Learning word meanings

1
Learning word meanings

2
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)

3
Concept learning review ctd

• Concept of race
• Interaction of universal / innate part with
  social learning
• A developmental approach

4
Concept learning review ctd

• But
• Simple associationism illuminates asymmetric
  category learning
• Its failures highlight what remains to be
  explained
• Its limitations dont mean we cant model concept
  learning

5
Overview of lecture

1. The computational problem
2. Constraints that might help
3. Summary

6
A. The computational problem

• 1. Quines rabbit
• 2. Searching a concept space
• 3. Winstons arch

7

• Gavagai

8

• 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?

9

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

10

• 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'

11

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

12
Winston's arch learner

13
B. Constraints that might help

• 1. General expectations
• 2. Cognitive constraints
• 3. Language form (syntax) constraints
• 4. Pragmatic constraints
• 5. World knowledge

14
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

15
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 Novelty preference
• This one is X-ish Novelty preference
• Look at this No novelty preference

16
Waxman Markow ctd

• Words prompt (very young) children to form
  concepts
• A general expectation about word forms
• The infants didnt 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

17
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

18
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

19
Cognitive constraints

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

20
Landau, Smith Jones (1988)
Is this a Dax?
Does this one match?
NO
YES
NO
YES
21
Jones, Smith Landau (1991)
Trained example
.53
.50
.76
.48
.82
.80
22
Soja, Carey, Spelke (1991)

• 2 yrs
• Novel object introduced, described, and handled
• My blicket, this blicket
• Then a forced choice point to the blicket

23
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

24
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

25
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

26
Colunga Smith (2003)

• Previously
• (Soja, Carey, Spelke, 1991, Cognition, 38,
  pp179-211)
• 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

27
Colunga Smith (2003)

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

28
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 Pick shape
• non-solid / same material 30
• solid / same shape 55

29
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 thats the same.
• without label - prefer thematic
• with label - prefer taxonomic

30
Markman Wachtel (1988)

• mutual exclusivity constraint
• - two words dont 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

31
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

32
Syntactic constraints

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

33
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 morphology (changes word shape)

34
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)

35
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 0.57 0.68
• Property new animal, purple or new animal,
  blue 0.55 0.44
• Adjectives
• Category new animal, purple or purple
  plate 0.59 0.50
• Property new animal, purple or new animal,
  blue 0.58 0.52
• No word
• Category new animal, purple or purple
  plate 0.46 -
• Property new animal, purple or new animal,
  blue 0.49 -

36
Soja, Carey, Spelke (1991)

• 2 yrs
• Novel object introduced, described, and handled
• My blicket, this blicket
• Then a forced choice point to the blicket

37
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

38
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

39
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

40
Soja et al. (1991)

• If the learned object was introduced with
  selective syntax
• a blicket
• some blicket
• it made no difference

41
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 substance
• a substance bounded pile

42
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

43
Language specificity ctd

• But, classifiers highlight shape
• Empitsu o gohon kudasi
• pencil five long thin given
• Yonpil tasot caru
• pencil five long thin

44
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

45

• Tomasello Barton (1994) DevPsych 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

46

• 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

47
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

48
C. Summary

• 1. Quines rabbit the problem
• 2. Constraints guide search of the space
• 3. A variety of factors influence learning word
  meanings

49
(No Transcript)