Second Annual Research Symposium of the Human Language Technology Research Institute Sequence Packag

1
Second Annual Research Symposium of the Human
Language Technology Research InstituteSequence
Package AnalysisA New Natural Language
Intelligence Method for Speeding Up Wiretap
Analysis

• Amy Neustein, Ph.D.
• Linguistic Technology Systems
• lingtec_at_banet.net

2
Sequence Package Analysis A New Natural Language
Intelligence Method to Speed Up Wiretap Analysis

• Question Why do we need a new method?
• Answer 1) In the real world speakers do not
• always use key words that can
• be spotted in a dialog.
• 2) In crime or terror related
  dialog,
• speakers will deliberately
  avoid the
• use of key words that can
  identify
• names, places, dates, etc.

3
Sequence Package Analysis How Does SPA Work?

• 1) Add rather than Replace
• SPA adds a layer of intelligence to standard
  dialog systems.
• 2) Mines audio data
• SPA goes beyond a conventional search for
  words and word strings.
• 3) Examines a series of related speaking turns
  that are discretely packaged as a sequence.

4
What is the Methodological Basis of Sequence
Package Analysis? SPA is derived from the
Conversation Analytic method of breaking down
natural language communication into its primary
units of analysis, sequences and turns within
sequences, rather than isolated sentences or
utterances. Conversation Analysis has been
called by some a sub field of A.I. because it can
detect the detailed structural organization of
dialog, which is critical in designing simulacra
that emulate how humans really talk.

5
What Makes Sequence Package Analysis Unique?

• 1. Sequence Packages go beyond standard
  grammatical formalisms (e.g., Q/A sequences) to
  include large, winding episodes of talk.
• 2. Sequence Packages are dialogically indigenous
  and thus must be detected by algorithms that are
  sophisticated and flexible enough to chart out
  these dialog patterns.

6
SPA A Unique Method but with a Conventional
Design ApproachSLM (Statistical Language
Modeling) can be applied to SPA. Heres
howThis extra layer of intelligence, that SPA
provides a dialog system, contains sequence
packageformulae that give the best statistical
match for these sequence package entries just as
how word entries are matched against their own
statistical approximations.

7
WHAT DOES SPA DO?

• 1) SPA permits the discovery of key words
  (e.g., the name of a location where a crucial
  meeting among terrorists will take place) that
  are not in the preset lexicon.
• 2) SPA permits rapid and efficient data mining of
  large volumes of audio text by spotting sequence
  packages in the dialog.

8
ADVANTAGES OF SPA

• Can be applied to different languages works
  by identifying interactional features of dialog
  (conversational sequence patterns) rather a
  preset glossary of words.
• Can perform data mining in real time
• permits a human analyst to be brought in
  immediately when high alarm content is being
  produced in the dialog.

9
DEMONSTRATION

• The following example shows how applying an SPA
  approach to wiretapped dialog can flag important
  security information that is cleverly disguised
  by the suspects

10
Speaker A is trying to educate Speaker B
about a new meeting place whose location is very
important. Any confusion or misunderstanding
about this meeting place could spoil the plans.
But Speaker A is very clever First, he
stays away from buzz words (such as naming a
bridge, a tunnel or a street).Second, he
refrains from making any prefatory remarks about
the importance of meeting at this new location,
and not confusing it with another place.
11
Dialog Example

• Speaker A Come to the intersection near
  Juniors? (the question mark shows an upward
  intonation) 0.2 - 0.5 second pause
  (speaker then pauses briefly)
• Speaker B 1.2 second pause
• Speaker A You know the thoroughfare with the
  big traffic light?
• Speaker B Juniors, yeah.

12
THE SEQUENCE PACKAGE

• Speaker A Come to the intersection near
  Juniors? 0.2-0.5
• Speaker B 1.2 seconds of silence
• A noun referent (Juniors) with an upward
  intonation
• A brief pause, giving the listener the chance to
  show recognition or ask for clarification.
• Silence by the listener which indicates lack of
  understanding or confusion.

13
Speaker A You know the thoroughfare with the
big traffic light?Speaker B Juniors, yeah.

• Clarification of the noun referent
• (You know the thoroughfare with...)
• Repeat of noun referent (Juniors) - the source
  of the recognition trouble - followed by a
  recognitional marker (Yeah).

14
Finding the Sequence Package in the Dialog
Example

• Look for a concatenation of these
• utterance components
• noun referent with upward intonation
• brief pause
• silence
• clarification of noun referent
• repeat of noun referent that was initial source
  of the recognition trouble
• recognitional marker

15
ADVANTAGES OF SPA
Can be applied to different languages works by
identifying interactional features of dialog
(conversational sequence patterns) rather a
preset glossary of words. Can perform data
mining in real time permits a human analyst to
be brought in immediately when high alarm content
is being produced in the dialog.
16
Private Industry Applications for SPA

• Technical Support Centers
• Help desks
• Call Centers
• Broadcast Media
• Depositions
• Courtroom Testimony
• Corporate Communications
• Conference Managers

17
Second Annual Research Symposium of the Human
Language Technology Research InstituteSequence
Package AnalysisA New Natural Language
Intelligence Method for Speeding Up Wiretap
Analysis

• Amy Neustein, Ph.D.
• Linguistic Technology Systems
• lingtec_at_banet.net