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
abstraction
Computation
Chang
Model
Bailey
Model
Structured
Connectionism
Neural Net
Regier
& Learning
Triangle Nodes
Narayanan
Model
Model
SHRUTI
Computational Neurobiology
Visual System
Neural
Development
Quiz
Biology
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?
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?
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?
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
Computational Details
• complexity of model + ability to explain data
• maximum a posteriori (MAP) hypothesis
argmax P(m | D)
wants the best model
given data
m
 argmax P( D | m) P(m) by Bayes' rule
m
how likely is the data
given this model?
penalize complex models –
those with too many word senses
schema
elbow jnt
posture
accel
slide 0.9
extend 0.9
palm 0.7
0.9
[6]- 8]
[6
grasp 0.3
data #1
data #2
data #3
data #4
schema
elbow jnt
posture
accel
depress 0.9
fixed 0.9
index 0.9
[2]
schema
elbow jnt
posture
accel
slide
extend
palm
6
schema
elbow jnt
posture
accel
slide
extend
palm
8
schema
elbow jnt
posture
accel
depress
fixed
index
2
schema
elbow jnt
posture
accel
slide
extend
grasp
2
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?
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?
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
Some linguistics theories on
Inherent Aspect
• Zeno Vendler (1957)’s distinction on state, activity,
accomplishment, achievement
FYI:
telic = bounded
atelic = unbounded
punctual = instantaneous
Verbal predicates
stative
dynamic
atelic
atelic
know
resemble
run
swim
state
activity
telic
protracted
instantaneous
write a letter
run a mile
jump
recognize
accomplishment
achievement
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
ready
abort
start
cancelled
resume
ongoing
iterate
finish
done
The car is on the verge of falling into
the ditch.
suspended
interrupt
ready
resume
start
finish
ongoing
abort
iterate
cancelled
FALL
done
He stumbled on the uneven road.
suspended
interrupt
ready
resume
start
finish
ongoing
abort
iterate
cancelled
WALK
done
She cancelled her trip to Paris.
suspended
interrupt
ready
resume
start
finish
ongoing
abort
iterate
cancelled
TRAVEL
done
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?
X-Schema Embedding
You can ‘blow up’ any state or transition into a lower
level x-schema, allowing embedding
suspended
interrupt
ready
abort
start
cancelled
resume
finish
ongoing
done
iterate
ready
start
ongoing
finish
done
He is almost done talking.
suspended
interrupt
ready
abort
start
cancelled
resume
finish
ongoing
done
iterate
ready
start
ongoing
finish
done
They are getting ready to continue
their journey across the desert.
suspended
interrupt
ready
abort
start
cancelled
resume
ongoing
finish
iterate
ready
start
ongoing
finish
done
done
She smokes. (habitual reading)
start
ready
finish
ongoing
done
suspended
interrupt
ready
abort
start
cancelled
resume
ongoing
iterate
finish
done
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?
Mapping down to the time line
• we can use Reichenbach’s
system to map the controller Xschema down to a time line and
get tenses
Speech Time (S)
Reference Time (R)
Event Time (E)
ready
start
ongoing
E
R
finish
done
S
He is talking
ready
start
ongoing
S
E
R
finish
done
He has talked
ready
start
ongoing
E
finish
done
S
R
He will have talked
ready
S
start
ongoing
E
finish
done
R
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?
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?
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
r3
anywhere
eat
r5
here
r4
or
r3
them
r3
r4
there
X1
Have a good Spring Break!!!