Presentation is loading. Please wait.

Presentation is loading. Please wait.

Human Language...human brains, have been armed by habits and methods, mind-tools and information, drawn from millions of other brains which are not ancestral.

Similar presentations


Presentation on theme: "Human Language...human brains, have been armed by habits and methods, mind-tools and information, drawn from millions of other brains which are not ancestral."— Presentation transcript:

1 Human Language...human brains, have been armed by habits and methods, mind-tools and information, drawn from millions of other brains which are not ancestral to [them]....Comparing our brains anatomically with [any other non- human brains] would be almost beside the point, because our brains are in effect joined together into a single cognitive system that dwarfs all others. They are joined by an innovation that has invaded our brains and no others: language. [Dennett, D. 1995. p.381]

2 human language development a quick overview

3 evolutionary timelines primates http://www.archaeologyinfo.com/species.htm general timeline http://andabien.com/html/evolution-timeline.htm

4 human language & pre-history 50-35kyr ago technological & cultural change symbolism semantically & syntactically rich Ln by 35kyr (probably much earlier)

5 human physiology for language brain function... Universal Human Grammar and innate language organ [Chomsky, N. 1986 & others] Language Acquisition Device [Searle, J. 1992. & others]. hard-wired overlaps general learning and imprinting mechanisms builds syntactic, semantic and word meaning knowledge into cognitive substrates physiologically housed in some (possibly distributed) language organ.

6 human physiology for language speech... discrete, digital system using limited set of phonemes approx 40 phonemes for English some make big deal of low human larynx position allows a diverse set of phonemes but: choking; infant larynx; developed 2myr-300kyr and: aquatic apes, minor birds, !Kung & Khosa

7 human physiology for language speech perception... normal speech 10-15 phonemes / sec phonemes smear into each other listeners can perceive upto 45 phonemes/sec (though brain probably hypothesises some) NB: Morse code operators only recognise 3 tokens/second clicks repeated 15-20 times/sec is heard as a buzz.

8 selection pressures ie: why language evolved issue highly colored by contemporary social beliefs. NB: social traits, behavioural patterns and cognitive functionality appear different to simple evolutionary forms but subject to the same evolutionary mechanisms

9 task related SPs toolmaker "Man the Toolmaker" [K. Oakley in 1949] agriculturalist hunter gatherer defence: man the warmonger

10 socially driven Darwinian signal-evolution theory invites us to abandon traditional assumptions about honest communication and instead ask questions about competition and co-operation, selfishness versus altruism, manipulation as opposed to communication. [Knight, C. 1998b]...primate intelligence - including our own - originally evolved to solve the challenges of interacting with one another. [Cheney et al 1986] an individual is most in competition with others from its own species, from the same social group: the extended clan, smaller coalitions, even its family [Ridley, M. 1993]

11 socially driven deceit & negotiation interesting primate activity is often concerned with conflicting goals in a social setting. deception requires a Theory of Mind - enhanced by means of communication referring to spatially/temporally distant actions/events. peer pressure & politics chatter replaces grooming, evolves to contain socially relevant infm & leads to emergence of structure/grammar gender differences & female co-operation pregnancy, childbirth & infant parenting (midwifery & bipedalism) controversial gender differences in use & development of Ln leads to sexual selection for language various other evidence supports social foundation

12 other issues adaptation or exaptation the Baldwin effect memetics

13 Computerised Natural Language Processing (a semantic approach) a quick overview

14 Natural Language Processing what it does what is involved why is it difficult brief history

15 sentence  structured rep n s of meaning "how old is my help3.doc file?" Lisp: (query (file-detail 'date "C:/help3.doc")) "the large cat chased the rat" Logic: (  1 s 1  large(s 1 )  feline(s 1 ))  (  1 s 2  rodent(s 2 ))  chased(s 1, s 2 ) "the young boy ate a bad apple" CD Graph...see next page...

16 CD graph "the young boy ate a bad apple"

17 what is involved either (a semantic approach)... symbolic computation ie: symbols manipulated by symbol processors search & inference knowledge representation techniques or... statistical techniques & machine learning

18 prejudice, politics, etc ambiguity... syntactic semantic pragmatic why is it difficult

19 example sentences the old man the boats my car drinks petrol I saw the Eiffel Tower flying to Paris he opened the door with the key he opened the door with the squeaking hinge the boy kicked the ball under the tree the boy kicked the wall under the tree put the bottles in the box on the shelf by the door

20 1950sRussian  English translation 1956Chomsky 1960sPattern matching 1970sParsing & some KnRep 1980sKn & inference 1990sbig dreams small results 2000s+divergent strategies (i)continuing work with semantics (ii)much greater use of stats/machine learning - origins in late 80s? (brief) history of language processing

21 matching: Sir

22 matching: Student

23 matching: Elisa

24 a modern semantic approach input sentence syntax analysis (parsing) semantic analysis pragmatic analysis target representation grammar lexicon semantic rules contextual information morphological processing

25 step 1- morphological processing objective: strip words into roots & modifiers issues inflection(cat pl  cat-s) derivation(happy adj  happiness noun) compounding(toothpaste)

26 morphological processing - notes all(?) spoken lngs exhibit morphology easier to handle in written lngs if not iconic some morphology describes infm beyond syntax eg:proximity(Tamil, Setswana, etc) case speaker / listener peer relationship

27 morphology examples

28 step 2- syntax analysis objectives:1check for correctness 2produce phrase structure uses parsera rule-based search engine grammarcontext-free production rules lexicondictionary of words & their categories

29 syntax rules parts of speech rules of combination consider the cat chases the mouse all large black dogs chase cats

30 example 1 - using Lkit (build-lexicon '((a determiner) (cat noun) (dog noun) (the determiner) (chased verb))) (build-grammar '((s1 (sentence -> noun-phrase verb-phrase)) (np (noun-phrase -> determiner noun)) (vp (verb-phrase -> verb noun-phrase)) ))

31 example 1 - output (parse 'sentence '(the dog chased a cat)) complete-edge 0 5 s1 sentence (the dog...) nil s1 sentence -> (noun-phrase verb-phrase) Syntax (sentence (noun-phrase (determiner the) (noun dog)) (verb-phrase (verb chased) (noun-phrase (determiner a) (noun cat)))) Semantics (sentence)

32 so what ? we want meaning

33 Remember: "the young boy ate a bad apple" how can semantics be encoded as symbols? the boy / an apple? young/old, happy/sad, good/bad? how can semantics be generated? what can be inferred from semantics?

34 Reminder: "the young boy ate a bad apple"

35 symbolic representation of semantics (actor (root boy) (id boy#732) (tags animate human male) (qual (age (val 5) (approx 3))) (quant specific)) (action (primitve INGEST)) (object (root apple) (id nil) (tags physob veg fruit food) (qual (phy-state -4)) (quant non-specific))

36 semantics in lexicon a simple example (build-lexicon '((a det any ) (cat noun feline ) (chased verb hunts ) (dog noun canine ) (the det specific) ))

37 semantics in grammar rules (s1 (sentence -> noun-phrase verb-phrase) (actor. noun-phrase) (action. verb-phrase.action) (object. verb-phrase.object) ) (np (noun-phrase -> det noun) (det. noun) ) (vp (verb-phrase -> verb noun-phrase) (action. verb) (object. noun-phrase) )

38 semantics - results (parse 'sentence '(the dog chased a cat)) complete-edge 0 5 s1 sentence (the dog...) nil s1 sentence -> (noun-phrase verb-phrase) Syntax (sentence (noun-phrase (det the) (noun dog)) (verb-phrase (verb chased) (noun-phrase (det a) (noun cat)))) Semantics (sentence (actor (specific canine)) (action hunts) (object (any feline)))

39 semantics in lexicon - checks 1 (a det (sems. any)) (all det (sems. every)) (cat noun (sems. feline) (num. sing)) (cats noun (sems. feline) (num. plur)) (chase verb (sems. hunts) (num. plur)) (chases verb (sems. hunts) (num. sing)) (dog noun (sems. canine) (num. sing)) (dogs noun (sems. canine) (num. plur)) (the det (sems. specific))

40 semantics in grammar - checks 1 (s1 (sentence -> noun-phrase verb-phrase) (actor. noun-phrase.sems) (action. verb-phrase.action) (object. verb-phrase.object) ; check number of noun-phrase & verb-phrase (if (noun-phrase.number = verb- phrase.number) numeric-agreement-ok numeric-agreement-bad )

41 semantics - results (parse 'sentence '(the dog chases a cat)) complete-edge 0 5 s1 sentence (the dog...) nil s1 sentence -> (noun-phrase verb-phrase) Syntax (sentence (noun-phrase (det the) (noun dog)) (verb-phrase (verb chases) (noun-phrase (det a) (noun cat)))) Semantics (sentence (actor specific canine) (action. hunts) (object any feline) numeric-agreement-ok)

42 semantics - results (parse 'sentence '(the dogs chases a cat)) complete-edge 0 5 s1 sentence (the dog...) nil s1 sentence -> (noun-phrase verb-phrase) Syntax (sentence (noun-phrase (det the) (noun dog)) (verb-phrase (verb chases) (noun-phrase (det a) (noun cat)))) Semantics (sentence (actor specific canine) (action. hunts) (object any feline) numeric-agreement-bad)

43 semantics in grammar - checks 2 (s1 (sentence -> noun-phrase verb-phrase) (fail if noun-phrase.number /= verb-phrase.number) (actor. noun-phrase.sems) (action. verb-phrase.action) (object. verb-phrase.object) )

44 semantics - results (parse 'sentence '(the dog chases a cat)) Semantics (sentence (actor specific canine) (action. hunts) (object any feline)) (parse 'sentence '(the dogs chases a cat)).... failed....

45 semantics in grammar - checks 3 (s1 (sentence -> noun-phrase verb-phrase) (glitch numeric-agreement if not noun-phrase.number = verb-phrase.number) (actor. noun-phrase.sems) (action. verb-phrase.action) (object. verb-phrase.object) )

46 semantics - results (parse 'sentence '(the dogs chases a cat)) complete-edge 0 5 s1 sentence (the dogs...) nil Glitches: (numeric-agreement) s1 sentence -> (noun-phrase verb-phrase) Syntax (sentence (noun-phrase (det the) (noun dogs)) (verb-phrase (verb chases) (noun-phrase (det a) (noun cat)))) Semantics (sentence (actor specific canine) (action. hunts) (object any feline))

47 example 2 - lexicon (a det any ) (cat noun feline ) (chase verb hunts ) (dog noun canine ) (the det specific) (black adj (color black)) (large adj (size 7/10)) (small adj (size 3/10))

48 example 2 - grammar (build-grammar '((np (noun-phrase -> ?det *adj noun) (if det (quantification. det) (quantification undefined)) (qualifiers. *.adj) (object. noun) ))

49 example 2 - results (parse 'noun-phrase '(small black dog)) complete-edge 0 3 np noun-phrase (small...) nil np noun-phrase -> (?det *adj noun) Syntax (noun-phrase (adj small) (adj black) (noun dog)) Semantics (noun-phrase (quantification undefined) (qualifiers ((size. 3/10)) ((color. black))) (object canine))

50 example 2 - results small dogs chase the small cats and large dogs chase the large cats (sentence conjunction ((actor (quant undefined) (qual (size. 3/10)) (object. canine)) (action. hunts) (object (quant. specific) (qual (size. 3/10)) (object. feline))) ((actor (quant undefined) (qual (size. 7/10)) (object. canine)) (action. hunts) (object (quant. specific) (qual (size. 7/10)) (object. feline))))

51 semantic processing (one approach) semantic rules in grammar  1st stage case frame verb form  primitive action case frame disambiguate & fill additional case frame slots check references with world and/or dialog do statement level inference integrate with dialog do event sequence dialog

52 step-1: produce raw case frame verb cases the cat chased the rat in the kitchen the cat chased the rat into the kitchen common cases sourcestart-timeinstrument destinationend-timebeneficiary locationduration

53 the ambiguity problem eg: the boy kicked the ball under the tree grammar rules S  S PP S  NP VP NP  ?det *adj noun NP  NP PP

54 example frame #1 actor (quant specific) (tags animate male human) (qual (age (range 3 13))) (root boy) action (root kick) object (root ball) (tags manip) (posn-relative (locator beneath) (object (root tree)...etc... )

55 example frame #2 actor (quant specific) (tags animate male human) (qual (age (range 3 13))) (root boy) action (root kick) object (root ball) (tags manip) dest (posn-relative (locator beneath) (object (root tree)...etc... )

56 example verb form #1 primitive strike prohibited object (tags manip) slots instrument (part-of $actor foot) legal start-time, end-time, duration instrument, beneficiary, location illegal source, dest

57 example verb form #2 primitive push required object (tags manip) slots instrument (part-of $actor foot) legal source, dest, start-time, end-time, instr, beneficiary, locatn, duration

58 semantic processing (one approach) ×semantic rules in grammar  1st stage case frame ×verb form  primitive action case frame ×disambiguate & fill additional case frame slots Þcheck references with world and/or dialog Þdo statement level inference integrate with dialog do event sequence dialog

59 integration with dialog dialogs have... players (actors) props (objects) locations (from case frames) themes (derived) event sequences (from themes) plans (from themes and/or derived)

60 event sequence set of... players (actors) props (objects) series of... semantically encoded activities (matched) escapes, exceptions & alternatives


Download ppt "Human Language...human brains, have been armed by habits and methods, mind-tools and information, drawn from millions of other brains which are not ancestral."

Similar presentations


Ads by Google