Presentation is loading. Please wait.

Presentation is loading. Please wait.

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

Similar presentations


Presentation on theme: "Text Language Technology Natural Language Understanding Natural Language Generation Speech Recognition Speech Synthesis Text Meaning Speech."— Presentation transcript:

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

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

3 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]

4 Example System: FoG Function: –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

5 FoG: Input

6 FoG: Output

7 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

8 TEMSIS

9 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 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 µg/m³, womit der gesetzlich zulässige Grenzwert nach MIK-Verordnung von 120 µg/m³ nicht überschritten wurde.

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

11 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))))

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

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

14 KPML lexicogrammar semantics sentence Semantic specification TACTICAL GENERATOR

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

16 lexicogrammar semantics sentence Semantic specification TACTICAL GENERATION

17 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 [McDonald]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

32 Generation Process: traversal indicative interrogative +Finite Finite^Subject

33 Generation Process: structure +Finite Finite^Subject interrogative

34 Generation Process: structure +Finite Finite^Subject interrogative

35 Immediate Dominance Linear Precedence Generation Process: realization statements +Finite Finite^Subject SubjectFinite [clause] Are yougoing? [interrogative]

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

37 Functionally Motivated Grammatical Choices USER

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

39 Functionally Motivated Grammatical Choices USER Semantic Specifications

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


Download ppt "Text Language Technology Natural Language Understanding Natural Language Generation Speech Recognition Speech Synthesis Text Meaning Speech."

Similar presentations


Ads by Google