1 / 40

Language Technology

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

luisa
Download Presentation

Language Technology

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

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

  2. Natural Language Understanding Speech Recognition Language Technology Meaning Natural Language Generation Text Text Speech Synthesis Speech 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. http://www.dfki.de/service/nlg-demo/ 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 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.

  10. 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/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. Document Planning Document Plan Standard Pipelined Architecture Microplanning Text Specification Surface Realisation

  14. Semantic specification TACTICAL GENERATOR KPML semantics lexicogrammar sentence

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

  16. Semantic specification TACTICAL GENERATION semantics lexicogrammar sentence

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

  33. Generation Process: structure interrogative Finite^Subject +Finite

  34. Generation Process: structure interrogative Finite^Subject +Finite

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

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

  37. USER Functionally Motivated Grammatical Choices

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

  39. USER Functionally Motivated Grammatical Choices Semantic Specifications

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

More Related