Connectionist Models of Language

1
Connectionist Models of Language

• Stephen E. Nadeau, M.D.
• Malcom Randall DVA Medical Center
• Department of Neurology, University of Florida
  College of Medicine, Gainesville, FL

2
(No Transcript)
3
Other References

• Nadeau SE. Connectionist models and language.
  In Nadeau SE, Gonzalez Rothi LJ, Crosson B, eds.
  Aphasia and Language Theory to Practice. New
  York, Guilford Publications, 2000299-347.
• Nadeau SE. Phonology A review and proposals from
  a connectionist perspective. Brain Lang
  200179511-579.
• Nadeau SE, Gonzalez Rothi LJ. Rehabilitation of
  language disorders. In Ponsford J (Ed).
  Cognitive and behavioral rehabilitation From
  neurobiology to clinical practice. New York
  Guilford, 2004129-174.
• H.L. Roth, S.E. Nadeau, and K.M. Heilman, Naming
  concepts evidence of two routes, Neurocase
  20061261-70.

4
(No Transcript)
5
(No Transcript)
6
Plaut DC. Relearning after damage in
connectionist networks toward a theory of
rehabilitation. Brain Lang 19965225-82
7
(No Transcript)
8
McClelland JL, Rumelhart DE. A distributed model
of human learning and memory. In McClelland JL,
Rumelhart DE, PDP Research Group, eds. Parallel
Distributed Processing. Cambridge MIT Press,
1986170-215. vol 2).
9
Rumelhart DE, Smolensky P, McClelland JL, Hinton
GE. Schemata and sequential thought processes in
PDP models. In McClelland JL, Rumelhart DE, the
PDP Research Group, eds. Parallel distributed
processing. Cambridge, Massachusetts MIT Press,
19867-57. vol 2).
10
Rumelhart DE, Smolensky P, McClelland JL, Hinton
GE. Schemata and sequential thought processes in
PDP models. In McClelland JL, Rumelhart DE, the
PDP Research Group, eds. Parallel distributed
processing. Cambridge, Massachusetts MIT Press,
19867-57. vol 2).
11
Rumelhart DE, Smolensky P, McClelland JL, Hinton
GE. Schemata and sequential thought processes in
PDP models. In McClelland JL, Rumelhart DE, the
PDP Research Group, eds. Parallel distributed
processing. Cambridge, Massachusetts MIT Press,
19867-57. vol 2).
12
(No Transcript)
13
(No Transcript)
14
Rumelhart DE, McClelland JL. On learning the past
tenses of English verbs. In McClelland JL,
Rumelhart DE, the PDP Research Group, eds.
Parallel distributed processing. Cambridge,
Massachusetts MIT Press, 1986216-271. vol 2).
15
Plaut DC, McClelland JL, Seidenberg MS, Patterson
K. Understanding normal and impaired word
reading computational principles in
quasi-regular domains. Psychol Rev
199610356-115.
16
Seidenberg MS, McClelland JL. A distributed,
developmental model of word recognition and
naming. Psych Rev 198996523-568
17
Nadeau SE. Phonology A review and proposals from
a connectionist perspective. Brain Lang
200179511-579.
18
Ive been retired since 1972 with /cardimiapesun/
(cardiomyopathy)Ten per cent of the
peoplewith the /catraps/ (cataracts) has the
problem with the retina.I was in the /bizzet/
(business) of records/fotegraph/ (phonograph)
recordsfor the/shusta (distribution?)In other
words, I was a /eksiev/ (executive).Look, I
think its /porten/ (important).I cant
say/tivelsha/, /diveltsher/ (television), uh TV.
19
Nadeau SE. Phonology A review and proposals from
a connectionist perspective. Brain Lang
200179511-579.
20
Properties of PDP Networks

• The knowledge is in the connections
• A network supports processing, working and
  long-term memory
• Hidden units nonlinearity support associations
  between orthogonal representations
• Distributed representations
• Content-addressable memory
• Graceful degradation
• Inference, generalization, confabulation
• Bottom-up and top-down processing
• Learning of implicit rules, structure of
  knowledge domain through experience

21
Roth HL, Nadeau SE, Hollingsworth AL,
Cimino-Knight AM, Heilman KM. Naming Concepts
Evidence of Two Routes. Neurocase 20061261-70.
22
Grammar

• Syntax (knowledge of word order and sentence
  structure)
• Sentence organization (verb argument structure,
  embedded clauses, passive voice constructions)
• Phrase structure rules
• Grammatic morphology (grammatic modifications of
  words words of primarily grammatic function)

23
Genesis of Grammar

• Chomsky a grammar generator
• A connectionist conceptualization
• Sentence organization reflects the ways in which
  the brain manipulates distributed concept
  representations
• Phrase structure rules grammatic morphology are
  emergent products of pattern associator networks
  responsible for articulatory and inscriptional
  output that incorporate sequence knowledge
• Several aspects of grammar are dependent on
  working memory systems (sustained selective
  engagement)

24
Neural Network Representation of Word Classes

• Concrete nouns
• Distributed concept representations
• Adjectives, intransitive verbs, auxiliar verbs
• Modification of distributed concept
  representations
• Main transitive verbs, locative prepositions
• Reciprocal modification and linkage of two or
  more distributed concept representations
• Abstract words
• Juxtaposition of multiple distributed concept
  representations limbic distributed
  representations

25
Concrete Nouns
26
Adjectives, Intransitive VerbsModification of
Distributed Concept Representations

• The obese, pockmarked, oily-haired, slovenly,
  unctuous, check-shirted, plaid-jacketed man with
  the striped pants, food-stained paisley tie,
  goatee, wire-rimmed glasses, bundle of pens in
  his pocket, and clip board in his hand

27
Main Transitive Verbs, Locative
PrepositionsReciprocal modification and linkage
of distributed concept representations

• Verb argument structure
• The old manAgent shot the burglarGoal.
• The manAgent gave flowersTheme to MaryGoal.
• HeAgent knew (Mary would arrive soon)Theme.
• Locative prepositions
• The book is on the table.

28
Abstract Words

• Juxtaposition of distributed concept
  representations limbic distributed
  representations
• Intellectual

29
Brocas Aphasia

• Cinderella uh scrubbing and uh hard worker
  and wants to go a ball. Step fa mother uh I
  want to go. Cant do it. Not no well why not?
  I dont know. Because uh I uh uh scrubbing uh
  uh watchacallit uh uh working object and so
  clean out bad.
• Cinderella uh seems like animals love her.
  Because uh dress Horse help her. And
  stepmother uh uh ruin dress. I dont know why.
  Probably because cute. Mad because uh uh
  stepmother really ugly. Dress broken and now
  cant do it because what dress? Mother Teresa
  not exactly uh uh magic godmother! Thats it.
  Godmother dress. Dont worry. I can fix it.
  And beautiful.
• Now carriage where? I dont know how do you go
  here? Because castle big. Probably uh mountain
  castle. How do you get uh here? Oh dont worry.
  I can uh pumpkin and uh servants and horse
  and beautiful carriage and so magic. But, better
  midnight be here because uh uh pumpkin carriage
  gone. Midnight be here .
• Thompson (2001)

30
Brocas Aphasia
31
Brocas Aphasia

• Agrammatism
• Impaired sentence organization
• Simplification of syntax
• Greater difficulty accessing nouns than verbs
• Greater impairment in use of verbs with complex
  argument structure
• Limited lexical priming
• Resistance to concatenating adjectives
• Deficits in selective engagement of distributed
  concepts representations and manipulation of
  those representations

32
Phrase Structure Rules

• Word sequence knowledge an extrapolation of
  phonemic sequence knowledge

33
Grammatic Morphology

• Free grammatical morphemes articles, auxiliary
  verbs, conjunctions, some prepositions
• Bound grammatic morphemes e.g., affixes
  specifying case, number or tense

34
Grammatic Morphology

• Articles
• Sequence knowledge underlying phrase structure
  rules
• Lexical semantic knowledge definite vs
  indefinite (but also case, number, gender)
• Working memory of current linguistic context
• Article production in Brocas aphasias

35
Conduction Aphasia

• Ive been retired since 1972 with
  /cardimiapesun/(cardiomyopathy).
• Ten percent of the people with the
  /catraps/(cataracts) has the problem with the
  retina.
• I was in the /bizzet/(business) of
  records/fotegraphy/(phonograph) recordsfor
  the/shusta/(distribution?)In other words, I was
  a /eksiev/(executive).
• Look, I think its /porten/(important).
• I cant say/tivelsha/, /diveltsher/(television),
  uh TV.

36
Conduction Aphasia
37
Wernickes Aphasia

• Tell me what happened that brought you here.
• I been going all right caut so far. They got
  hold of my lackid last night. Yard in the back.
  I dont know what all kapt it. Old himbone and
  boy I hadnt seen crosswayson time and best
  size. You asked when they gave me tham garden
  sizm made me so sorejust bugarden you know. I
  didnt go a slooten until way in the night-time
  afterwards. Course there was a long lot of,
  somebodys bunyangin or something.

38
Wernickes Aphasia
39
Transcortical Sensory Aphasia
40
Other Aphasias

• Anomic
• Transcortical motor
• Mixed transcortical

41
Summary Domains of Neural Network Knowledge
Underlying Language Function

• Lexical semantic function
• Semantic
• Sequence
• Pattern associators linking
• Semantic sequence
• knowledge (the basis for
• the phonological lexicons)
• Grammar
• Elaboration of sequence knowledge (affixes,
  phrase structure rules)
• Lexical syntactic
• Selection of an articulatory sequence by
  configurations of reciprocally related concept
  representations (transitive verbs, locative
  prepositions)
• Selection of an articulatory sequence by
  configurations of yet to be spoken concept
  representations and working memory of already
  spoken representations (articles, pronouns, many
  auxiliary verbs)

42
Summary of Aphasia Types

• Brocas
• Grammar, articulation
• Conduction
• Phonological sequence
• Wernickes
• Lexical semantic,
• phonological sequence
• TCSA
• Semantic, lexical semantic
• Anomic
• Semantic, lexical semantic in output
• TCMA