Constructing Grammar: a computational model of the acquisition of early constructions CS 182 Lecture April 25, 2006

2 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)

3 What do we know about language development? (focusing mainly on first language acquisition of English-speaking, normal population)

4 Children are amazing learners cooing reduplicated babbling first word 0 mos2 yr6 mos3 yrs4 yrs5 yrs12 mos two-word combinationsmulti-word utterances questions, complex sentence structures, conversational principles

5 Phonology: Non-native contrasts Werker and Tees (1984) Thompson: velar vs. uvular, /`ki/-/`qi/. Hindi: retroflex vs. dental, /t.a/-/ta/

6 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) pretty baby

7 Word order: agent and patient Hirsch-Pasek and Golinkoff (1996) 1;4-1;7 mostly still in the one-word stage Where is CM tickling BB?

8 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’

9 MOTHER:what are you doing? NAOMI:I climbing up. MOTHER:you’re climbing up? 2;0.18 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 FATHER:Nomi are you climbing up the books? NAOMI:up. NAOMI:climbing. NAOMI:books. 1;11.3 Sachs corpus (CHILDES) From Single Words To Complex Utterances

10 How Can Children Be So Good At Learning Language? 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!

11 Modeling the acquisition of grammar: Theoretical assumptions

12 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)

13 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) get ball get bottle get OBJECT … throw frisbee throw ball throw OBJECT … this should be reminiscent of your model merging assignment

14 Comprehension is partial. (not just for dogs)

15 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 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.

16 Language Learning Hypothesis Children learn constructions that bridge the gap between what they know from language and what they know from the rest of cognition

17 Modeling the acquisition of (early) grammar: Comprehension-driven, usage-based

18 Embodied Construction Grammar (Bergen and Chang 2005) construction T HROWER -T HROW -O BJECT constructional constituents t1 : R EF- E XPRESSION t2 : T HROW t3 : O BJECT -R EF form t1 f before t2 f t2 f before t3 f meaning t2 m.thrower ↔ t1 m t2 m.throwee ↔ t3 m role-filler bindings

19 “you” you schema Addressee subcase of Human FORM (sound) MEANING (stuff) Analyzing “You Throw The Ball” “throw” throw schema Throw roles: thrower throwee “ball” ball schema Ball subcase of Object “block” block schema Block subcase of Object t1 before t2 t2 before t3 Thrower- Throw-Object t2.thrower ↔ t1 t2.throwee ↔ t3 “the” Addressee Throw thrower throwee Ball

20 Constructions (Utterance, Situation) 1.Learner passes input (Utterance + Situation) and current grammar to Analyzer. Analyze Semantic Specification, Constructional Analysis 2.Analyzer produces SemSpec and Constructional Analysis. 3.Learner updates grammar: Hypothesize a.Hypothesize new map. Reorganize b.Reorganize grammar (merge or compose). c.Reinforce (based on usage). Learning-Analysis Cycle (Chang, 2004)

21 Hypothesizing a new construction through relational mapping

22 “you” “throw” “ball” you throw ball “block” block schema Addressee subcase of Human FORM (sound) MEANING (stuff) lexical constructions Initial Single-Word Stage schema Throw roles: thrower throwee schema Ball subcase of Object schema Block subcase of Object

23 “you” you schema Addressee subcase of Human FORMMEANING New Data: “You Throw The Ball” “throw” throw schema Throw roles: thrower throwee “ball” ball schema Ball subcase of Object “block” block schema Block subcase of Object “the” Addressee Throw thrower throwee Ball Self SITUATION Addressee Throw thrower throwee Ball before role-filler throw-ball

24 New Construction Hypothesized construction THROW-BALL constructional constituents t : THROW b : BALL form t f before b f meaning t m.throwee ↔ b m

25 Three kinds of meaning relations 1. When B.m fills a role of A.m 2. When A.m and B.m are both filled by X 3. When A.m and B.m both fill roles of X throw ball throw.throwee ↔ ball put ball down put.mover ↔ ball down.tr ↔ ball Nomi ball possession.possessor ↔ Nomi possession.possessed ↔ ball

26 Reorganizing the current grammar through merge and compose

27 Merging Similar Constructions throw before block Throw.throwee = Block throw before ball Throw.throwee = Ball throw before-s ing Throw.aspect = ongoing throw-ing the ball throw the block throw before Object f THROW.throwee = Object m THROW- OBJECT

28 Resulting Construction construction THROW-OBJECT constructional constituents t : THROW o : OBJECT form t f before o f meaning t m.throwee ↔ o m

29 Composing Co-occurring Constructions ball before off Motion m m.mover = Ball m.path = Off ball off throw before ball Throw.throwee = Ball throw the ball throw before ball ball before off THROW.throwee = Ball Motion m m.mover = Ball m.path = Off THROW- BALL- OFF

30 Resulting Construction construction THROW-BALL-OFF constructional constituents t : THROW b : BALL o : OFF form t f before b f b f before o f meaning evokes MOTION as m t m.throwee ↔ b m m.mover ↔ b m m.path ↔ o m

31 Precisely defining the learning algorithm

32 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

33 Language Learning Problem Performance measure Goal: Comprehension should improve with training Criterion: need some objective function to guide learning… Minimum Description Length: Probability of Model given Data:

34 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

35 Size Of Grammar Size of the grammar G is the sum of the size of each construction: Size of each construction c is: where n c = number of constituents in c, m c = number of constraints in c, length(e) = slot chain length of element reference e

36 Example: The Throw-Ball Cxn construction THROW-BALL constructional constituents t : THROW b : BALL form t f before b f meaning t m.throwee ↔ b m size ( THROW-BALL ) = (2 + 3) = 9

37 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 weight c ≈ relative frequency of c, |type r | = number of ontology items of type r used, height d = height of the derivation graph, semfit d = semantic fit provide by the analyzer

38 Preliminary Results

39 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

40 Learning Throw-Constructions 1. Don’t throw the bear.throw-bear 2. you throw ityou-throw 3. throwing the thing.throw-thing 4. Don’t throw them on the ground.throw-them 5. throwing the frisbee.throw-frisbee MERGEthrow-OBJ 6. Do you throw the frisbee? COMPOSE you-throw-frisbee 7. She’s throwing the frisbee. COMPOSE she-throw-frisbee

41 Learning Results

42 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