1. CS 182 Sections 103 - 104 slides created by: Eva Mok (emok@icsi.berkeley.edu) modified by jgm April 26, 2006

2. Announcements a9 due Tuesday, May 2 nd, 11:59pm final paper due Tuesday May 9 th, 11:59pm final exam Tuesday May 9 th in class final review?

3. Schedule Last Week –Constructions, ECG –Models of language learning This Week –Embodied Construction Grammar learning –(Bayesian) psychological model of sentence processing Next Week –Applications –Wrap-Up

4. Quiz 1.How does the analyzer use the constructions to parse a sentence? 2.What is the process by which new constructions are learned from pairs? 3.What are ways to re-organize and consolidate the current grammar? 4.What metric is used to determine when to form a new construction?

5. Quiz 1.How does the analyzer use the constructions to parse a sentence? 2.What is the process by which new constructions are learned from pairs? 3.What are ways to re-organize and consolidate the current grammar? 4.What metric is used to determine when to form a new construction?

6. “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

7. I will get the cup the analyzer allows the skipping of unknown lexical items here is the SemSpec CauseMove1:CauseMove mover = {Cup1:Cup} direction = {Place2:Place} causer = {Entity4:Speaker} motion = Move1:Move mover = {Cup1:Cup} direction = Place2:Place agent = {Entity4:Speaker} patient = {Cup1:Cup} Referent2:Referent category = {Cup1:Cup} resolved-ref = {Cup1:Cup} Referent1:Referent category = {Entity4:Speaker} resolved-ref = {Entity4:Speaker} Remember that the transitive construction takes 3 constituents: agt : Ref-Expr v : Cause-Motion-Verb obj : Ref-Expr their meaning poles are: agt : Referent v : CauseMove obj : Referent

8. Another way to think of the SemSpec

9. Analyzer Chart Chart Entry 0: Transitive-Cn1 span: [0, 4] processed input: i bring cup Skipped: 1 3 semantic coherence: 0.56 I-Cn1 span: [0, 0] processed input: i Skipped: none semantic coherence: 0.3333333333333333 Chart Entry 2: Bring-Cn1 span: [2, 2] processed input: bring Skipped: none semantic coherence: 0.9090909090909091 Chart Entry 4: Cup-Cn1 span: [4, 4] processed input: cup Skipped: none semantic coherence: 0.2857142857142857

10. Analyzing in ECG create a recognizer for each construction in the grammar for each level j (in ascending order) repeat for each recognizer r in j for each position p of utterance initiate r starting at p until the number of states in the chart doesn't change

11. Recognizer for the Transitive-Cn an example of a level-1 construction is Red-Ball-Cn each recognizer looks for its constituents in order (the ordering constraints on the constituents can be a partial ordering) agtvobj Igetcup level 0 level 2 level 1

12. 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)

13. Quiz 1.How does the analyzer use the constructions to parse a sentence? 2.What is the process by which new constructions are learned from pairs? 3.What are ways to re-organize and consolidate the current grammar? 4.What metric is used to determine when to form a new construction?

14. Acquisition Reorganize Hypothesize Production Utterance (Comm. Intent, Situation) Generate Constructions (Utterance, Situation) Analysis Comprehension Analyze Partial Usage-based Language Learning

15. Basic Learning Idea The learner’s current grammar produces a certain analysis for an input sentence The context contains richer information (e.g. bindings) that are unaccounted for in the analysis Find a way to account for these meaning relations (by looking for corresponding form relations) SemSpec r1 r2 r1 r2 r3 r1 r2 Context r1 r2 r1 r2 r3 r1 r2

16. “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

17. “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

18. Relational Mapping Scenarios AfAf BfBf AmAm BmBm A B form- relation role- filler throw ball throw.throwee ↔ ball AfAf BfBf AmAm BmBm A B form- relation role- filler X put ball down put.mover ↔ ball down.tr ↔ ball AfAf BfBf AmAm BmBm A B form- relation role- filler Y Nomi ball possession.possessor ↔ Nomi possession.possessed ↔ ball

19. Quiz 1.How does the analyzer use the constructions to parse a sentence? 2.What is the process by which new constructions are learned from pairs? 3.What are ways to re-organize and consolidate the current grammar? 4.What metric is used to determine when to form a new construction?

20. 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

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

22. 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

23. 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

24. Quiz 1.How does the analyzer use the constructions to parse a sentence? 2.What is the process by which new constructions are learned from pairs? 3.What are ways to re-organize and consolidate the current grammar? 4.What metric is used to determine when to form a new construction?

25. 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) ≈ 1/posterior probability ≈ 1/P(G|D) Size of grammar = size(G) ≈ 1/prior ≈ 1/P(G) –favor fewer/smaller constructions/roles; isomorphic mappings Complexity of data given grammar ≈ 1/likelihood ≈ 1/P(D|G) –favor simpler analyses (fewer, more likely constructions) –based on derivation length + score of derivation

26. 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

27. 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 + 2 + (2 + 3) = 9

28. 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

29. Final Remark The goal here is to build a cognitive plausible model of language learning A very different game that one could play is unsupervised / semi-supervised language learning using shallow or no semantics –statistical NLP –automatic extraction of syntactic structure –automatic labeling of frame elements Fairly reasonable results for use in tasks such as information retrieval, but the semantic representation is very shallow