Current Research - PowerPoint PPT Presentation

1 / 21
About This Presentation
Title:

Current Research

Description:

SNePS Research Group (SNeRG) Center for Cognitive Science. Cognitive Science ... Joint research with Michael Kibby, GSE/LAI. CVA: From algorithm to curriculum ... – PowerPoint PPT presentation

Number of Views:39
Avg rating:3.0/5.0
Slides: 22
Provided by: rapa
Category:
Tags: current | lai | research

less

Transcript and Presenter's Notes

Title: Current Research


1
Current Research
  • William J. Rapaport
  • http//www.cse.buffalo.edu/rapaport
  • CVA Research Group
  • SNePS Research Group (SNeRG)
  • Center for Cognitive Science

2
Cognitive Science
  • def interdisciplinary study of mind/cognition
  • (AI, PHI, PSY, LIN, etc.)
  • Artificial Intelligence
  • (good old-fashioned classical symbolic AI)
  • Computational philosophy
  • Knowledge representation for natural-language
    understanding
  • Computational linguistics
  • Knowledge representation and reasoning

3
Computational Philosophy
  • Philosophy as source of computational problems
  • computational solutions to philosophical
    problems
  • Understanding understanding
  • Syntax suffices for semantics
  • How a computational cognitive agent can pass a
    Turing Test
  • E.g., SNePS/Cassie
  • overcome the Chinese-Room-Argument objections
    to
  • the Turing Test
  • Its possible to pass TT without really thinking

4
Knowledge Representation for Natural-Language
Understanding
  • Computational contextual vocabulary acquisition
    (CVA)
  • Based on Karen Ehrlichs 1995 CS PhD dissertation
  • from NSF ROLE Program
  • Research On Learning and Education
  • In STEM
  • Science, Technology, Engineering, and Mathematics
  • Formerly known as SMET ?
  • Joint research with Michael Kibby, GSE/LAI

5
CVA From algorithm to curriculum
  • People do incidental CVA
  • Know more words than explicitly taught
  • Learn the meanings of most words from context
  • Unconsciously
  • How?

6
CVA From Algorithm to Curriculum (continued)
  • People do deliberate CVA
  • Youre reading
  • You understand everything you read, until
  • You come across a new word
  • Not in dictionary
  • No one to ask
  • So, you try to figure out its meaning
  • from context background knowledge
  • How?

7
What does brachet mean?
8
(From Malorys Morte DArthur page in
brackets)
  • 1. There came a white hart running into the hall
    with a white brachet next to him, and thirty
    couples of black hounds came running after them.
    66
  • As the hart went by the sideboard, the white
    brachet bit him. 66
  • The knight arose, took up the brachet and rode
    away with the brachet. 66
  • A lady came in and cried aloud to King Arthur,
    Sire, the brachet is mine. 66
  • There was the white brachet which bayed at him
    fast. 72
  • 18. The hart lay dead a brachet was biting on
    his throat, and other hounds came behind. 86

9
CVA From algorithm (continued)
  • CVA studied by computational linguists
  • word-sense disambiguation
  • Given ambiguous word and list of all meanings,
  • determine the correct meaning
  • Multiple-choice test ?
  • CVA as we do it
  • Given new word, compute its meaning
  • Essay question ?

10
Implementation
  • SNePS (Stuart C. Shapiro SNeRG)
  • Intensional, propositional semantic-network
    knowledge-representation reasoning system
  • Node-based path-based reasoning
  • I.e., logical inference generalized inheritance
  • SNeBR belief revision system
  • Used for revision of definitions
  • SNaLPS natural-language input/output
  • Cassie computational cognitive agent

11
How It Works
  • SNePS represents
  • background knowledge text information
  • in a single, consolidated semantic network
  • Algorithms search network for slot-fillers for
    definition frame
  • Search is guided by desired slots
  • E.g., prefers general info over particular info,
    but takes what it can get

12
Cassie learns what brachet meansBackground
info about harts, animals, King Arthur, etc.No
info about brachetsInput formal-language
version of simplified EnglishA hart runs into
King Arthurs hall. In the story, B17 is a
hart. In the story, B18 is a hall. In the
story, B18 is King Arthurs. In the story, B17
runs into B18.A white brachet is next to the
hart. In the story, B19 is a brachet. In the
story, B19 has the property white. Therefore,
brachets are physical objects. (deduced while
reading Cassie believes that only physical
objects have color)
13
--gt (defineNoun "brachet") Definition of
brachet Class Inclusions phys obj,
Possible Properties white, Possibly Similar
Items animal, mammal, deer, horse,
pony, dog,
I.e., a brachet is a physical object that can be
white and that might be like an animal,
mammal, deer, horse, pony, or dog
14
A hart runs into King Arthurs hall. A white
brachet is next to the hart. The brachet bites
the harts buttock. The knight picks up the
brachet. The knight carries the brachet. --gt
(defineNoun "brachet") Definition of brachet
Class Inclusions animal, Possible Actions
bite buttock, Possible Properties small,
white, Possibly Similar Items mammal, pony,
15
  • A hart runs into King Arthurs hall.A white
    brachet is next to the hart.The brachet bites
    the harts buttock.The knight picks up the
    brachet.The knight carries the brachet.The lady
    says that she wants the brachet.
  • The brachet bays at Sir Tor. background
    knowledge only hunting dogs bay
  • --gt (defineNoun "brachet")
  • Definition of brachet
  • Class Inclusions hound, dog,
  • Possible Actions bite buttock, bay, hunt,
  • Possible Properties valuable, small, white,
  • I.e. A brachet is a hound (a kind of dog) that
    can bite, bay, and hunt,
  • and that may be valuable, small, and white.

16
General Comments
  • Systems behavior ? human protocols
  • Systems definition ? OEDs definition
  • A brachet is a kind of hound which hunts by
    scent
  • Our inferential search algorithms are syntactic
    semantics in action

17
CVA to curriculum
  • CVA studied by
  • Psychologists
  • Reading specialists
  • L1 researchers
  • L2 researchers/educators (e.g., ESL)
  • Contextual cues to aid in CVA
  • Spatial/temporal info, class membership, etc.
  • But what to do with them?

18
CVA to curriculum
  • Is this an algorithm? (Clarke Nation 1980)
  • Look at word context
  • determine POS
  • Look at grammatical context
  • who does what to whom?
  • Look at wider context
  • Search for spatial/temporal/classification cues
  • Guess the word check your guess

19
CVA From Algorithm to Curriculum
  • guess the word
  • then a miracle occurs
  • Surely we computer scientists can be
    more explicit!

20
CVA From algorithm to curriculum and back
again!
  • Treat guess as a procedure call
  • Fill in the details with our algorithm
  • Convert the algorithm into a curriculum
  • To enhance students abilities to use deliberate
    CVA strategies
  • To improve reading comprehension of STEM texts
  • And use knowledge gained from CVA case studies to
    improve the algorithm
  • I.e., use Cassie to learn how to teach humans
  • use humans to learn how to teach Cassie

21
Problem in ConvertingAlgorithm into Curriculum
  • A knight picks up a brachet and carries it away
  • Cassie
  • Has perfect memory
  • Is perfect reasoner
  • Automatically infers that brachet is small
  • People dont always realize this
  • May need prompting How big is the brachet?
  • May need relevant background knowledge
  • May need help in drawing inferences
  • Teaching CVA ? teaching general reading
    comprehension
  • Vocabulary knowledge correlates with reading
    comprehension

22
CVA Science Education
  • Original goal CVA in for science education
  • Use CVA to improve reading of STEM materials
  • A side effect CVA as science education
  • There are no ultimate authorities to consult
  • No answers in the back of the book of life!
  • As true for physics as for reading
  • ? Goal of education
  • To learn how to learn on ones own
  • Help develop confidence desire to use that
    skill
  • CVA as sci. method in miniature furthers this
    goal
  • Find clues/evidence (gathering data)
  • Integrate them with personal background knowledge
  • Use together to develop new theory (e.g., new
    meaning)
  • Test/revise new theory (on future encounters with
    word)

23
Conclusion
  • Developing a computational theory of CVA,
  • which can become
  • a useful educational technique for improving
    STEM vocabulary and reading comprehension
  • a model of the scientific method
  • a useful tool for learning on ones own.

24
Meetings Websites
  • SNeRG
  • Fridays, 900-1100, Bell 242
  • starting Aug. 29 (tomorrow)
  • www.cse.buffalo.edu/sneps
  • Center for Cognitive Science
  • Wednesdays, 200-400, Park 280
  • starting Sept. 3
  • wings.buffalo.edu/cogsci
  • CVA
  • Mondays, 200-330, Baldy 17
  • starting Sept. 8
  • www.cse.buffalo.edu/rapaport/cva.html

25
Courses
  • Fall 2003
  • CSE 663 Knowledge Representation Reasoning
  • Spring 2004
  • CSE 510 Philosophy of Computer Science
  • CSE 7xx Seminar (probably on CVA)

26
Question (objection)
  • Why not use a dictionary?
  • Because
  • People are lazy (!)
  • Dictionaries are not always available
  • Dictionaries are always incomplete
  • Dictionary definitions are not always useful
  • chaste df pure, clean /? new dishes are
    chaste
  • Most words learned via incidental CVA,
  • not via dictionaries

27
Question (objection)
  • Teaching computers ? teaching humans!
  • But
  • Our goal
  • Not teach people to think like computers
  • But to explicate computable teachable methods
    to hypothesize word meanings from context
  • AI as computational psychology
  • Devise computer programs that are essentially
    faithful simulations of human cognitive behavior
  • Can tell us something about human mind.
  • We are teaching a machine, to see if what we
    learn in teaching it can help us teach students
    better.
Write a Comment
User Comments (0)
About PowerShow.com