Constructing grammar a computational model of the acquisition of early constructions l.jpg
This presentation is the property of its rightful owner.
Sponsored Links
1 / 42

Constructing Grammar: a computational model of the acquisition of early constructions PowerPoint PPT Presentation


  • 117 Views
  • Uploaded on
  • Presentation posted in: General

Constructing Grammar: a computational model of the acquisition of early constructions. CS 182 Lecture April 25, 2006. What constitutes learning a language?. What are the sounds (Phonology) How to make words (Morphology) What do words mean (Semantics)

Download Presentation

Constructing Grammar: a computational model of the acquisition of early constructions

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.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Constructing grammar a computational model of the acquisition of early constructions l.jpg

Constructing Grammar:a computational modelof the acquisition of early constructions

CS 182 Lecture

April 25, 2006


What constitutes learning a language l.jpg

What constitutes learning a language?

  • What are the sounds (Phonology)

  • How to make words (Morphology)

  • What do words mean (Semantics)

  • How to put words together (Syntax)

  • Social use of language (Pragmatics)

  • Rules of conversations (Pragmatics)


Slide3 l.jpg

What do we know about language development?

(focusing mainly on first language acquisition of English-speaking, normal population)


Children are amazing learners l.jpg

0 mos

6 mos

12 mos

2 yr

3 yrs

4 yrs

5 yrs

Children are amazing learners

cooing

first word

reduplicated babbling

two-word combinations

multi-word utterances

questions, complex sentence structures, conversational principles


Phonology non native contrasts l.jpg

Phonology: Non-native contrasts

  • Werker and Tees (1984)

  • Thompson: velar vs. uvular, /`ki/-/`qi/.

  • Hindi: retroflex vs. dental, /t.a/-/ta/


Finding words statistical learning l.jpg

pretty baby

Finding words: Statistical learning

  • Saffran, Aslin and Newport (1996)

  • /bidaku/, /padoti/, /golabu/

  • /bidakupadotigolabubidaku/

  • 2 minutes of this continuous speech stream

  • By 8 months infants detect the words (vs non-words and part-words)


Word order agent and patient l.jpg

Hirsch-Pasek and Golinkoff (1996)

1;4-1;7

mostly still in the one-word stage

Where is CM tickling BB?

Word order: agent and patient


Early syntax l.jpg

Early syntax

  • agent + action‘Daddy sit’

  • action + object‘drive car’

  • agent + object‘Mommy sock’

  • action + location‘sit chair’

  • entity + location‘toy floor’

  • possessor + possessed‘my teddy’

  • entity + attribute‘crayon big’

  • demonstrative + entity‘this telephone’


From single words to complex utterances l.jpg

From Single Words To Complex Utterances

FATHER:Nomi are you climbing up the books?

NAOMI:up.

NAOMI:climbing.

NAOMI:books.

1;11.3

FATHER:what’s the boy doing to the dog?

NAOMI:squeezing his neck.

NAOMI:and the dog climbed up the tree.

NAOMI:now they’re both safe.

NAOMI:but he can climb trees.

4;9.3

MOTHER:what are you doing?

NAOMI:I climbing up.

MOTHER:you’re climbing up?

2;0.18

Sachs corpus (CHILDES)


How can children be so good at learning language l.jpg

Gold’s Theorem:

No superfinite class of language is identifiable in the limit from positive data only

Principles & Parameters

Babies are born as blank slates but acquire language quickly (with noisy input and little correction) → Language must be innate:

Universal Grammar + parameter setting

But babies aren’t born as blank slates!

And they do not learn language in a vacuum!

How Can Children Be So Good At Learning Language?


Slide11 l.jpg

Modeling the acquisition of grammar:

Theoretical assumptions


Language acquisition l.jpg

Language Acquisition

  • Opulence of the substrate

    • Prelinguistic children already have rich sensorimotor representations and sophisticated social knowledge

    • intention inference, reference resolution

    • language-specific event conceptualizations

      (Bloom 2000, Tomasello 1995, Bowerman & Choi, Slobin, et al.)

  • Children are sensitive to statistical information

    • Phonological transitional probabilities

    • Even dependencies between non-adjacent items

      (Saffran et al. 1996, Gomez 2002)


Language acquisition13 l.jpg

throw frisbee

get ball

this should be reminiscent of your model merging assignment

throw ball

get bottle

get OBJECT

throw OBJECT

Language Acquisition

  • Basic Scenes

    • Simple clause constructions are associated directly with scenes basic to human experience

      (Goldberg 1995, Slobin 1985)

  • Verb Island Hypothesis

    • Children learn their earliest constructions (arguments, syntactic marking) on a verb-specific basis

      (Tomasello 1992)


Slide14 l.jpg

Comprehensionispartial.

(not just for dogs)


What children pick up from what they hear l.jpg

What children pick up from what they hear

  • Children use rich situational context / cues to fill in the gaps

  • They also have at their disposal embodied knowledge and statistical correlations (i.e. experience)

what did you throw it into?

they’re throwing this in here.

they’re throwing a ball.

don’t throw it Nomi.

well you really shouldn’t throw things Nomi you know.

remember how we told you you shouldn’t throw things.

what did you throw it into?

they’re throwing this inhere.

they’re throwing a ball.

don’t throw it Nomi.

wellyou really shouldn’t throw things Nomi you know.

remember how we told you you shouldn’t throw things.


Language learning hypothesis l.jpg

Language Learning Hypothesis

Children learn constructionsthat bridge the gap between

what they know from language

and

what they know from the rest of cognition


Slide17 l.jpg

Modeling the acquisition of (early) grammar:

Comprehension-driven, usage-based


Embodied construction grammar bergen and chang 2005 l.jpg

Embodied Construction Grammar (Bergen and Chang 2005)

construction THROWER-THROW-OBJECT

constructional

constituents

t1 : REF-EXPRESSION

t2 : THROW

t3 : OBJECT-REF

form

t1f before t2f

t2f before t3f

meaning

t2m.thrower ↔t1m

t2m.throwee ↔t3m

role-filler bindings


Analyzing you throw the ball l.jpg

Analyzing “You Throw The Ball”

MEANING (stuff)

FORM (sound)

Thrower-Throw-Object

t1 before t2

t2 before t3

t2.thrower ↔ t1

t2.throwee ↔ t3

schema Addressee

subcase of Human

Addressee

you

“you”

Throw

thrower

throwee

schema Throw

roles:

thrower

throwee

throw

“throw”

“the”

Ball

schema Ball

subcase of Object

ball

“ball”

schema Block

subcase of Object

“block”

block


Learning analysis cycle chang 2004 l.jpg

1.Learner passes input (Utterance + Situation) and current grammar to Analyzer.

Constructions

(Utterance, Situation)

2.Analyzer produces SemSpec and Constructional Analysis.

Analyze

Hypothesize

Semantic Specification,Constructional Analysis

Learning-Analysis Cycle (Chang, 2004)

Reorganize

  • Learner updates grammar:

a.Hypothesize new map.

b.Reorganize grammar (merge or compose).

c.Reinforce(based on usage).


Slide21 l.jpg

Hypothesizing a new construction

through

relational mapping


Initial single word stage l.jpg

Initial Single-Word Stage

lexical constructions

MEANING (stuff)

FORM (sound)

schema Addressee

subcase of Human

“you”

you

schema Throw

roles:

thrower

throwee

throw

“throw”

ball

“ball”

schema Ball

subcase of Object

schema Block

subcase of Object

block

“block”


New data you throw the ball l.jpg

throw-ball

role-filler

before

New Data: “You Throw The Ball”

FORM

MEANING

SITUATION

Self

schema Addressee

subcase of Human

you

Addressee

Addressee

“you”

schema Throw

roles:

thrower

throwee

Throw

thrower

throwee

Throw

thrower

throwee

throw

“throw”

“the”

schema Ball

subcase of Object

ball

Ball

Ball

“ball”

schema Block

subcase of Object

“block”

block


New construction hypothesized l.jpg

New Construction Hypothesized

construction THROW-BALL

constructional

constituents

t : THROW

b : BALL

form

tf before bf

meaning

tm.throwee ↔ bm


Three kinds of meaning relations l.jpg

Three kinds of meaning relations

  • When B.m fills a role of A.m

  • When A.m and B.m are both filled by X

  • When A.m and B.m both fill roles of X

throwballthrow.throwee ↔ ball

put ball downput.mover ↔ balldown.tr↔ ball

Nomiballpossession.possessor ↔ Nomipossession.possessed ↔ ball


Slide26 l.jpg

Reorganizing the current grammar

through

merge and compose


Merging similar constructions l.jpg

throw the block

THROW-OBJECT

THROW.throwee = Objectm

throw before Objectf

throw-ing the ball

Merging Similar Constructions

Throw.throwee = Block

throw before block

throw before ball

Throw.throwee = Ball

Throw.aspect = ongoing

throw before-s ing


Resulting construction l.jpg

Resulting Construction

construction THROW-OBJECT

constructional

constituents

t : THROW

o : OBJECT

form

tf before of

meaning

tm.throwee ↔ om


Composing co occurring constructions l.jpg

throw the ball

Throw.throwee = Ball

throw before ball

THROW.throwee = Ball

Motion m

m.mover = Ball

m.path = Off

THROW-BALL-OFF

throw before ball

ball before off

Motion m

m.mover = Ball

m.path = Off

ball before off

ball off

Composing Co-occurring Constructions


Resulting construction30 l.jpg

Resulting Construction

construction THROW-BALL-OFF

constructional

constituents

t : THROW

b : BALL

o : OFF

form

tf before bf

bf before of

meaning

evokes MOTION as m

tm.throwee ↔ bm

m.mover ↔ bm

m.path ↔ om


Slide31 l.jpg

Precisely defining the learning algorithm


Language learning problem l.jpg

Language Learning Problem

  • Prior knowledge

    • Initial grammar G (set of ECG constructions)

    • Ontology (category relations)

    • Language comprehension model (analysis/resolution)

  • Hypothesis space: new ECG grammar G’

    • Search = processes for proposing new constructions

    • Relational Mapping, Merge, Compose


Language learning problem33 l.jpg

Language Learning Problem

  • Performance measure

    • Goal: Comprehension should improve with training

    • Criterion: need some objective function to guide learning…

Probability of Model given Data:

Minimum Description Length:


Minimum description length l.jpg

Minimum Description Length

  • Choose grammar G to minimize cost(G|D):

    • cost(G|D) = α • size(G) + β • complexity(D|G)

    • Approximates Bayesian learning; cost(G|D) ≈ posterior probability P(G|D)

  • Size of grammar = size(G) ≈ prior P(G)

    • favor fewer/smaller constructions/roles; isomorphic mappings

  • Complexity of data given grammar ≈ likelihood P(D|G)

    • favor simpler analyses(fewer, more likely constructions)

    • based on derivation length + score of derivation


Size of grammar l.jpg

Size Of Grammar

  • Size of the grammar G is the sum of the size of each construction:

  • Size of each construction c is:

    where

    • nc = number of constituents in c,

    • mc = number of constraints in c,

    • length(e) = slot chain length of element reference e


Example the throw ball cxn l.jpg

Example: The Throw-Ball Cxn

construction THROW-BALL

constructional

constituents

t : THROW

b : BALL

form

tf before bf

meaning

tm.throwee ↔ bm

size(THROW-BALL)

= 2 + 2 + (2 + 3) = 9


Complexity of data given grammar l.jpg

Complexity of Data Given Grammar

  • Complexity of the data D given grammar G is the sum of the analysis score of each input token d:

  • Analysis score of each input token d is:

    where

    • c is a construction used in the analysis of d

    • weightc ≈ relative frequency of c,

    • |typer| = number of ontology items of type r used,

    • heightd= height of the derivation graph,

    • semfitd= semantic fit provide by the analyzer


Slide38 l.jpg

Preliminary Results


Experiment learning verb islands l.jpg

Experiment: Learning Verb Islands

  • Subset of the CHILDES database of parent-child interactions (MacWhinney 1991; Slobin et al.)

  • coded by developmental psychologists for

    • form: particles, deictics, pronouns, locative phrases, etc.

    • meaning: temporality, person, pragmatic function,type of motion (self-movement vs. caused movement; animate being vs. inanimate object, etc.)

  • crosslinguistic (English, French, Italian, Spanish)

    • English motion utterances: 829 parent, 690 child utterances

    • English all utterances: 3160 adult, 5408 child

    • age span is 1;2 to 2;6


Learning throw constructions l.jpg

Learning Throw-Constructions


Learning results l.jpg

Learning Results


Summary l.jpg

Summary

  • Cognitively plausible situated learning processes

  • What do kids start with?

    • perceptual, motor, social, world knowledge

    • meanings of single words

  • What kind of input drives acquisition?

    • Social-pragmatic knowledge

    • Statistical properties of linguistic input

  • What is the learning loop?

    • Use existing linguistic knowledge to analyze input

    • Use social-pragmatic knowledge to understand situation

    • Hypothesize new constructions to bridge the gap


  • Login