Double R Theory January 2011 Jerry Ball Human Effectiveness Directorate 711 th Human Performance Wing Air Force Research Laboratory.
Post on 02-Apr-2015
214 Views
Preview:
Transcript
Double R TheoryJanuary 2011
Jerry Ball
Human Effectiveness Directorate
711th Human Performance Wing
Air Force Research Laboratory
2
Theoretical FoundationsLanguage Representation and Processing
• Double R Grammar
– Cognitive Linguistic theory of the grammatical encoding of referential and relational meaning
• Double R Process
– Psycholinguistic theory of the processing of English text into Double R Grammar based representations
• Double R Model
– Computational implementation using the ACT-R cognitive architecture and modeling environment
DoubleRTheory.com
3
Theoretical FoundationsLanguage Representation and Processing
• Double R Grammar
– Cognitive Linguistic theory of the grammatical encoding of referential and relational meaning
• Double R Process
– Psycholinguistic theory of the processing of English text into Double R Grammar based representations
• Double R Model
– Computational implementation using the ACT-R cognitive architecture and modeling environment
DoubleRTheory.com
4
Theoretical FoundationsGrounding Language in Experience
• Symbol Grounding (Harnad)
– Ungrounded symbols are meaningless
– There must be a chain from abstract to perceptually grounded concepts that provides the grounding for abstract concepts
• Perceptual Symbol Systems (Barsalou)
– No purely abstract concepts
– The brain is a highly evolved perceptual (motor) organ
– Imagery simulates perceptual experience
• Embodied Cognition (Lakoff et al.)
– Abstract concepts are often understood via metaphorical association with more concrete concepts
• Good is up—Bad is down; Life is a journey
5
Theoretical FoundationsSituation Model
• Situation Model (Kintsch et al.)
– Originally viewed as a propositional text base (van Dijk & Kintsch)
• Elaboration of propositions in linguistic input
– Now viewed as a Spatial-Imaginal (and Temporal) representation of the objects and situations described by linguistic expressions and encoded directly from the environment (Zwann et al.)
• Non-propositional (in part)
• Non-textual
• No available computational implementations
– Provides grounding for linguistic representations
6
Abstract Concepts vs. Perceptually Grounded Language
“pilot”
XY-123
(aka PILOT)
Real World Mental Box
Cognition
The Prevailing “Cognitive Psychological” View
Concept ~ abstract amodal fixed point in conceptual space
“pilotpilot”
Perception
7
Abstract Concepts vs. Perceptually Grounded Language
“pilot” “pilotpilot”
Mental BoxReal World
perception
An Emerging “Embodied Cognition” View
gro
un
din
g
perception
Explicit(Perceptual)
Perceptual
Symbol
Do we really need
abstract concepts?
How are they learned?
Cognition is the
simulation of
perceptual experience
Concept ~ dynamic and tangled interconnections of associated experiences
8
Language is Grounded in a Situation Model
The horse runs
the
horse
runs
subj
headSRE
ORE
PRED
Dynamic mental simulation of horse running would be better!
SRE: Situation Referring Expression
ORE: Object Referring Expression
PRED: Predicate
refers
refers
9
Language is Grounded in a Situation Model
The paint runs
the
paint
runs
subj
headSRE
ORE
PRED
Dynamic mental simulation of paint running would be better!
refers
refers
Each experience of a running event changes the RUN concept!
10
Guiding Linguistic Principles
• Jackendoff’s (1983) Grammatical Constraint:
…one should prefer a semantic theory that explains otherwise arbitrary generalizations about the syntax and the lexicon…a theory’s deviations from efficient encoding must be vigorously justified, for what appears to be an irregular relationship between syntax and semantics may turn out merely to be a bad theory of one or the other
11
Guiding Linguistic Principles
• Langacker’s Cognitive Grammar (1987, 1991)
– Grammar is simply the structuring and symbolization of semantic content
– Exclusionary Fallacy – one analysis, motivation, categorization, cause, function or explanation for a linguistic phenomenon necessarily precludes another
– Rule/List Fallacy – the assumption, on grounds of simplicity, that particular statements (i.e. lists) must be excised from the grammar of a language if general statements (i.e. rules) that subsume them can be established
12
Construction Grammar (Fillmore, Goldberg, Sag, etc.)
• Constructions—the basic units of grammar—are pairings of form, function and meaning
the man hit the ballform
function
meaning
subject predicator object
HIT(AGENT:MAN PATIENT:BALL)
“concepts”uppercase word syndrome
semantic roles
13
Construction Grammar
• Declarative Clause + Intransitive Verb construction
– The woman sneezed
• Decl Clause + Transitive Verb construction
– The man hit the ball
• Wh-Question + Ditransitive Verb + Passive constr.
– Who was given the ball?
• Decl Clause + Intrans Verb + Causative constr.
– The woman sneezed the napkin off the table
14
X-Bar Theory
• Key element of Chomsky’s Generative Grammar from the 1970’s to the 1990’s
• Theory of the universal structure of all languages
– Autonomous from meaning
• X-Bar structure presumed to be innate (not learned)
• Replaced Phrase Structure Grammar component of earlier theory (e.g. S NP VP; NP Det N; …)
• Has gone thru several major revisions resulting in more and more complex syntactic representations
• Subsumed by other theoretical considerations in Chomsky’s Minimalist Program (circa. 1995)
15
X-Bar Theory (Chomsky 1970)
Specifier X-Bar
XP
X (head)
Complement(s)
Generalization over Syntactic Categories – NP, VP, AP, PP
XP Spec X-Bar
X-Bar X (Head) Comp(s)
Universal structure of all languages except that relative locations can vary (e.g. complements may occur before or after head)
Universal structure of all languages – very strong claim – generative linguists spent next 20+ years trying to demonstrate it!
16
X-Bar Theory ~ 1993
Universal structure of all languages Something went seriously wrong!
XP
(X’’)
Spec X-Bar
(X’)
X Comp
(YP)
Locally adheres to X-Bar Schema Globally very complex!
X-Bar schema Universal structure of clause
17
X-Bar Theory (adapted in Ball 2007)
Specifier X-Bar
XP
X (head)
Complement(s)
Generalization over grammatical categories – referring expression
referential
layer
relational
layer
What’s right about X-Bar Theory:
1.Referential layer
2.Relational layer
3.Grammatical functions: specifier, head, complement, modifier (but need to be semantically motivated)
head – semantically most significant element
specifier – indicates referential
function
complements – arguments of
relational head
18
Simpler Syntax(Culicover & Jackendoff 2005)
• Reaction against the complex syntactic representations of modern mainstream generative grammar
– Against syntactocentrism
• If there is a level of meaning representation, then syntactic representations can be simpler
– Flat as opposed to deeply nested syntactic representations
• Culicover & Jackendoff are former students of Chomsky
19
Comprehensive Grammars of English
• Cambridge Grammar (Huddleston & Pullum, 2002)
– Informed by linguistic theory, but attempts to cover most of English with all its exceptions
– Adds functional categories to syntactic representations
• Longman’s Grammar (Quirk et al., 1985)
– Focus on basic functions of linguistic elements
– In the spirit of Functional Grammar as opposed to Chomsky’s Generative Grammar
20
Double R Grammar
• Theory of the grammatical encoding of Referential and Relational meaning
• Derived from X-Bar Theory prior to the introduction of functional heads (Chomsky, 1970)
• Grammatical Functions (GFs) explicitly represented
– Phrase Level: Specifier, Head, Complement, Modifier
– Clause Level: Specifier, Head, Subject (Comp), Modifier
• Specifier + Head Referring Expression (Max Proj)
– All the grammatical info needed to support reference
• Specifier = locus of Referential meaning
• Head = locus of Relational meaning
21
Basic Nominal – X-Bar Theory (Chomsky 1970)
the captain
D
N
NP
Lexical Item
Syntactic Category
NP D N-Bar
N-Bar N
the captain
N-BarHead (implicit)
Specifier (implicit)
Maximal Projection
Grammatical Functions are implicit in syntactic representation
• Noun is head of nominal (NP)• N-bar level is required
Later – D reanalyzed
as head of DP
(functional head)
DP D-bar NP
22
Basic Nominal – Simpler Syntax
the captain
D N
NP
Double Line marks head
Lexical Item
• Noun is head of nominal (NP)• No N-bar level
Syntactic Category
One (explicit) phrase level GF:
1.Head
NP D N (head) the captain
23
Basic Nominal – Cambridge Grammar
the captain
Det:D
Head:N
NP
GF:
Syntactic Category
Lexical Item
Four phrase level (NP) GF’s:
1.Head
2.Determiner
3.Complement
4.Modifier
• Noun is head of nominal (NP)• N-Bar level allowed, but not required
Note: Nominal = N-bar, not NP
for H&P
NP Det:D Head:N the captain
24
Nominal ~ Referring Expression
John Lyons, Semantics, Vol 2, 1977, p. 445
“Looked at from a semantic point of view, nominals are referring expressions”
“They are expressions which have a certain potential for reference”
25
Basic Nominal – Double R
the captain
Spec Head
Object Referring Expression (ORE)
Referential pole Relational pole
D N
Grammatical
Function (GF)Grammatical/ Lexical Construction
Lexical Item
Four phrase level GF’s:
1.Head
2.Specifier
3.Complement
4.Modifier
• Nominal ~ Object Referring Expression• Noun is head of nominal (NP)• No N-bar level
ORE Spec Head; Spec D; Head N the captain
26
Basic Clause X-Bar Theory ~ 1970s
Joe run
VP
S
NP
N V
S NP VP
VP Specv V-Bar
V-Bar V
Joe runs
Structure of S
not explained
by X-Bar Theory
circa. 1970
-- no specifier or head of S
N-bar V-barSpecv
TENSEpres
Deep Structure gets transformed
into Surface Structure
(Transformational Grammar)
-- TENSEpres + run runs
Deep Structure
27
Basic Clause – Simpler Syntax
Joe run
VP
S
NP
N V
Syntactic Tier:
GF Tier: Subject
• Head of S not specified in Culicover (2009)
• In Jackendoff (2002), no lexical items in syntactic tier
S NP AUX VP Joe runs
Clause level GF’s:
1.Subject
2.Object
3.Second Object
CS: RUN(AGENT:X)
AUX
TENSEpres
affix hoppingVestige of
Transformational Grammar
28
Basic Clause – Cambridge Grammar
Joe runs
Predicate:VP
Clause
Subj:NP
Head:N
Predicator:V
Clause level GF’s:
1.Predicate ~ Head of Clause
2.Subject ~ External Complement
3.Modifier
Additional phrase level (VP) GF:
1.Predicator ~ Head of VP
Clause Subj:NP Predicate:VP
Predicate:VP Predicator:V
Joe runs
No equivalent to determiner at clause level!
29
Basic Clause – Double R
(Spec+)Head
Situation Referring Expression (SRE)
Subj|
ORE|
(Spec+)Head|
PN|
Joe
Vfin
|runs
Clause level GF’s:
1.Head
2.Specifier
3.Subject ~ External Complement
4.Modifier
• SRE ~ Clause or S
SRE Subj (Spec+)Head
Subj ORE
(Spec+)Head Vfin
Joe runs
Grammatical Construction
Specification fused with Head
30
Basic Clause X-Bar Theory ~ 1970s
VP
S
NP|
N-bar|N|
Joe
S NP VP
VP Specv V-Bar (head)
V-Bar V (head) NP (comp)
NP D (spec) N-bar (head)
N-Bar N (head)
Joe kicks the ball
N-bar|N|
ball
D|
the
NP
Later – VP reanalyzed as head of S & Subject NP
reanalyzed as
specifier of S – left of head so must be spec!
S NP (spec) VP (head)
Later – tense reanalyzed as head of IP;
S reanalyzed as CP (complementizer phrase) with C-bar = IP
CP IP = C-bar (head)
IP (inflection phrase) NP (spec) I-bar (head)
I-bar I (tense head) VP (comp)
Specv
TENSEpres
V-Bar
V|
kick
31
Basic Clause – X-Bar Theory ~ 1980s
VP
CP
NP|
N-bar|N|
Joe
CP IP = C-bar (head)
IP NP (spec) I-bar (head)
I-bar I (head) VP (comp)
VP V-Bar (head) NP (comp)
V-Bar V (head)
Joe kicks the ball
N-bar|N|
ball
D|
the
NP
IP = C-bar
Later – additional levels proposed:
AgrP (agreement) AgrSP, AgrOP
NegP (negation)
ModP (modality)
Etc.
Complement of I-bar
Spec of IP
(subject)
Head of CP
I-bar
V-Bar
V|
kick
I|
TENSEpres
Sentence now adheres to X-Bar Theory!
32
Basic Clause – X-Bar Theory ~ 1993
C’ = C-bar
TP = IP
Subj Agreement
Obj Agreement
VP way down here!
Structure below VP not shown
Universal clausal structure of all languages!
Some languages have object agreement, so universal, innate structure must have this layer!
|Joe?
kick the ball
TENSEpres
Joe kicks the ball
33
Basic Clause – Simpler Syntax
VP||V|
kick
S
NP||N|
Joe
Syntactic Tier:
GF Tier: Subject Object
S NP AUX VP
VP V (head) NP
Joe kicks the ball
CS: KICK(AGENT:X PATIENT:Y )
N|
ball
D|
the
NP
AUX
TENSEpres
affix hopping
34
Basic Clause – Cambridge Grammar
Predicator:V|
kicks
Clause
Subj:NP
|Head:
N|
JoeHead:
N|
ball
Det:D|
the
Predicate:VP
Obj:NP
Clause Subj:NP Predicate:VP
Predicate:VP Predicator:V Obj:NP
Joe kicks the ball
Additional phrase level (VP) GF:
1.Object ~ Complement
35
Basic Clause – Double R
(Spec+)Head|
Vfin
|kicks
SRE
Subj|
ORE|
(Spec+)Head|
PN|
JoeHead
|N|
ball
Spec|D|
the
(Spec+)Head|
Pred-Trans-Verb
Obj|
ORE
SRE Subj (Spec+)Head
Subj ORE
Head Pred-Trans-Verb
PTV Head Obj
Joe kicks the ball
Grammatical Construction
Additional phrase level GF:
1.Object ~ Complement
36
Basic Clause with Auxiliary – Simpler Syntax
VP[PROG-PART]
||V
[PROG-PART]
|kick
S
NP||N|
Joe
Syntactic Tier:
GF Tier: Subject
N|
ballObject
AUX
S NP AUX VP
VP V (head) NP
D|
the
NP
Joe is kicking the ball
CS: KICK(AGENT:X PATIENT:Y )
TENSEpres VAUX
|be
affix hopping
37
Basic Clause with Auxiliary – Cambridge Grammar
Predicator:V|
kicking
Clause
Subj:NP
|Head:
N|
Joe
Head:N|
ball
Det:D|
the
Predicate:VP
Obj:NP
Predicate:VP
Predicator:V|is
Clause Subj:NP Pred:VP
Pred:VP Pred-or:V Comp:Clausebare
Comp:Clausebare Pred:VP
Pred:VP Pred-or:V Obj:NP
Joe is kicking the ball
Comp:Clausebare
|
catenative verbs
bare clause
(no subj or tense)
No specifier GF
head of
clause!
38
Basic Clause with Auxiliary – Double R
Head|V|
kicking
SRE
Subj|
ORE|
Head|N|
Joe
Head|N|
ball
Spec|D|
the
Head|
Pred-Trans-Verb
Obj|
ORE
Spec|
Aux|is
SRE Subj Spec Head
Subj ORE
Spec Aux
Head Pred-Trans-Verb
PTV Head Obj
Joe is kicking the ball
head of
clause
39
Possessive Nominal – Simpler Syntax
Joe book
N
NP
NP
NP NP’s N Joe’s book
’s
No label!
40
Possessive Nominal – Cambridge Grammar
Joe’s book
Head:N
NPPlain
Subj+Det:NPGen
Fused subject-determiner
H & P allow GF’s to be fused
– consistent with grammatical evidence
NPPlain Subj+Det:NPGen Head:N Joe’s book
Additional phrase level GF:
1.Subj ~ Complement
41
Possessive Nominal – Double R
Joe ’s book
RefPt Head
Possessive Object Referring Expression (ORE)
Spec
Referential pole Relational pole
NPoss-Mkr
ORE – (Spec+)Head –
PN
Poss-ORE RefPt+Spec Head Joe’s book
Additional phrase level GF:
1.Ref Pt ~ Complement
Grammatical Construction
42
Clause without Main Verb – Simpler Syntax
PP||P|
on
S
N|
book
Syntactic Tier:
GF Tier: Subject
N|
table
S NP AUX PP
D|
the
NP
NP
D|
the
the book is on the table
CS Tier: BE(THEME:X, ON(THEME:Y))
AUX
TENSEpres VAUX
|be
43
Clause without Main Verb – Cambridge Grammar
Head:P|
on
Clause
Head:N|
book
Head:N|
table
Det:D|
the
Comp:PP
Obj:NP
Predicate:VP
Predicator:V|is
Clause Subj:NP Pred:VP
Pred:VP Pred-or:V Comp:PP
Comp:PP Head:P Obj:NP
Det:D|
the
Subj:NP
the book is on the table
head of
clause!
44
Clause without Main Verb – Double R
Head|P|
on
SRE
Head|N|
bookHead
|N|
table
Spec|D|
the
Head|
Pred-Prep
Obj|
ORE
Spec|
Aux|is
SRE Subj Spec Head
Subj ORE
Spec Aux
Head Pred-Prep
Pred-Prep Head Obj
Subj|
ORE
Spec|D|
the
the book is on the table
Grammatical Construction
head of
clause!
45
Clause without Main Verb – Simpler Syntax
PP||P|
on
S
N|
book
Syntactic Tier:
GF Tier: Subject
N|
table
S NP AUX PP
D|
the
NP
NP
D|
the
the book’s on the table
CS Tier: BE(THEME:X, ON(THEME:Y))
AUX
TENSEpres VAUX
|be
46
Clause without Main Verb – Cambridge Grammar
Head:P|
on
Clause
Head:N|
book
Head:N|
table
Det:D|
the
Comp:PP
Obj:NP
Predicate:VP
Predicator:V|’s
Clause Subj:NP Pred:VP
Pred:VP Pred-or:V Comp:PP
Comp:PP Head:P Obj:NP
Det:D|
the
Subj:NP
Don’t see how H&P can allow
GF’s to be fused
– inconsistent with grammatical evidence
the book’s on the table
fused?
47
Clause without Main Verb – Double R
Head|P|
on
SRE
Head|N|
bookHead
|N|
table
Spec|D|
the
Head|
Pred-Prep
Obj|
ORE
Spec|
Aux|’s
SRE Subj+Spec Head
Subj ORE
Spec Aux
Head Pred-Prep
Pred-Prep Head Obj
Subj|
ORE
Spec|D|
the
the book’s on the table
48
Passive Clause – Simpler Syntax
VP
S
Syntactic Tier:
GF Tier: Subject
PP
bev-aux
S NP AUX VPbe
VPbe be (head) VP[PASS]
VP[PASS] V[PASS] (PPby)
PPby by NP
V[PASSIVE]
|
take
VP[PASSIVE]
NP
byp NP
the book was taken by Joe
CS: TAKE(AGENT:X, PATIENT:Y)
AUX
TENSEpast
the book
Joe
49
Passive Clause – Cambridge Grammar
Predicator:V|
taken
Clause
Head:N|
book
Comp:NP
Joe
Comp:P|
by
Predicate:VP
Comp:PP
Predicate:VP
Predicator:V|
was
Clause Subj:NP Pred:VP
Pred:VP Pred-or:V Comp:Clausebare
Comp:Clausebare Pred:VP
Pred:VP Pred-or:V Comp:PP
Det:D|
the
Subj:NP
the book was taken by Joe
Comp:Clausebare
|
50
Passive Clause – Double R
Head|V|
taken
SRE
Head|N|
bookObj ORE
Head, PN Joe
Head, P by
Head|
Pred-Trans-Verb
Obj|
Bind1
Spec|
Aux|
was
SRE Subj Spec Head
Subj ORE1
Spec Aux
Head Pred-Trans-Verb
PTV Head Obj Mod
Obj Bind1
Subj|
ORE1
Spec|D|
the
the book was taken by Joe
Mod|
Pass-By-RE
Grammatical
Construction
51
Yes-No-Question – Double R
Y-N-Quest-SRE
Head|
Pred-Trans-Verb
Obj|
ORE|
Operator|
Aux|
did
Y-N-Quest-SRE Op Subj (Spec) Head
Pred-Trans-Verb Head ObjDid he take it?
Subj|
ORE
|Head
|Pron
|he
Head, Pron|it
Additional clause level GF:
1.Operator ~ Specifier
Grammatical Construction
Head|V|
take
52
Yes-No-Question – Double R
Head|V|
taken
Y-N-Quest-SRE
Head|
Pred-Trans-Verb
Obj|
ORE|
Operator|
Aux|
could
Y-N-Quest-SRE Op Subj (Spec) Head
Pred-Trans-Verb Head Obj
Could he have taken it?
Subj|
ORE|
Head|
Pron|
he
Head, Pron|it
Spec|
Aux|
have
53
Wh-Question – Double R
Wh-Quest-SRE
Head|
Pred-Trans-Verb
Obj|
Bind1
Wh-Quest-SRE Wh-Focus Op Subj (Spec) Head
Pred-Trans-Verb Head Obj
Wh-Focus|
Wh-ORE1
|Head
|Wh-Pron
|what
What did he take?
Subj|
ORE1
|Head
|Pron
|he
Additional clause level GF:
1.Wh-Focus ~ Complement
Grammatical Construction
Head|V|
take
Operator|
Aux|
did
54
Wh-Question – Double R
Head|V|
taken
Wh-Quest-SRE
Head|
Wh-Pron|
what
Head|
Pred-Trans-Verb
Obj|
Bind1
Operator|
Aux|
could
Wh-Quest-SRE Wh-Focus Op Subj (Spec) Head
Pred-Trans-Verb Head Obj
Wh-Focus|
Wh-ORE1
What could he have taken?
Subj|
ORE|
Head|
Pron|
he
Spec|
Aux|
have
55
Wh-Question + Passive + Ditrans – Double R
Head|V|
given
Wh-Quest-SRE
Head|
Pred-Ditrans-Verb
IObj|
Bind2
Operator|
Aux|
could
Wh-Quest-SRE Wh-Focus Op Subj (Spec) Head
Pred-Ditrans-Verb Head (IObjxor) Obj (Recipxor)
Wh-Focus|
Wh-ORE1
|Head
|Wh-Proninan
|what
What could he have been given?
Subj|
ORE2
|Head
|Pronhuman
|he
Spec|
Aux
have beenObj
|Bind1
Grammatical Construction
Animacy determines
binding!
56
Wh-Question + Passive + Ditrans – Double R
Head|V|
given
Wh-Quest-SRE
Head|
Wh-Pronhuman
|who
Head|
Pred-Ditrans-Verb
IObj|
Bind1
Operator|
Aux|
could
Wh-Quest-SRE Wh-Focus Op Subj (Spec) Head
Pred-Ditrans-Verb Head (IObjxor) Obj (Recipxor)
Wh-Focus|
Wh-ORE1
Who could it have been given?
Subj|
ORE2
|Head
|Proninan
|it
Spec|
Aux
have beenObj
|Bind2
Animacy determines
binding!
57
Wh-Question + Passive + Ditrans – Double R
Head|V|
given
Wh-Quest-SRE
Head|
Wh-Pron|
who
Head|
Pred-Ditrans-Verb
Recip|
To-LRE
Operator|
Aux|
could
Wh-Quest-SRE Wh-Focus Op Subj (Spec) Head
Pred-Ditrans-Verb Head (IObjxor) Obj (Recipxor)
Wh-Focus|
Wh-ORE1
Who could it have been given to?
Subj|
ORE2
|Head
|Pron
|it
Spec|
Aux
have beenObj
|Bind2
P|
to
Obj|
Bind1
58
Grammatical Features of Nominals in English
• Definiteness – definite, indefinite, universal
• Number – singular, plural
• Animacy – human, animate, inanimate
• Gender – male, female
• Person – first, second, third
• Case – subj, obj, gen (2)
59
Why We Need Grammatical Features
• Definiteness:
– Give me the ball (definite)
– Give me a ball (indefinite)
• Number
– The men (plural) kick the ball (sing). They (plural)…
• Animacy
– The man (human) kicks the ball (inanimate). It (inanimate)…
• Gender
– The man (male) likes the woman (female). She (female)…
or
60
Simple Nominal
the man
singular human male
“the” projects definite to obj-refer-expr
“man” projects singular, human and male
definite
61
Grammatical Features of Clauses in English
• Tense – present, past, non-finite
• Aspect – perfect, progressive
• Modality – “could”, “should”, “must”…
• Polarity – negative
• Voice – active, inactive, passive
62
Simple Clause
…could not have gone
finite
present
perfect
active
“could”
negative
“could” projects finite present tense and modality
“not” projects negative polarity
“have gone” projects perfect aspect and active voice
“could not” recognized as a multi-word unit
63
Summary
• Representations matter!
• Language is complex!
• In complex systems, overall coherence is more important than overall simplicity!
– Einstein: make your theory as simple as possible, but no simpler!
– Computational implementation necessitates coherence
• If axioms + logical reasoning incoherence or a system that is obviously false, then question your axioms or your “logical” reasoning
– E.g. if innateness assumptions lead to overly complex representations, then question the innateness assumptions or the reasoning
64
Theoretical FoundationsLanguage Representation and Processing
• Double R Grammar
– Cognitive Linguistic theory of the grammatical encoding of referential and relational meaning
• Double R Process
– Psycholinguistic theory of the processing of English text into Double R Grammar based representations
• Double R Model
– Computational implementation using the ACT-R cognitive architecture and modeling environment
DoubleRTheory.com
65
Double R Process
• Serial, incremental, pseudo-deterministic language processor with a non-monotonic context accommodation mechanism (with limited parallelism) that is capable of making modest changes to the evolving representation
• Parallel, interactive, highly context sensitive, probabilistic mechanism which uses all available information to make the best choice at each choice point
• Processor presents the appearance and efficiency of deterministic processing, but is capable of handling the ambiguity which makes truly deterministic processing impossible
66
Double R Process
• Construction Driven Language Processing
– Activation, Selection and Integration of constructions corresponding to the linguistic input
• Lexical items in the input activate constructions
– Activation depends on current input, current context, and prior history of use
– “give” activates ditransitive verb construction
• Most highly activated construction is selected
• Selected construction is integrated with evolving representation
67
Double R Process
• Adhere to well-established cognitive constraints on Human Language Processing
• Don’t use any obviously cognitively implausible mechanisms!
• Adhering to cognitive constraints may actually facilitate the development of functional NLP systems
– Pushes development in directions that are more likely to be successful given inherently human nature of language processing
– You don’t know what you’re giving up when you adopt cognitively implausible mechanisms!
68
ACT-R Cognitive Architecture
• Theory of human cognition based on 40+ years of psychological research (Anderson, 2007)
– Computational implementation since 1993
• Combines a symbolic procedural memory implemented as a production system with a symbolic frame based declarative memory (DM)
• Includes modules for vision, audition, and motor processing
– Supports interaction with external world
http://act-r.psy.cmu.edu/
69
ACT-R Cognitive Architecture
• Procedural memory is the central component
– All modules interface to procedural memory via buffers (e.g. goal buffer, retrieval buffer, visual buffer)
• Productions have “subsymbolic” utilities
– Productions match against buffers of other modules
– Intentional module goal buffer is primary driver of behavior
– Matching production with highest utility is selected for execution
70
ACT-R Cognitive Architecture
• DM contains chunks which are frame based
– Chunk type + slot-value pairs (aka AVMs)
• Chunk types are organized into a single inheritance hierarchy
• Chunks have “subsymbolic” activations based on current input, current context and prior history of use
• Chunks are retrieved from memory by execution of a production which specifies a retrieval template
– DM chunk with highest activation that matches retrieval template is retrieved (soft constraint retrieval)
71
ACT-R Cognitive Architecture
Intentional Module(not identified)
Declarative Module(Temporal/Hippocampus)
Goal Buffer(DLPFC)
Retrieval Buffer(VLPFC)
Matching (Striatum)
Execution (Thalamus)
Selection (Pallidum)
Pro
du
ctio
ns
(Bas
al G
ang
lia)
Visual Module(Occipital/etc)
Manual Module(Motor/Cerebellum)
Visual Buffer(Parietal)
Manual Buffer(Motor)
External World
modules &
buffers
mapped to
brain
regions
72
ACT-R Cognitive Architecture
• Supports timing of cognitive processing
– Production execution takes 50 ms
– DM chunk retrieval time depends on level of activation of retrieved chunk
– Timing of motor events based on Fitts’ Law
– Used for empirical validation of models
• Provides a powerful debugging environment
73
Architectural Constraints
• No language specific module
– although buffers and productions accessing buffers might be viewed as a module
• Forward chaining productions with no backtracking
• Limited pattern matching – not full unification
• Serial bottleneck
– only one production can execute at a time
• Modules interact with production system via buffers
– buffers have limited capacity for storing current context
• Activation spreads in parallel
• Activation and Utility subject to noise
74
Constraints on Human Language Processing
• Visual World Paradigm (Tanenhaus et al. 1995)
– Subjects presented with a visual scene
– Subjects listen to auditory linguistic input describing scene
• Immediate determination of meaning
– Subjects look immediately at referents of linguistic expressions, sometimes before end of expression
• Incremental processing
• Interactive processing (Trueswell et al. 1999)
– Ambiguous expressions are processed consistent with scene
“the green…”
“put the arrow on the paper into the box”
75
• According to Crocker (1999), there are three basic mechanisms for dealing with ambiguity in natural language
– Serial processing with backtracking or reanalysis
– Deterministic processing with lookahead (Marcus 1980)
– Parallel processing with alternative analyses carried forward in parallel (Gibson 1991; MacDonald, Pearlmutter & Seidenberg 1994; Trueswell & Tanenhaus 1994)
• According to Lewis (2000) “…existing evidence is compatible only with probabilistic serial-reanalysis models, or ranked parallel models augmented with a reanalysis component.”
• According to Gibson & Pearlmutter (2000) “noncompetitive ranked parallel models” are most consistent with the empirical evidence
Constraints on Human Language Processing
76
• Serial and deterministic with reanalysis for pathological input
– Empirical evidence that we don’t carry forward all representations in parallel – Garden Path Sentences
• “The horse raced past the barn fell” (Bever 1970)
• “The old train the young” (Just & Carpenter, 1987)
– Empirical evidence that we don’t retract previously built representations (Christianson et al. 2001)
• “While Mary dressed the baby sat up on the bed”
– In a post test, a majority of subjects answered yes to the question “Did Mary dress the baby?”
– Processing doesn’t slow down with increasing length of non-pathological input
– Typically only aware of a single interpretation
Constraints on Human Language Processing
77
• Parallel and probabilistic with reanalysis for pathological input
– Empirical evidence that we may carry forward multiple representations in parallel – Garden Path Effects can be eliminated with sufficient context
– Empirical evidence that dispreferred representations can affect processing time (Gibson & Pearlmutter 2000)
• It’s extremely difficult to empirically falsify either
– Could be parallel slow down or occasional switch between serial alternatives that causes effect
• Don’t have all the answers, but maybe it’s both!
– A parallel, probabilistic substrate may make a pseudo-deterministic serial processing mechanism possible!
Constraints on Human Language Processing
78
Cognitively Implausible Mechanism
• Serial processing with algorithmic backtracking
– Algorithmically simple, but…
• Computationally intractable for NLP which is highly ambiguous
• Context which led to dead end is retracted on backtracking
–Why give up the context?
– How do we know it’s a dead end?
• Practical Consequences
– No hope for on-line processing in real-time in large coverage NLP system
– No hope for integration with speech recognition system
– Performance degrades with length of input
– Can’t easily handle degraded or ungrammatical input
79
Cognitively Implausible Mechanism
• Multiple pass or multi-stage parsing
– Separate passes tokenize and assign part of speech
• Can’t use full context in each pass
• Errors get propagated
– Separate pass builds structure
• Typically limited to using part of speech of words
– Separate pass determines meaning
• Practical Consequences
– Difficult to do on-line processing in real-time
– Can’t easily integrate with speech recognition
– Performance degrades with length of input
– Limited context available to handle ambiguity at each stage
80
Outrageously Implausible Mechanism!
• Parsing input from right to left (Microsoft NLP system)
– May have engineering advantages, but…
• Presumes a staged approach to NLP
• Completely ignores cognitive plausibility
• Practical consequences
• Impossible to do on-line processing in real-time
–Must wait for end of input
• Nearly impossible to integrate with speech recognition
81
Cognitively Plausible Mechanism?
• Deterministic processing with lookahead
– Many ambiguities resolved by looking ahead a few words, but…
• Don’t know how far to look ahead
– Cognitive plausibility improved by limiting amount of lookahead
• 3 constituent lookahead (Marcus 1980)
• 1 word lookahead (Henderson 2004)
• Practical consequences
– Difficult to use with eager algorithms for which there is good empirical evidence (immediate determination of meaning)
– The smaller the lookahead, the less deterministic
82
Cognitively Plausible Mechanism?
• Parallel processing with multiple analyses carried forward
– “Full parallelism – where every analysis is pursued – is not psychologically possible” (Crocker 1999)
– Cognitive plausibility improved by limiting number of analyses carried forward and ranking alternatives (bounded ranked parallelism) and not having analyses compete
• Practical Consequences
– The longer and more ambiguous the input, the less likely to have the correct representation in the parallel spotlight – necessitating a reanalysis mechanism
– Impractical if multiple representations must be built at each choice point as opposed to just being selected
83
Cognitively Plausible Mechanism
• Pseudo-deterministic, serial processing mechanism with context accommodation operating over a parallel, probabilistic substrate
– Parallel, probabilistic substrate proposes best alternative given current context
– Processor proceeds as though it were serial and deterministic, but accommodates the subsequent input as needed
– Integrates the advantages of parallel processing with an essentially serial processing mechanism
• Practical Consequences
– How to accommodate when things go seriously wrong?
– Mechanism is essentially non-monotonic
84
Cognitively Plausible Mechanism
• Serial, Pseudo-deterministic processing and Context Accommodation
– Uses ACT-R’s production system
– Builds structure
– Limited parallelism
• Parallel, Probabilistic processing
– Uses ACT-R’s declarative memory
– Retrieves existing structure from memory
85
• If current input is unexpected given the prior context, then accommodate the input
– Adjust the representation
– Coerce the input into the representation
• The following example demonstrates the context accommodation mechanism
– “no target airspeed or altitude restrictions”
Context Accommodation
86
no
“no” object referring expression
“no” projects obj-refer-expr and functions as specifier
“head-indx” indicates head expected
“bind-indx” provides index for binding
87
no target
“target” head
tree structures generated automatically with dynamic visualization
tool (Heiberg, Harris & Ball 2007) based on phpSyntaxTree
software (Eisenberg & Eisenberg)
integration
88
no target airspeed
“airspeed” head
Accommodation
of second noun via
function shift and overriding
override
function shiftintegration
89
no target airspeed or altitude
“or altitude” conj
Conjunction integrated into
noun
integration
90
no target airspeed or altitude restrictions
“restrictions” head
Appearance of parallel processing!
Accommodation
of new head via
function shift and override
function shift
override
integration
91
• Coercion
– “the hiking of Mt Lemon” – head of nominal
• “hiking” construed objectively, arguments not expressed (“of Mt Lemon” functions as a modifier)
– “a Bin Laden supporter”
• Proper Noun functions as modifier
– “you’re no Jack Kennedy”
• Proper Noun functions as head (following specifier)
– “the newspaper boy porched the newspaper” – nonce expression (H. Clark 1983)
• “porched” construed as transitive action
Types of Accommodation
92
• Override
– Single word vs. Multi-Word Expression (MWE)
• “kicked…” transitive verb
– “kicked the bucket” idiomatic expression
• “take…” transitive verb
– “take a hike” “take five” “take time” “take place” “take out” “take my wife, please” “take a long walk off a short pier” … many idiomatic expressions
• Not possible to carry all forward in parallel
– Morphologically simple vs. complex
• “car…” noun (sing)
– “carpet…” noun (sing)
– “carpets” noun (plur)
– “carpeting” noun (sing) or verb
Types of Accommodation
93
• Grammatical Function Shift
– “he gave it to me”
• direct object (initial preference due to inanimacy)
– “he gave it the ball”
• direct object (initial preference) indirect object
– “he gave her the ball”
• indirect object (initial preference due to animacy)
– “he gave her to the groom”
• indirect object (initial preference) direct object
Types of Accommodation
94
• Nominal Head Override
• “he gave her the dog biscuit” head = her
• “he gave her dog the biscuit” head = dog
• Grammatical Function “Juggling”
– “he gave the…” indirect object
– “he gave the very old bone…” direct object
– “he gave the very old bone collector…” indirect object
– “he gave the very old dog…” indirect object
– “he gave the very old dog collar…” direct object
– “he gave the very old dog to me” direct object
Types of Accommodation
95
• Grammatical Function Shift
– “he said that…”
• In context of “said”, “that” typically functions as a complementizer
– But subsequent context can cause a function shift from
• complementizer
– “he said that she was happy”
• To nominal specifier to
– “he said that book was funny”
• To nominal head
– “he said that.”
Types of Accommodation
96
• Grammatical Function Shift
– “pressure” vs. “pressure valve” vs. “pressure valve adjustment” vs. “pressure valve adjustment screw” vs. “pressure valve adjustment screw fastener” vs. “pressure valve adjustment screw fastener part” vs. “pressure valve adjustment screw fastener part number”
• Serial nouns (and verbs) incrementally shift from head to modifier function as each new head is processed
• Functions like lookahead, but isn’t limited
• Not clear if a bounded ranked parallel mechanism can handle this!
– 2n possibilities if head or modifier at each word
Types of Accommodation
97
• Modulated Projection
– “the rice” vs. “rice”
– “the” projects a nominal and functions as a specifier
– In the context of “the” “rice” is integrated as the head of the nominal
– When there is no specifier, “rice” projects a nominal and functions as the head without separate specification
Types of Accommodation
nominal
spec
the
head
rice
vs. head
rice
nominal
“the rice” “rice”
98
Grammatical Feature Accommodation
99
• Context Accommodation is part and parcel of the pseudo-deterministic processing mechanism
– Not viewed as a repair mechanism (Lewis 1998)
• Processor proceeds as though it were deterministic, but accommodates the input as needed
• Gives the appearance of parallel processing in a serial, deterministic mechanism
Summary of Context Accommodation
100
Combining Serial, Deterministicand Parallel, Probabilistic Mechanisms
Tree Supertagging
Construction Activation
& Selection
Supertag
Stapling
Construction
Integration
Rule ApplicationLexical Rule Selection
Rule
SelectionRule Application
Rule Selection & Application
Parallel Probabilistic
Serial Deterministic
Parallel Distributed Processing
CFG
PCFG
Lexicalized
PCFG
Double R
Probabilistic
LTAG
PDP
Pseudo
Deterministic
Range
Nondeterministic
The parallel probabilistic substrate makes a pseudo-deterministic serial processing mechanism possible!
101
Questions?
top related