1. CS 182 Sections 103 - 104 slides created by Eva Mok (emok@icsi.berkeley.edu)emok@icsi.berkeley.edu modified by JGM March 22, 2006

2. The Last Stretch Cognition and Language Computation Structured Connectionism Computational Neurobiology Biology MidtermQuiz Finals Neural Development Triangle Nodes Neural Net & Learning Spatial Relation Motor Control Metaphor SHRUTI Grammar abstraction Regier Model Bailey Model Narayanan Model Chang Model Visual System Psycholinguistics Experiments

3. Quiz How does Bailey use multiple levels of representation to learn different senses of verbs? What’s the difference between aspect and tense? What’s X-schema embedding? Give an example where embedding is necessary. How can Reichenbach’s system be used with X-schemas? When does this system break down? 1.What does the prefix affix tree look like for the following sentences: –eat them here or there –eat them anywhere 2.What does the affix tree look like after the best prefix merge?

4. Quiz How does Bailey use multiple levels of representation to learn different senses of verbs? What’s the difference between aspect and tense? What’s X-schema embedding? Give an example where embedding is necessary. How can Reichenbach’s system be used with X-schemas? When does this system break down? 1.What does the prefix affix tree look like for the following sentences: –eat them here or there –eat them anywhere 2.What does the affix tree look like after the best prefix merge?

5. Bailey’s VerbLearn Model 3 Levels of representation 1.cognitive: words, concepts 2.computational: f-structs, x-schemas 3.connectionist: structured models, learning rules Input: labeled hand motions (f-structs) learning: 1.the correct number of senses for each verb 2.the relevant features in each sense, and 3.the probability distributions on each included feature execution: perform a hand motion based on a label

7. Computational Details complexity of model + ability to explain data maximum a posteriori (MAP) hypothesis how likely is the data given this model? penalize complex models – those with too many word senses wants the best model given data

8. schemaelbow jntpostureaccel slideextendpalm6 schemaelbow jntpostureaccel slideextendpalm8 schemaelbow jntpostureaccel slide 0.9extend 0.9palm 0.9[6] data #1 data #2 data #3 data #4 schemaelbow jntpostureaccel depress 0.9fixed 0.9index 0.9[2] schemaelbow jntpostureaccel slide 0.9extend 0.9palm 0.9[6 - 8] schemaelbow jntposture slide 0.9extend 0.9palm 0.7 grasp 0.3 schemaelbow jntpostureaccel depressfixedindex2 schemaelbow jntpostureaccel slideextendgrasp2

10. Limitations of Bailey’s model an instance of recruitment learning (1-shot) embodied (motor control schemas) learns words and carries out action the label contains just the verb assumes that the labels are mostly correct no grammar

11. Quiz How does Bailey use multiple levels of representation to learn different senses of verbs? What’s the difference between aspect and tense? What’s X-schema embedding? Give an example where embedding is necessary. How can Reichenbach’s system be used with X-schemas? When does this system break down? 1.What does the prefix affix tree look like for the following sentences: –eat them here or there –eat them anywhere 2.What does the affix tree look like after the best prefix merge?

12. Aspect Aspect is different from tense in that it deals with the temporal structure of events Viewpoints –looking at the same event at different granularity –He was walking / He has walked / He walks Phases of Events –zooming in at a level and focusing on a stage in an event –He is about to walk / He finished walking Inherent Aspect –perfective / imperfective (telic / atelic) –He is walking / He is tapping his finger

13. Some linguistics theories on Inherent Aspect Zeno Vendler (1957)’s distinction on state, activity, accomplishment, achievement stative Verbal predicates dynamic atelic telic protractedinstantaneous know resemble run swim write a letter run a mile jump recognize stateactivity accomplishmentachievement FYI: telic = bounded atelic = unbounded punctual = instantaneous

14. Controller X-Schema The controller x-schema is meant to capture the generic structure of events. Aspect therefore marks (or profiles) certain states or transitions. ready start ongoing finish done iterateabort cancelled interruptresume suspended

15. The car is on the verge of falling into the ditch. ready start ongoing finish done iterateabort cancelled interruptresume suspended FALL

16. He stumbled on the uneven road. ready start ongoing finish done iterateabort cancelled interruptresume suspended WALK

17. She cancelled her trip to Paris. ready start ongoing finish done iterateabort cancelled interruptresume suspended TRAVEL

18. Quiz How does Bailey use multiple levels of representation to learn different senses of verbs? What’s the difference between aspect and tense? What’s X-schema embedding? Give an example where embedding is necessary. How can Reichenbach’s system be used with X-schemas? When does this system break down? 1.What does the prefix affix tree look like for the following sentences: –eat them here or there –eat them anywhere 2.What does the affix tree look like after the best prefix merge?

19. X-Schema Embedding You can ‘blow up’ any state or transition into a lower level x-schema, allowing embedding ready start ongoing finish done iterateabort cancelled interruptresume suspended ready start ongoing finish done

20. He is almost done talking. ready start ongoing finish done iterateabort cancelled interruptresume suspended ready start ongoing finish done

21. They are getting ready to continue their journey across the desert. ready start ongoing finish done iterateabort cancelled interruptresume suspended ready start ongoing finish done

22. She smokes. (habitual reading) ready start ongoing finish done iterateabort cancelled interruptresume suspended ready start ongoing finish done

23. Quiz How does Bailey use multiple levels of representation to learn different senses of verbs? What’s the difference between aspect and tense? What’s X-schema embedding? Give an example where embedding is necessary. How can Reichenbach’s system be used with X-schemas? When does this system break down? 1.What does the prefix affix tree look like for the following sentences: –eat them here or there –eat them anywhere 2.What does the affix tree look like after the best prefix merge?

24. Mapping down to the time line we can use Reichenbach’s system to map the controller X- schema down to a time line and get tenses SRE ready start ongoing finish done Speech Time (S) Reference Time (R) Event Time (E)

25. He is talking S R E ready start ongoing finish done

26. He has talked S R E ready start ongoing finish done

27. He will have talked SRE ready start ongoing finish done

28. He would have talked... … by the time the bell rang. … if you had not shushed him. okay this is getting complicated interaction with modals like would could be a strictly past reading (case 1) possibly a counterfactual (case 2)

29. Not much of a stretch… to get to metaphorical sentences like this: The US Economy is on the verge of falling back into recession after moving forward on an anaemic recovery. You would just need to map from this physical domain (source domain) to the say, economics (target domain) the Event Structure Metaphor is exactly the general mapping from motion to changes, locations to states and then you need some domain specific mappings more on that in lecture…

30. Quiz How does Bailey use multiple levels of representation to learn different senses of verbs? What’s the difference between aspect and tense? What’s X-schema embedding? Give an example where embedding is necessary. How can Reichenbach’s system be used with X-schemas? When does this system break down? 1.What does the prefix affix tree look like for the following sentences: –eat them here or there –eat them anywhere 2.What does the affix tree look like after the best prefix merge?

31. Affix Trees Data structures that help you figure out what merges are possible Each node in the tree represents a symbol, either terminal or non-terminal (we call that the “affix” in the code) Prefix Tree Suffix Tree

32. Prefix Tree r1: S  eat them here or there r2: S  eat them anywhere eat them here or there r1 r2 anywhere r2 S r1r2

33. Prefix Merge r3: S  eat them X1 r4: X1  here or there r5: X1  anywhere eat them r3 S here or there r4 anywhere r5 X1 r3 r4r5

34. Have a good Spring Break!!!