The Loose Speak Project James Fan Knowledge-Based Systems Research Group University of Texas at Austin May 8, 2002

1
The Loose Speak ProjectJames FanKnowledge-Based
Systems Research GroupUniversity of Texas at
AustinMay 8, 2002
2
Outline

• Loose speak overview
• Two types of LS
• Complex nominal interpretation
• Metonymy
• Future work on LS

3
Loose Speak

• Loose speak(LS) the phenomenon that human
  listeners are able to correctly interpret a
  speaker's imprecise utterance.
• Relevance
• LS common in human communication, but rarely
  supported in human-computer-interaction.
• Lack of LS requires SMEs talk in precise terms to
  KB, makes KA tedious and error prone, and
  contributes to the brittleness of KB.

Here's a KA example without LS ...
4
Mitochondrion Catalysis
5
Current KA Process
6
Current KA Process
7
Current KA Process
8
Correct Representation
9
Loose Speak Project

• Task given an imprecise expression, correctly
  form an interpretation consistent with the
  existing KB.
• Goal
• To show that (semi)-automatic interpretation of
  imprecise terms is possible.
• It can accelerate KA.

Here's how the previous example works with LS ...
10
KA With LS
11
KA With LS
After clicking on the See CMAP link
12
KA With LS
13
Outline

• Loose speak overview
• Two types of LS
• Complex nominal interpretation
• Metonymy
• Future work on LS

14
Complex Nominal Interpretations

• Complex nominal is an expression that has a head
  noun proceeded by a modifying element. Levi '78
  the semantic relation between the two is
  implicit.
• Marble statue statue made of marble
• Animal cell cell that is the basic structural
  unit of an animal
• Metal detection detecting metal.
• Complex nominal interpretation task given a
  complex nominal, return the semantic relation
  between the head noun and it's modifying element.

15
Related Work

• A set of rules that includes most of the semantic
  relations in complex nominals Levi '78.
• Hand coded rules Leonard '84.
• Statistically learned rules Lauer '95.
• Learned rules under the user's guidance Barker
  '98.

16
Our Approach

• Given a complex nominal made of two concepts H
  M,
• Search KB up to certain depth, return any
  relations between H any of M's
  super/subclasses, or vice-versa.
• If no relation is returned, select from a set of
  templates based on domain/range match.

Let's see what the templates are ...
17
Templates

• Templates A set of 32 relations, which includes
  most of the common semantic relations occur in
  complex nominals.
• Example
• (a H with (element-type ((a M))))
• (a H with (is-part-of ((a M))))
• ...
• Zero, one, or multiple relations may be returned.

Let's step through a few examples ...
18
Example 1

• Given a complex nominal made of two concepts H
  M,
• Search KB up to certain depth, return any
  relations between H any of M's
  super/subclasses, or vice-versa.
• If no relation is returned, select from a set of
  templates based on domain/range match.

• M Animal H Cell

• Do breadth-first KB search, and found the
  following in KB

(every Cell has (is-basic-structural-unit-of ((a
Organism)))

• Return

(a Cell with (is-basic-structural-unit-of ((a
Animal)))
19
Example 2

• Given a complex nominal made of two concepts H
  M,
• Search KB up to certain depth, return any
  relations between H any of M's
  super/subclasses, or vice-versa.
• If no relation is returned, select from a set of
  templates based on domain/range match.

• M Cell H Locomotion

• Do breadth-first KB search, and found the
  following in KB

(every Locomotion has (object ((a
Tangible-Entity))))

• Return

(a Locomotion has (object ((a Cell))))
20
Example 3

• M Bond H Energy.

• Given a complex nominal made of two concepts H
  M,
• Search KB up to certain depth, return any
  relations between H any of M's
  super/subclasses, or vice-versa.
• If no relation is returned, select from a set of
  templates based on domain/range match.

• Do breadth-first KB search, and found the nothing
  in KB

• Select from the templates

• (a Create with (raw-material ((a Bond))) (result
  ((a Energy)))) -- match.

• (a Create with (result ((a Bond))) (agent ((a
  Energy))) -- match.

• (a Energy with (element-type ((a Bond)))) --
  mismatch.
• ... ...

21
Performance Measurements

• Precision C / A, where C number of instances
  in which a correct answer is returned, A number
  of instances in which an answer is returned.
• Recall C / T, where C number of instances in
  which a correct answer is returned, T the total
  number of test instances.
• Avg. ans. length L / A, where L total lengths
  of all the answers returned, A number of
  instances in which an answer is returned.

22
Evaluation

• Tested on 2 sets of data from Alberts Alberts,
  el with a total of 184 test examples.
• Our approach has similar precision and recall
  values as the templates method does.
• Our approach has much shorter average answer
  length.
• The distribution of answer lengths is bi-modal
  65 answers have 1 or 2 choices 19 have 9 or 10
  choices.

23
Evaluation (Continued)

• Our approach is compared to a templates based
  method because the templates resemble the
  hand-coded rules approach.
• Mistakes from data set 2 are caused by
• invalid data entries (e.g. phosphate residue -gt
  phosphate substance translation)
• incomplete KB (e.g. topic slot missing from KB).

24
Future Work for Complex Nominal Interpretation

• Gather more data for further evaluation.
• Integrate the KB search with the templates.

25
KB Search And Templates Integration

• KB search is bounded by a certain depth.
• The selections from the templates can direct
  deeper searches.
• Example
• Cell Ribosome.
• KB search found nothing.
• Templates
• (a Ribosome with (is-part-of ((a Cell))))
• (a Ribosome with (material ((a Cell))))
• Deeper search reveals
• (a Ribosome with (element-type-of ((a Aggregate
  with (is-part-of ((a Cytoplasm with (is-part-of
  ((a Cell))))))))))

26
Outline

• Loose Speak Overview
• Two types of LS
• Complex Nominal interpretation
• Metonymy
• Future work on LS

27
Metonymy

• Metonymy a figurative speech in which "one
  entity the metonym is used to refer to another
  the referent that is related to it". Lakoff
  Johnson '80
• Example
• Joe read Shakespeare. It was good.
• Metonymy resolution task given an input
  expression denoting a piece of knowledge,
  identify any occurrence of metonymy, uncover the
  referent, and returned the paraphrased version of
  the input expression.

28
Relevance of Metonymy Resolution
29
Traditional Approaches Fass '91Hobbs
'93Markert Hahn '97Harabagiu '98

• Given an input (often in the form of sentences in
  natural language)
• Detect metonymy based on detection of type
  constraints,
• Resolve metonymy based on a search in metonymy
  space.
• Anaphora is used to validate the result of the
  metonymy resolution.

Let's what the metonymy space is ...
30
Metonymy Space

• Metonymy space the set of entities related to
  the metonym.
• Metonymy space construction
• given the metonym A, return set S X exists
  A-r1-A1-r2-A2- ... -rn-X where r1, r2, ..., rn
  are members of a fixed set of slots, such as
  has-part, material, agent, result, etc., and A1,
  A2, ..., X are frames.
• Given A Shakespeare, S Shakespeare, His
  Head, His Text, ... because
• Shakespeare, r1 self
• Shakespeare-has-part-His Head, r1 has-part
• Shakespeare-agent-of-Write-result-His Text, r1
  agent-of, A1 Write, r2 result

Let's step through a few examples ...
31
Metonymy Example 1 (Traditional Approach)

• Given an input (often in the form of sentences in
  natural language)
• Detect metonymy based on detection of type
  constraints,
• Resolve metonymy based on a search in metonymy
  space.
• Anaphora is used to validate the result of the
  metonymy resolution.

• Given Joe read Shakespeare. It was good.

• Type constraints
• agent-of-read Person.
• object-of-read Text

• MetonymySpace Shakespeare, His Head, His Text
  ... .
• Selects His Text

• Anaphora It confirms His Text fits better than
  Shakespeare.

32
Metonymy Example 2 (Traditional Approach)

• Given an input (often in the form of sentences in
  natural language)
• Detect metonymy based on detection of type
  constraints,
• Resolve metonymy based on a search in metonymy
  space.
• Anaphora is used to validate the result of the
  metonymy resolution.

• Given electrons are removed from water
  molecules.

• Type Constraints
• object-of-remove Entity.
• base-of-remove Entity.

• No violation found, no metonymy resolution
  needed.

33
Metonymy Example 2 (Continued)

• However the input, Electrons are removed from
  water molecules, does need metonymy resolution
  in our representation because
• Remove requires the base have the object as its
  part, e.g. water molecule should have a part
  called electron.
• Water molecule does not have a part called
  electron. It has a hydrogen atom part, which has
  a electron part, and it has an oxygen atom part,
  which has a electron part.
• Therefore the literal translation of the input
  does NOT work, and the traditional approach does
  NOT give the correct answer either.

34
Our Approach

• Given (a Read with (object (Shakespeare))),
  translate it into Read-object-Shakespeare

• Given KM expression that can be translated into
  X-r-Y, where X, Y are frames, and r is a slot
• Do
• X' X, Y' Y
• I Ideal(X, r)
• M MetonymySpace(Y)
• Y m such that m Î M and distance(m, I) lt
  distance(m', I) for all m' Î M
• I Ideal(Y, rinverse)
• M MetonymySpace(X)
• X m such that m Î M and distance(m, I) lt
  distance(m', I) for all m' Î M
• Until (X X' and Y Y')
• Return X'-r-Y'

1st iteration X Read, Y Shakespeare
I (a Text with (purpose ((a Role with (in-event
((a Read)))))) M Shakespeare, His Head, His
Text, Y His Text I (a Event) M Read X
Read
2nd iteration
Return Read-object-His Text
35
Ideal and Metonymy Space

• Ideal
• Type constraints.
• Add/delete/precondition list of the action.
• Teleological constraints.
• Metonymy Space given the metonym A, return set
  S X exists A-r1-A1-r2-A2- -rn-X where r1,
  r2, , rn are members of a fixed set of slots,
  such as has-part, material, agent, result, etc.,
  and A1, A2, , X are frames.
• Search depth the n in the A-r1-A1-r2-A2- -rn-X
  path mentioned above. For example, search depth
  of A 0, search depth of A1 1, etc.

36
Distance Measurement and Comparison

• Distance - (p, n, t) the similarity between an
  element from the metonymy space and the ideal.
• p number of shared properties between the
  element and the ideal.
• n search depth of the element in the metonymy
  space.
• t taxonomical distance between the element and
  the ideal.
• Given (p1, n1, t1) and (p2, n2, t2), then.
• (p1, n1, t1) lt (p2, n2, t2) if
• p1 gt p2 or.
• p1 p2 and n1 lt n2 or.
• p1 p2 and n1 n2 and t1 lt t2.

37
Metonymy Example 2 (Continued)

• Given KM expression that can be translated into
  X-r-Y, where X, Y are frames, and r is a slot
• Do
• X' X, Y' Y
• I Ideal(X, r)
• M MetonymySpace(Y)
• Y m such that m Î M and distance(m, I) lt
  distance(m', I) for all m' Î M
• I Ideal(Y, rinverse)
• M MetonymySpace(X)
• X m such that m Î M and distance(m, I) lt
  distance(m', I) for all m' Î M
• Until (X X' and Y Y')
• Return X'-r-Y'

• Given (a Remove with (object ((a Electron)))
  (base ((a Water-Molecule)))), translate into
  Remove-object-Electron and Remove-base-Water-Molec
  ule. Lets consider Remove-base-Water-Molecule

1st iteration X Remove, Y Water-Molecule
I(a Tangible-Entitytype constraint with
(purpose ((a Role with (in-event ((a Remove))))
teleological constraint (has-part ((a
Electron)))) del-list M Water-Molecule,
Oxygen-Atom, Hydrogen-Atom, Electron, Y
Oxygen-Atom I (an Event M Remove X
Remove
2nd iteration Return (a Remove with (object
((a Electron))) (base ((a Oxygen-Atom with
(is-part-of ((a Water-Molecule)))))))
38
Metonymy Example 3

• Given KM expression that can be translated into
  X-r-Y, where X, Y are frames, and r is a slot
• Do
• X' X, Y' Y
• I Ideal(X, r)
• M MetonymySpace(Y)
• Y m such that m Î M and distance(m, I) lt
  distance(m', I) for all m' Î M
• I Ideal(Y, rinverse)
• M MetonymySpace(X)
• X m such that m Î M and distance(m, I) lt
  distance(m', I) for all m' Î M
• Until (X X' and Y Y')
• Return X'-r-Y'

• Given (a Nucleus with (content ((a Object)))),
  translate it into Nucleus-content-Object.

1st iteration. X' Nucleus, Y' Object
I (a Tangible-Entity) M Object Y
Object I (a Container) M Nucleus, Container,
Nucleoplasm, ... X Container
2nd iteration Return (a Nucleus with (purpose
((a Container with (content ((a Object)))))))
39
Metonymy Example 4

• Given (a Catalyze with (instrument ((a
  Mitochondrion)))), translate it into
  Catalyze-instrument-Mitochondrion.

• Given KM expression that can be translated into
  X-r-Y, where X, Y are frames, and r is a slot
• Do
• X' X, Y' Y
• I Ideal(X, r)
• M MetonymySpace(Y)
• Y m such that m Î M and distance(m, I) lt
  distance(m', I) for all m' Î M
• I Ideal(Y, rinverse)
• M MetonymySpace(X)
• X m such that m Î M and distance(m, I) lt
  distance(m', I) for all m' Î M
• Until (X X' and Y Y')
• Return X'-r-Y'

1st iteration X' Catalyze, Y' Mitochondrion
I (a Chemical-Object with (purpose ((a
Catalyst)))) M Mitochondrion, Container,
Aggregate, Oxido-Reductase, ... Y
Oxido-Reductase I (a Event) M Catalyze X
Catalyze
2nd iteration ... Return (a Catalyze with
(instrument ((a Oxido-Reductase with
(element-type-of ((a Aggregate with (content-of
((a Be-Contained with (in-event-of ((a Container
with (purpose-of ((a Mitochondrion)).
40
Future Work on Metonymy

• Test data bounded by KB. More data needed for
  evaluation.
• Other applications of the metonymy resolution
  algorithm.

41
Other Applications of Metonymy Resolution

• Shields SMEs from the idiosyncrasy of the
  representation
• roles,
• spatial representations,
• aggregates,
• properties.
• E.g. instead of (a Car with (color ((a
  Color-Value with (value (pair red Object)))))),
  do (a Car with (color (red))) directly
• LS generation for concise display of the
  knowledge to users.

42
Outline

• Loose speak overview
• Two types of LS
• Complex nominal interpretation
• Metonymy
• Future work on LS

43
Future Work on LS Project

• Discover more patterns of LS.
• Overly general speak stating knowledge in an
  overly general way, often using a general concept
  in the place of a specific one.
• Example "there may be 15 RNA polymerases
  speeding along the same stretch of DNA ..".
• More extensive evaluations.
• Explore the process of theory and validation.