View
216
Download
1
Tags:
Embed Size (px)
Citation preview
CS 182Sections 103 - 104
slides created by:
Eva Mok ([email protected])
modified by jgm
April 26, 2006
Announcements
• a9 due Tuesday, May 2nd, 11:59pm
• final paper due Tuesday May 9th, 11:59pm
• final exam Tuesday May 9th in class
• final review?
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
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 <utterance, situation> 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?
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 <utterance, situation> 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?
“you” you schema Addresseesubcase of Human
FORM (sound) MEANING (stuff)
Analyzing “You Throw The Ball”
“throw” throw
schema Throwroles:
throwerthrowee
“ball” ball schema Ballsubcase of Object
“block” blockschema Block
subcase of Object
t1 before t2t2 before t3
Thrower-Throw-Object
t2.thrower ↔ t1t2.throwee ↔ t3
“the”
Addressee
Throwthrowerthrowee
Ball
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} 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-Exprv : Cause-Motion-Verbobj : Ref-Expr
their meaning poles are:agt : Referentv : CauseMoveobj : Referent
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: 0.3333333333333333Chart Entry 2: Bring-Cn1 span: [2, 2] processed input: bring Skipped: none semantic coherence: 0.9090909090909091Chart Entry 4: Cup-Cn1 span: [4, 4] processed input: cup Skipped: none semantic coherence: 0.2857142857142857
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
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)
agt v obj
I get cuplevel 0
level 2
level 1
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)
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 <utterance, situation> 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?
Acquisition
Reorganize
Hypothesize
Production
Utterance
(Comm. Intent, Situation)
Generate
Constructions
(Utterance, Situation)
Analysis
Comprehension
Analyze
Partial
Usage-based Language Learning
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)
SemSpecr1r2
r1r2r3
r1r2
Contextr1r2
r1r2r3
r1r2
“you”
“throw”
“ball”
you
throw
ball
“block” block
schema Addresseesubcase of Human
FORM (sound) MEANING (stuff)lexical constructions
Initial Single-Word Stage
schema Throwroles:
throwerthrowee
schema Ballsubcase of Object
schema Blocksubcase of Object
“you” you schema Addresseesubcase of Human
FORM MEANING
New Data: “You Throw The Ball”
“throw” throw
schema Throwroles:
throwerthrowee
“ball” ball schema Ballsubcase of Object
“block” blockschema Block
subcase of Object
“the”
Addressee
Throwthrowerthrowee
Ball
Self
SITUATION
Addressee
Throwthrowerthrowee
Ball
before
role-filler
throw-ball
Relational Mapping Scenarios
Af
Bf
Am
Bm
A
B
form-relation
role-filler
throw ball throw.throwee ↔ ball
Af
Bf
Am
Bm
A
B
form-relation
role-filler
X
role-filler
put ball down put.mover ↔ balldown.tr ↔ ball
Af
Bf
Am
Bm
A
B
form-relation
role-filler
Y
role-filler
Nomi ball possession.possessor ↔ Nomipossession.possessed ↔
ball
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 <utterance, situation> 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?
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 Objectf THROW.throwee = Objectm
THROW-OBJECT
Resulting Construction
construction THROW-OBJECTconstructional constituentst : THROWo : OBJECT
formtf before of
meaning tm.throwee ↔ om
Composing Co-occurring Constructions
ball before offMotion mm.mover = Ballm.path = Offball off
throw before ball Throw.throwee = Ball
throw the ball
throw before ball ball before off
THROW.throwee = BallMotion mm.mover = Ballm.path = Off
THROW-BALL-OFF
Resulting Constructionconstruction THROW-BALL-OFFconstructional constituentst : THROWb : BALLo : OFF
formtf before bf
bf before of
meaning evokes MOTION as m tm.throwee ↔ bm
m.mover ↔ bm
m.path ↔ om
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 <utterance, situation> 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?
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
Size Of Grammar• Size of the grammar G is the sum of the size of each
construction:
• Size of each construction c is:
where
• nc = number of constituents in c,
• mc = number of constraints in c,
• length(e) = slot chain length of element reference e
Gc
cG )size()size(
ce
cc emnc )length()size(
Example: The Throw-Ball Cxn
construction THROW-BALLconstructional constituents
t : THROWb : BALL
formtf before bf
meaning tm.throwee ↔ bm
size(THROW-BALL) = 2 + 2 + (2 + 3) = 9
ce
cc emnc )length(++)size(
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
• weightc ≈ relative frequency of c,
• |typer| = number of ontology items of type r used,
• heightd = height of the derivation graph,
• semfitd = semantic fit provide by the analyzer
Dd
dGD )score()|(complexity
dddc cr
rc semfitheighttypeweightd
)score(
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