Learning word meanings Concept learning review Simple associations

  • Slides: 49
Download presentation
Learning word meanings

Learning word meanings

Concept learning review Simple associations not enough • Goal direction / determining tendency •

Concept learning review Simple associations not enough • Goal direction / determining tendency • Essences for some types of concept (“natural kinds”) • Defining features present early for some concepts (robber) • Characteristic defining for others (uncle)

Concept learning review ctd Concept of race Interaction of universal / innate part with

Concept learning review ctd Concept of race Interaction of universal / innate part with social learning A “developmental” approach

Concept learning review ctd But: • Simple associationism illuminates asymmetric category learning • Its

Concept learning review ctd But: • Simple associationism illuminates asymmetric category learning • Its failures highlight what remains to be explained • Its limitations don’t mean we can’t model concept learning

Overview of lecture A. The computational problem B. Constraints that might help C. Summary

Overview of lecture A. The computational problem B. Constraints that might help C. Summary

A. The computational problem 1. Quine’s rabbit 2. Searching a concept space 3. Winston’s

A. The computational problem 1. Quine’s rabbit 2. Searching a concept space 3. Winston’s arch

Gavagai

Gavagai

Inductive concept learning (eats-meat fluffy small red) (eats-meat fluffy big red) (eats-fruit fluffy small

Inductive concept learning (eats-meat fluffy small red) (eats-meat fluffy big red) (eats-fruit fluffy small red) (eats-fruit smooth small red) (eats-meat fluffy small red) + + What's the concept? (eats-meat fluffy small) Can a concept like this be learned automatically?

A search problem For a given number of attributes, a space can be defined

A search problem For a given number of attributes, a space can be defined of possible concepts (eats-meat) (eats-fruit) (fluffy) (eats-meat smooth) (eats-meat fluffy small) () (smooth). . . (eats-fruit fluffy). . . (eats-meat smooth small) . . . etc. Operators: generalisation & specialisation

Generalisation Cover more examples: drop an attribute from a concept First positive case initialises

Generalisation Cover more examples: drop an attribute from a concept First positive case initialises concept: (eats-meat fluffy small red) + (eats-meat fluffy small blue) + Generalise: (eats-meat fluffy small) This is a 'move in concept space'

Specialisation Cover fewer examples: add an attribute to a concept (eats-meat fluffy) + -

Specialisation Cover fewer examples: add an attribute to a concept (eats-meat fluffy) + - Specialise: try (eats-meat fluffy small) … a 'move in concept space'

Winston's arch learner

Winston's arch learner

B. Constraints that might help 1. General expectations 2. Cognitive constraints 3. Language form

B. Constraints that might help 1. General expectations 2. Cognitive constraints 3. Language form (syntax) constraints 4. Pragmatic constraints 5. World knowledge

Balaban & Waxman (1997) 9 month old children prediction - if child forms category

Balaban & Waxman (1997) 9 month old children prediction - if child forms category while viewing instance: 1. they get bored (habituate) 2. they'll show a novelty preference is the effect greater with naming? 9 rabbits then a pig and a rabbit More children showed pig preference (sig. ) with words than tones accompanying

Waxman & Markow (1995) novelty preference method 12 -13 mths - N or Adj

Waxman & Markow (1995) novelty preference method 12 -13 mths - N or Adj (novel word), or no label Train: 4 instances (eg. 4 animals) Test: choice of new instance, or non-member This one is an X This one is X-ish Look at this Novelty preference No novelty preference

Waxman & Markow ctd Words prompt (very young) children to form concepts A general

Waxman & Markow ctd Words prompt (very young) children to form concepts A general expectation about word forms The infants didn’t differentiate between the noun and adjective form However: Children with a high vocabulary facilitated superordinate but not basic level category formation Children with a low vocabulary neither clearly assisted

Booth & Waxman (2002) Stages 1 and 2: Training Stage 1 Familiarisation 4 novel

Booth & Waxman (2002) Stages 1 and 2: Training Stage 1 Familiarisation 4 novel objects with characteristic shape & colour This one is a dax, and this one, … Look what I can do with this one… [demo] Look at this one… Stage 2 Contrast

Booth & Waxman ctd Stage 3: Generalisation Forced choice between a new instance and

Booth & Waxman ctd Stage 3: Generalisation Forced choice between a new instance and a non-member Can you find me another one of these? At 14 mths, demo of function helps - because it focuses child on a relevant subset of properties

Cognitive constraints • • • Perceptual constraints eg. shape Constraints can be learned Ontological

Cognitive constraints • • • Perceptual constraints eg. shape Constraints can be learned Ontological constraint Taxonomic constraint Mutual exclusivity

Landau, Smith & Jones (1988) Is this a Dax? YES Does this one match?

Landau, Smith & Jones (1988) Is this a Dax? YES Does this one match? NO YES NO

Jones, Smith & Landau (1991) Trained example . 50 . 53 . 76 .

Jones, Smith & Landau (1991) Trained example . 50 . 53 . 76 . 48 . 82 . 80

Soja, Carey, & Spelke (1991) 2 yrs Novel object introduced, described, and handled My

Soja, Carey, & Spelke (1991) 2 yrs Novel object introduced, described, and handled My blicket, this blicket Then a forced choice: point to the blicket

Soja et al. ctd Object learned: another same shape different stuff or three little

Soja et al. ctd Object learned: another same shape different stuff or three little chunks same stuff Substance learned: another pile or slick the same shape, but different stuff or three blobs the same stuff

Soja et al. ctd If just ask to choose (no trained item, no word)

Soja et al. ctd If just ask to choose (no trained item, no word) responses were at chance = another same shape different stuff three little chunks same stuff and = another pile or slick the same shape, but different stuff three blobs the same stuff

Soja et al. ctd By 2 years Children know about the distinction between objects

Soja et al. ctd By 2 years Children know about the distinction between objects and substances And they use it to organise the generalisation of word meanings

Colunga & Smith (2003) Previously (Soja, Carey, & Spelke, 1991, Cognition, 38, pp 179

Colunga & Smith (2003) Previously (Soja, Carey, & Spelke, 1991, Cognition, 38, pp 179 -211) Children aged 24/30 months solid objects same shape non-solid objects same material But not at 18 months… Hypothesis: learn this pattern by association First 300 words Most denote solid objects, objects that have a consistent shape … and non-solid mostly denote substances i. e. child learns to apply this mapping pattern from associations present in first words learned

Colunga & Smith (2003) Output units [words] Hidden units […] Inputs Train: Test: ball

Colunga & Smith (2003) Output units [words] Hidden units […] Inputs Train: Test: ball [shape] [substance] [ball-shape] [random] [solid, not s. ] [1 0] novel shapes/materials Prediction - hidden unit activation patterns ("representations") will be similar for non-solid / same material or solid / same shape

Colunga & Smith (2003) Prediction - hidden unit activation patterns ("representations") will be similar

Colunga & Smith (2003) Prediction - hidden unit activation patterns ("representations") will be similar when non-solid and same material solid and same shape Testing Forced choice non-solid / same material solid / same shape Pick shape 30% 55%

Markman & Hutchinson (1984) Taxonomic constraint words refer to whole objects; of same type

Markman & Hutchinson (1984) Taxonomic constraint words refer to whole objects; of same type 3 -4 year old children Target picture eg. poodle Test pictures eg. alsation or dog food Give the puppet the one that’s the same. without label with label - prefer thematic prefer taxonomic

Markman & Wachtel (1988) mutual exclusivity constraint - two words don’t mean the same

Markman & Wachtel (1988) mutual exclusivity constraint - two words don’t mean the same thing Expt 1 (3 years old) Offer child choice of objects, one unfamiliar. Familiar object already has a name. Give me a merk Children tend to choose the novel object

Markman & Wachtel (1988) Expt 2 to check for response bias Present one object

Markman & Wachtel (1988) Expt 2 to check for response bias Present one object (with a salient part) FAMILIAR fish (fin) UNFAMILIAR microscope (platform) Which is the fripe, the whole thing or just this part? - What predictions do the constraints make? whole object constraint? mutual exclusivity? 20% chose part for unfamiliar object 57% chose part for familiar object

Syntactic constraints • General expectation differentiates into more specific, syntactically driven, expectations • Soja

Syntactic constraints • General expectation differentiates into more specific, syntactically driven, expectations • Soja • Language specificity

Syntax – a very brief intro! Word order indicates relationships among event participants The

Syntax – a very brief intro! Word order indicates relationships among event participants The boy kicked the dog Part of speech is indicated by word order function words, and morphology The boy function word (= closed class word) kicked kick morphology (changes word shape)

Syntax – brief intro ctd Word order indicates relationships among event participants Part of

Syntax – brief intro ctd Word order indicates relationships among event participants Part of speech is indicated by word order, function words, and morphology In some languages, morphology can do nearly all the work, and word order matters less (eg. Latin)

Waxman & Booth (2001; 2003) 1. Training on 4 purple animals, presented in 2

Waxman & Booth (2001; 2003) 1. Training on 4 purple animals, presented in 2 pairs (same colour, same category) 2. Contrast example orange carrot 3. Then test generalisation 11 mths 14 mths Nouns Category [new animal, purple; or purple plate] Property [new animal, purple; or new animal, blue] 0. 57 0. 55 0. 68 0. 44 Adjectives Category [new animal, purple; or purple plate] Property [new animal, purple; or new animal, blue] 0. 59 0. 58 0. 50 0. 52 No word Category [new animal, purple; or purple plate] Property [new animal, purple; or new animal, blue] 0. 46 0. 49 -

Soja, Carey, & Spelke (1991) 2 yrs Novel object introduced, described, and handled My

Soja, Carey, & Spelke (1991) 2 yrs Novel object introduced, described, and handled My blicket, this blicket Then a forced choice: point to the blicket

Soja et al. ctd Object learned: another same shape different stuff or three little

Soja et al. ctd Object learned: another same shape different stuff or three little chunks same stuff Substance learned: another pile or slick the same shape, but different stuff or three blobs the same stuff

Soja et al. ctd If just ask to choose (no trained item, no word)

Soja et al. ctd If just ask to choose (no trained item, no word) responses were at chance = another same shape different stuff three little chunks same stuff and = another pile or slick the same shape, but different stuff three blobs the same stuff

Soja et al. ctd By 2 years Children know about the distinction between objects

Soja et al. ctd By 2 years Children know about the distinction between objects and substances And they use it to organise the generalisation of word meanings

Soja et al. (1991) If the learned object was introduced with selective syntax a

Soja et al. (1991) If the learned object was introduced with selective syntax a blicket some blicket … it made no difference

Soja (1992) 2 and 2. 5 year olds who had mastered mass-count syntax in

Soja (1992) 2 and 2. 5 year olds who had mastered mass-count syntax in their speaking Were partly sensitive to syntax in word learning GENERALISES TO some [substance] a [substance] substance bounded pile

Language specificity English, Spanish - plural marks noun English - mass/count distinction draws attention

Language specificity English, Spanish - plural marks noun English - mass/count distinction draws attention to shape Korean - classifier language Experiment (3 -5 years; n = 16) novel word applied to an object: "fep", a magnet choice: cube of same substance wood block same shape English, Spanish - prefer shape similar Korean - prefer substance

Language specificity ctd But, classifiers highlight shape: Empitsu pencil Yonpil pencil o gohon kudasi

Language specificity ctd But, classifiers highlight shape: Empitsu pencil Yonpil pencil o gohon kudasi five long thin given tasot caru five long thin

Pragmatic influences Principle of contrast Clark (1993) - every difference of form marks difference

Pragmatic influences Principle of contrast Clark (1993) - every difference of form marks difference in meaning - economical for learning - a pragmatic principle -- used once understand speaker is intentional For Clark, contrast means any difference in meaning (including connotation, register & dialect). Identity of reference is not sufficient

Tomasello & Barton (1994) Dev. Psych 30 639 -650 2 years "Let's go find

Tomasello & Barton (1994) Dev. Psych 30 639 -650 2 years "Let's go find the toma" look in one of buckets (5) Either find it straight away or first find and reject two ("oh no", scowl, put back) then find the right thing

Akhtar & Tomasello (1996) 2 years Similar expt but one (distinctively shaped) bucket is

Akhtar & Tomasello (1996) 2 years Similar expt but one (distinctively shaped) bucket is shut and can't be opened Pre-play, so that child is familiar with the objects in each bucket (no naming) Put them back Adult - "Now, let's find the toma!" Adult expresses disappointment at no access, but plays with other objects Learned equally well whether no access or did retrieve

Role of world knowledge Schank, Collins & Hunter (1986) • Hijackings ® cuba generalisation?

Role of world knowledge Schank, Collins & Hunter (1986) • Hijackings ® cuba generalisation? ® cuba? • Hijacking ® libya syntactically, do what? drop destination as a dimension? or generalise feature content? e. g. warm country? Target concept - a model of how terrorists select destinations Which are relevant features has to be worked out often not perceptually available

C. Summary 1. Quine’s rabbit & the problem 2. Constraints guide search of the

C. Summary 1. Quine’s rabbit & the problem 2. Constraints guide search of the space 3. A variety of factors influence learning word meanings