Language Technology Meaning Natural Language Understanding Natural Language

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

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

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

Example System: Fo. G • Function: – Produces textual weather reports in English and French • Input: – Graphical/numerical weather depiction • User: – Environment Canada (Canadian Weather Service) • Developer: – Co. Gen. Tex • Status: – Fielded, in operational use since 1992

Fo. G: Input

Fo. G: 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 Gmb. H • Status: – Prototype developed; requirements for fielded system being analysed

M E T S I S http: //www. dfki. de/service/nlg-demo/

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 (MIKVerordnung), 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 – 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/Start. SMT. 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

TACTICAL GENERATOR Semantic specification KPML sentence semantics lexicogrammar

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

TACTICAL GENERATION Semantic specification semantics lexicogrammar sentence

What is NLG? 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 [Mc. Donald]

Linguistic Description with system networks imperative AXES indicative +Finite atic gm a t n sy paradigmatic interrogative Finite^Subject declarative Subject^Finite

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

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

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

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

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

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

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

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

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

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

Generation Process: traversal indicative +Finite interrogative Finite^Subject

Generation Process: structure interrogative Finite^Subject +Finite

Generation Process: structure interrogative Finite^Subject +Finite

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

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

USER Functionally Motivated Grammatical Choices

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

USER Semantic Specifications Functionally Motivated Grammatical Choices

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