input: Graphical/numerical weather depiction User: Environment Canada (Canadian Weather Service) Developer: CoGenTex Status: Fielded, in operational use since 1992

FoG: Input

FoG: Output

Example System: TEMSIS Function: Summarises pollutant information for environmental officials Input: Environmental data + a specific query User: Regional environmental agencies in France and Germany Developer: DFKI GmbH Status: Prototype developed; requirements for fielded system being analysed

http://www.dfki.de/service/nlg-demo/ TEMSIS

TEMSIS: Output Summary Le 21/7/1998 à la station de mesure de Völklingen -City, la valeur moyenne maximale d'une demi-heure (Halbstundenmittelwert) pour l'ozone atteignait 104.0 µg/m³. Par conséquent, selon le decret MIK (MIK-Verordnung), la valeur limite autorisée de 120 µg/m³ n'a pas été dépassée. Der höchste Halbstundenmittelwert für Ozon an der Meßstation Völklingen -City erreichte am 21. 7. 1998 104.0 µg/m³, womit der gesetzlich zulässige Grenzwert nach MIK-Verordnung von 120 µg/m³ nicht überschritten wurde.

A further system ILEX SUMTIME generation of virtual museum information online http://www.hcrc.ed.ac.uk/ilex/demos/museum.cgi SUMTIME generation of weather reports http://www.csd.abdn.ac.uk/~ssripada/cgi_bin/StartSMT.html

TEMSIS: Input Query ((LANGUAGE FRENCH) (GRENZWERTLAND GERMANY) (BESTAETIGE-MS T) (BESTAETIGE-SS T) (MESSSTATION \"Voelklingen City\") (DB-ID \"#2083\") (SCHADSTOFF \"#19\") (ART MAXIMUM) (ZEIT ((JAHR 1998) (MONAT 7) (TAG 21))))

Basic Generation Problem How to go from an abstract semantic input to a concrete linguistic form that is semantically correct stylistically appropriate textually appropriate ???

Standard Pipelined Architecture Document Planning Document Plan Microplanning Text Specification Surface Realisation

KPML TACTICAL GENERATOR semantics lexicogrammar Semantic specification sentence

KPML TACTICAL GENERATOR semantics lexicogrammar KPML is a Process generation engine Semantic specification Resources KPML semantics lexicogrammar sentence

TACTICAL GENERATION semantics lexicogrammar Semantic specification sentence

What is NLG? NLG is a process of choice under specified constraints Natural language generation is the process of deliberately constructing a natural language text in order to meet specified communicative goals. NLG is a process of choice under specified constraints [McDonald]

Linguistic Description with system networks imperative interrogative Finite^Subject indicative +Finite AXES declarative syntagmatic Subject^Finite paradigmatic

Resource Architecture in KPML: system networks imperative indicative interrogative declarative lexicogrammar

Resource Architecture in KPML: system networks grammatical systems imperative interrogative indicative declarative

Resource Architecture in KPML: system networks grammatical features imperative interrogative indicative declarative

Resource Architecture in KPML: system networks imperative interrogative Finite^Subject indicative +Finite declarative Subject^Finite

Resource Architecture in KPML: system networks realization statements imperative interrogative Finite^Subject indicative +Finite declarative Subject^Finite

Generation Process: system networks imperative interrogative Finite^Subject indicative +Finite declarative Subject^Finite

Generation Process: system networks imperative interrogative Finite^Subject indicative +Finite declarative Subject^Finite

Generation Process: traversal imperative interrogative Finite^Subject indicative +Finite declarative Subject^Finite

Generation Process: traversal imperative interrogative Finite^Subject indicative +Finite declarative Subject^Finite

Generation Process: traversal imperative interrogative Finite^Subject indicative +Finite declarative Subject^Finite

Generation Process: traversal imperative interrogative Finite^Subject indicative +Finite declarative Subject^Finite

Generation Process: traversal imperative interrogative Finite^Subject indicative +Finite declarative Subject^Finite

Generation Process: traversal imperative interrogative Finite^Subject indicative +Finite declarative Subject^Finite

Generation Process: traversal interrogative Finite^Subject indicative

Generation Process: structure interrogative Finite^Subject +Finite

Generation Process: structure interrogative Finite^Subject +Finite

realization statements Generation Process: realization statements Linear Precedence Subject Finite [clause] Finite^Subject Are you going? Immediate Dominance +Finite [interrogative]

Types of Realization Statements Ordering (immediate, relative) Structure building Lexicalization

Motivated Grammatical USER Functionally Motivated Grammatical Choices

Motivated Grammatical USER Functionally Motivated Grammatical Choices user = language engineer: developing and debugging the “grammatical competence” of a language resource

Motivated Grammatical USER Functionally Motivated Grammatical Choices Semantic Specifications

Motivated Grammatical USER Functionally Motivated Grammatical Choices Semantic Specifications user = system builder: developing and debugging a system that expects natural language generation functionality