communicat ion
play

Communicat ion J uly 14, 2005 CS 486/ 686 Universit y of Wat - PowerPoint PPT Presentation

Communicat ion J uly 14, 2005 CS 486/ 686 Universit y of Wat erloo Out line Communicat ion Symbolic Nat ural Language Processing Reading: R&N Sect . 22.1-22.6 2 CS486/686 Lecture Slides (c) 2005 P. Poupart Communicat ion


  1. Communicat ion J uly 14, 2005 CS 486/ 686 Universit y of Wat erloo

  2. Out line • Communicat ion • Symbolic Nat ural Language Processing • Reading: R&N Sect . 22.1-22.6 2 CS486/686 Lecture Slides (c) 2005 P. Poupart

  3. Communicat ion • Communicat ion: int ent ional exchange of inf ormat ion brought about by t he product ion and percept ion of signs drawn f rom shared syst em of convent ion. • Language: – Enables us t o communicat e – I nt imat ely t ied t o t hinking 3 CS486/686 Lecture Slides (c) 2005 P. Poupart

  4. Turing Test • Can a comput er f ool a human t o t hink t hat it is communicat ing wit h anot her human? 4 CS486/686 Lecture Slides (c) 2005 P. Poupart

  5. Speech • Speech: communicat ion act – Talking – Wr it ing ut t erances – Facial expression – Gest ure situation ut t erances Speaker Hearer 5 CS486/686 Lecture Slides (c) 2005 P. Poupart

  6. Component s of Communicat ion • I nt ent ion – Speaker S decides t hat t here is some proposit ion P wort h saying t o hearer H. • Generat ion – Speaker plans how t o t urn proposit ion P int o an ut t erance (i.e. a sequence of words W) • Synt hesis – Speaker produces t he physical realizat ion W’ of t he words W (i.e., vibrat ion in air, ink on paper) 6 CS486/686 Lecture Slides (c) 2005 P. Poupart

  7. Component s of Communicat ion • Percept ion – Hearer perceives physical realizat ion W’ as W 2 and decodes it as t he words W 2 (i.e., speech recognit ion, opt ical charact er recognit ion) • Analysis – Hearer inf ers W 2 has possible meanings P 1 , P 2 , … , P n – Three part s: • Synt act ic int erpret at ion • Semant ic int erpret at ion • Pragmat ic int erpret at ion 7 CS486/686 Lecture Slides (c) 2005 P. Poupart

  8. Component s of Communicat ion • Disambiguat ion – Hearer inf ers t hat speaker int ended t o convey P i (where ideally P i = P). • I ncorporat ion – Hearer decides t o believe P i (or not ). 8 CS486/686 Lecture Slides (c) 2005 P. Poupart

  9. Component s of Communicat ion SPEAKER Synthesis: Intention: Generation: [thaxwahmpaxsihzdehd] "The wumpus is dead" Know(H, Alive(Wumpus,S )) L 3 HEARER Perception: Analysis: Disambiguation: S (Parsing): "The wumpus is dead" Alive(Wumpus,S ) L NP VP 3 Article Noun Verb Adjective The wumpus is dead Incorporation: (Semantic Interpretation): Alive(Wumpus,Now) L Tired(Wumpus,Now) TELL( KB, Alive(Wumpus,S ) L 3 (Pragmatic Interpretation): Alive(Wumpus,S ) L 3 Tired(Wumpus,S ) 3 9 CS486/686 Lecture Slides (c) 2005 P. Poupart

  10. Dif f icult ies • How could communicat ion go wrong? – I nsincer it y – Speech recognit ion errors – Ambiguous ut t er ance – Dif f erent cont ext s 10 CS486/686 Lecture Slides (c) 2005 P. Poupart

  11. Language • Formal language – Set of st rings of t erminal symbols (words) – St rict rules – E.g., f irst order logic, J ava • Nat ural language – No st rict def init ion – Chinese, Danish, English, et c. 11 CS486/686 Lecture Slides (c) 2005 P. Poupart

  12. Grammar • Grammar specif ies t he composit ional st ruct ure of complex messages • Each st ring in a language can be analyzed/ generat ed by t he grammar • A grammar is a set of rewrit e rules – S � NP VP – Ar t icle � t he | a | an | … 12 CS486/686 Lecture Slides (c) 2005 P. Poupart

  13. Grammar Types • Regular grammar: – nont erminal � t erminal [nont erminal] – S � a S – S � b • Cont ext f ree grammar (CFG): – nont erminal � anyt hing – S � aSb 13 CS486/686 Lecture Slides (c) 2005 P. Poupart

  14. Grammar Types • Cont ext sensit ive grammar: – More t erminals on right -hand side – ASB � AAaBB • Recursively enumerable grammar: – No const raint s 14 CS486/686 Lecture Slides (c) 2005 P. Poupart

  15. Lexicon example • Noun � breeze | glitter | agent • Verb � is | see | smell | shoot • Adj ect ive � right | lef t | east | dead • Adverb � there | nearby | ahead • Pronoun � me | you | I | it • Name � John | Mary | Boston • Art icle � the | a | an 15 CS486/686 Lecture Slides (c) 2005 P. Poupart

  16. Grammar example • S � NP VP | S Conjunction S • NP � Pronoun | Name | Noun | Article Noun | NP PP | NP RelClause • VP � Verb | VP NP | VP Adjective | VP PP | VP Adverb • PP � � Preposition PP � � • RelClause � � that VP � � 16 CS486/686 Lecture Slides (c) 2005 P. Poupart

  17. Grammat icalit y J udgement s Set of strings Natural Grammar language agreement Goal: design grammar to match natural language 17 CS486/686 Lecture Slides (c) 2005 P. Poupart

  18. Grammat icalit y J udgement s • Overgenerat ion examples: – Me go Bost on. – I smell pit gold wumpus not hing east . • Undergenerat ion example: – I t hink t he wumpus is smelly 18 CS486/686 Lecture Slides (c) 2005 P. Poupart

  19. Synt act ic Analysis • Parsing: process of f inding a parse t ree f or a given input st ring S NP VP NP proposition noun pronoun verb I shoot the wumpus 19 CS486/686 Lecture Slides (c) 2005 P. Poupart

  20. Top-down parsing • St art wit h S and search f or a t ree t hat has st ring at leaves S NP VP NP proposition noun pronoun verb I shoot the wumpus 20 CS486/686 Lecture Slides (c) 2005 P. Poupart

  21. Bot t om up parsing • St art wit h st ring and search f or a t ree t hat has S as root S NP VP NP proposition noun pronoun verb I shoot the wumpus 21 CS486/686 Lecture Slides (c) 2005 P. Poupart

  22. Parsing ef f iciency • Top-down and bot t om up parsing inef f icient … – Exponent ial running t ime • Alt ernat ive: chart parsing – Dynamic progr amming – Cubic running t ime 22 CS486/686 Lecture Slides (c) 2005 P. Poupart

  23. Augment ed Grammars • Grammars t end t o overgenerat e – Ex: “me eat apple” • Augment grammar t o require – Agreement bet ween subj ect and verb • Ex: “I smells” vs “I smell” – Agreement bet ween verb subcat egory and complement • Ex: “give t he gold t o me” • Ex: “give me t he gold” 23 CS486/686 Lecture Slides (c) 2005 P. Poupart

  24. Parse ambiguit y • Some sent ences have many grammat ical parses • Example: – “Fall leaves f all and spring leaves spring” 24 CS486/686 Lecture Slides (c) 2005 P. Poupart

  25. Semant ic I nt erpret at ion • Ext ract meaning f rom ut t erances • Tradit ional approach – Express meaning wit h logic • Problem – Ambiguous semant ics – Ex: “Helicopt er powered by human f lies” 25 CS486/686 Lecture Slides (c) 2005 P. Poupart

  26. Ambiguit y • Possible causes: – Met onymy: f igure of speech in which one obj ect is used t o st and f or anot her – Met aphor: f igure of speech in which a phrase wit h one lit eral meaning is used t o suggest a dif f erent meaning by analogy – Vagueness – Unknown cont ext 26 CS486/686 Lecture Slides (c) 2005 P. Poupart

  27. Cont ext / Experience • Meaning of t en grounded in experience • But humans and machines have dif f erent experiences because of dif f erent sensors… • I s t hat a problem f or nat ural language underst anding? 27 CS486/686 Lecture Slides (c) 2005 P. Poupart

  28. Next Class • Next Class: •Probabilist ic Language Processing •Russell and Norvig Ch. 23 28 CS486/686 Lecture Slides (c) 2005 P. Poupart

Recommend


More recommend