330 likes | 430 Views
CS 182 Sections 103 - 104. slides created by Eva Mok ( emok@icsi.berkeley.edu ) modified by JGM March 22, 2006. The Last Stretch. Psycholinguistics Experiments. Spatial Relation. Motor Control. Metaphor. Grammar. Cognition and Language. Computation. Chang Model. Bailey Model.
E N D
CS 182Sections 103 - 104 slides created by Eva Mok (emok@icsi.berkeley.edu) modified by JGM March 22, 2006
The Last Stretch Psycholinguistics Experiments Spatial Relation Motor Control Metaphor Grammar Cognition and Language Computation Chang Model Bailey Model Narayanan Model Structured Connectionism abstraction Neural Net & Learning Regier Model SHRUTI Computational Neurobiology Triangle Nodes Visual System Biology Neural Development Quiz Midterm Finals
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? • What does the prefix affix tree look like for the following sentences: • eat them here or there • eat them anywhere • What does the affix tree look like after the best prefix merge?
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? • What does the prefix affix tree look like for the following sentences: • eat them here or there • eat them anywhere • What does the affix tree look like after the best prefix merge?
Bailey’s VerbLearn Model • 3 Levels of representation • cognitive: words, concepts • computational: f-structs, x-schemas • connectionist: structured models, learning rules • Input: labeled hand motions (f-structs) • learning: • the correct number of senses for each verb • the relevant features in each sense, and • the probability distributions on each included feature • execution: perform a hand motion based on a label
wants the best model given data how likely is the data given this model? penalize complex models – those with too many word senses Computational Details • complexity of model + ability to explain data • maximum a posteriori (MAP) hypothesis
data #1 data #2 data #3 data #4
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
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? • What does the prefix affix tree look like for the following sentences: • eat them here or there • eat them anywhere • What does the affix tree look like after the best prefix merge?
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
Verbal predicates stative dynamic atelic atelic telic knowresemble runswim protracted instantaneous write a letter run a mile jump recognize state activity accomplishment achievement Some linguistics theories on Inherent Aspect • Zeno Vendler (1957)’s distinction on state, activity, accomplishment, achievement FYI: telic = bounded atelic = unbounded punctual = instantaneous
suspended interrupt resume start finish ready ongoing done abort iterate cancelled 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.
suspended interrupt resume start finish ready ongoing done abort iterate cancelled The car is on the verge of falling into the ditch. FALL
suspended interrupt resume start finish ready ongoing done abort iterate cancelled He stumbled on the uneven road. WALK
suspended interrupt resume start finish ready ongoing done abort iterate cancelled She cancelled her trip to Paris. TRAVEL
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? • What does the prefix affix tree look like for the following sentences: • eat them here or there • eat them anywhere • What does the affix tree look like after the best prefix merge?
suspended interrupt resume start finish ready ongoing done start finish done ready ongoing abort iterate cancelled X-Schema Embedding You can ‘blow up’ any state or transition into a lower level x-schema, allowing embedding
suspended interrupt resume start finish ready ongoing done start finish done ready ongoing abort iterate cancelled He is almost done talking.
suspended interrupt resume start finish ready ongoing done start finish done ready ongoing abort iterate cancelled They are getting ready to continue their journey across the desert.
suspended interrupt resume start finish ready ongoing done start finish done ready ongoing abort iterate cancelled She smokes. (habitual reading)
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? • What does the prefix affix tree look like for the following sentences: • eat them here or there • eat them anywhere • What does the affix tree look like after the best prefix merge?
start finish done ready ongoing 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 Speech Time (S) Reference Time (R) Event Time (E) E R S
start finish done ready ongoing S E R He is talking
start finish done ready ongoing E S R He has talked
start finish done ready ongoing S E R He will have talked
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)
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…
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? • What does the prefix affix tree look like for the following sentences: • eat them here or there • eat them anywhere • What does the affix tree look like after the best prefix merge?
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
Prefix Tree r1: S eat them here or there r2: S eat them anywhere r1 r2 S r1 r2 eat r1 r2 them r1 r2 anywhere here r1 or r1 there
Prefix Merge r3: S eat them X1 r4: X1 here or there r5: X1 anywhere r4 r5 r3 S X1 r4 r5 here r3 anywhere eat r4 or r4 r3 them there r3 X1