1. Models of Grammar Learning CS 182 Lecture April 24, 2008

2. 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. 3 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

4. 4 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:

5. 5 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

6. 6 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

7. 7 What do we know about language development? (focusing mainly on first language acquisition of English-speaking, normal population)

8. 8 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

9. 9 Phonology: Non-native contrasts Werker and Tees (1984) Thompson: velar vs. uvular, /`ki/-/`qi/. Hindi: retroflex vs. dental, /t.a/-/ta/

10. 10 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

11. 11 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?

12. 12 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’

13. 13 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

14. 14 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!

15. 15 Modifications of Gold’s Result (Weakly) Ordered Examples, implicit negatives Loosened Identification Conditions Complexity Measures, Best Fit No Theorems will resolve these issues

16. 16 Modeling the acquisition of grammar: Theoretical assumptions

17. 17 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)

18. 18 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

19. 19 Comprehension is partial. (not just for dogs)

20. 20 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.

21. 21 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

22. 22 Modeling the acquisition of (early) grammar: Comprehension-driven, usage-based

23. Natural Language Processing at Berkeley Dan Klein EECS Department UC Berkeley

24. 24 NLP: Motivation It’d be great if machines could Read text and understand it Translate languages accurately Help us manage, summarize, and aggregate information Use speech as a UI Talk to us / listen to us But they can’t Language is complex Language is ambiguous Language is highly structured

25. 25 Machine Translation Syntactic MT Learn grammar mappings between languages Fully data-driven

26. 26 Information Extraction Unsupervised Coreference Resolution Take in lots of text Learn what the entities are and how they corefer Fully unsupervised, but gets supervised performance! General research goal: unsupervised learning of meaning

27. 27 Syntactic Learning Grammar Induction Raw text in Learned grammars out Big result: this can be done! Grammar Refinement Coarse grammars in Detailed grammars out Gives top parsing systems

28. 28 Influental members of the House Ways and Means Committee introduced legislation that would restrict how the new S&L bailout agency can raise capital, creating another potential obstacle to the government's sale of sick thrifts. Syntactic Inference Natural language is very ambiguous Grammars are huge Billions of parses to consider Milliseconds to do it

29. 29 Non-Parametric Grammars

30. 30 Idea: Learn PCFGs with EM Classic experiments on learning PCFGs with Expectation- Maximization [Lari and Young, 1990] Full binary grammar over n symbols Parse uniformly/randomly at first Re-estimate rule expectations off of parses Repeat Their conclusion: it doesn’t really work. XjXj XiXi XkXk { X 1, X 2 … X n }

31. 31 Re-estimation of PCFGs Basic quantity needed for re-estimation with EM: Can calculate in cubic time with the Inside-Outside algorithm. Consider an initial grammar where all productions have equal weight: Then all trees have equal probability initially. Therefore, after one round of EM, the posterior over trees will (in the absence of random perturbation) be approximately uniform over all trees, and symmetric over symbols.

32. 32 Problem: “Uniform” Posteriors Tree Uniform Split Uniform

33. 33 Problem: Model Symmetries Symmetries How does this relate to trees? NOUN VERB ADJ NOUN X1?X1?X2?X2?X1?X1?X2?X2? NOUN VERB NOUN VERB ADJ

34. 34 Overview: NLP at UCB Lots of research and resources: Dan Klein: Statistical NLP / ML Marti Hearst: Stat NLP / HCI Jerry Feldman: Language and Mind Michael Jordan: Statistical Methods / ML Tom Griffiths: Statistical Learning / Psychology ICSI Speech and AI groups (Morgan, Stolcke, Shriberg, Fillmore, Kay, Narayanan…) Great linguistics and stats departments! No better place to solve the hard NLP problems!

35. 35 Other Approaches Evaluation: fraction of nodes in gold trees correctly posited in proposed trees (unlabeled recall) Some recent work in learning constituency: [Adrians, 99] Language grammars aren’t general PCFGs [Clark, 01] Mutual-information filters detect constituents, then an MDL-guided search assembles them [van Zaanen, 00] Finds low edit-distance sentence pairs and extracts their differences Adriaans, 199916.8 Clark, 200134.6 van Zaanen, 200035.6