Transcript Advanced TuTalk Dialogue Agents - Pittsburgh Science of Learning

Advanced TuTalk
Click to edit the title text format
Dialogue Agents
Pamela Jordan
University of Pittsburgh
Learning Research and Development Center
Agenda

Introducing the TuTalk dialogue system server
 System
architecture (briefly)
 Web interface to server for




Fielding experiments
Analyzing experiments
For uploading sc and xml directly to dialogue system server
Introduce additional authoring features
 Enabling
and controlling automated feedback
 Optional steps (sc only)
 Looping (sc only)
Architecture of TuTalk Dialogue
System
Hub & spokes architecture
 Main modules:

 Coordinator
 Language
recognition
 Language generation
 Dialogue manager
 Dialogue History database
Language recognition


Refers to labelled sets of alternative phrasings
called concepts
Inputs from dialogue manager
 normalized
sentence,
 set of expected response concepts


Computes minimum edit distance, number of
adds and deletes of words needed to match
input language to a concept
Returns expected response concept with
smallest minimum edit distance that falls within a
threshold
Language generation





Refers to labelled sets of alternative phrasings
called concepts
Input from dialogue manager: a concept
If > 1 alternative phrasing, removes one last
used according to dialogue history
Randomly selects from remaining alternative
phrasings
Requests output of selected phrasing to student
Integrating TuTalk

Can integrate (embed/wrap) other
modules
 ProPL
 Cordillera

Hub & spokes architecture
 Replaceable
modules e.g., NLU
Replaceable language modules


Replace:

Use a human (1 experiment)

Use another approach
Supplement: Human reviews and corrects choices
made by recognition module (1 experiment)
Experiment management/analysis


Experiment management tools: http://pyrenees.lrdc.pitt.edu/~tutalk/cgibin/admin.cgi
One scenario/script = one dialogue agent = one condition, but can organize
in other ways

One agent per unit
 One agent that tells all knowledge components vs. one that elicits vs. one that
uses a strategy to decide which to do

Condition management

Start on server and leave it running
 Designate who is allowed in the condition

SQL database of information collected during interaction

Can download or query
 Working on producing DataShop format
Setting up a scenario
SQL database access
SQL database access
Requesting a transcript
Transcript for a student
Additional authoring features

Automated turn transitions/feedback
 Must
specify truth-values for responses in context of
an initiation
 Default truth-value is “unknown”
 Override automated turn transitions/feedbacks with a
“say”

Optional steps:
 Skip
if specified condition met in recent dialogue
history

Looping:
 Repeat
the template for a goal until a condition is met
 Globally set condition once set
Script w/ truth-val in sc
g select-appetizer
say enthuse_about_appetizers
say ask_share_appetizer
if agree_to_share_appetizer
if skip_appetizer true
do “abort ask-soup”
else do “abort lose-temper”
do agree-on-appetizer
Automatically generated response
feedback
“say” feature in authoring tool overrides
automatic feedback
 “say” following a response in sc overrides
automatic feedback
 Can globally enable/disable in xml
configuration section (default is enabled)

Script w/ auto feedback override in sc
g select-appetizer
say enthuse_about_appetizers
say ask_share_appetizer
if agree_to_share_appetizer
if skip_appetizer true say “Okay, in that case I won’t get an appetizer.”
do “abort ask-soup”
else do “abort lose-temper”
do agree-on-appetizer
Authoring response feedback (1)
Authoring response feedback (2)
Additional authoring features

Automated turn transitions/feedback
 Must
specify truth-values for responses in context of
an initiation
 Default truth-value is “unknown”
 Override automated turn transitions/feedbacks with a
“say”

Optional steps:
 Skip
if specified condition met in recent dialogue
history

Looping:
 Repeat
the template for a goal until a condition is met
 Globally set condition once set
Optional Steps
As a runner pushes a ball
away, what horizontal forces
act on it?
{runner’s}
Good!
{gravitational, *}
<subdialog >
<anything else>
<subdialog>
not said
Any others?
said
Any others?
After the push ends, what forces….?
Example of optional steps
T: … what horizontal forces are acting on it while she is pushing it?
S: Gravity?
T: In what direction does gravity act?
.
T: So are there any other forces on the ball?
subdialogue
S: no
T: What about the runner?
.
T: Okay. After the push ends, what forces…
T: … what horizontal forces are acting on it while she is pushing it?
S: The runner’s
T: Right! So are there any other forces on the ball?
S: no
T: Good. After the push ends, what forces…
Script with an optional step and
semantic labels in sc
g ask-appetizer
say enthuse-about-appetizers opt sem enthuse-about-appetizers
say ask-appetizer
if skip-appetizer sem skip-appetizer-order do “abort soup”
if no do “abort soup”
else do lose-temper
do order-appetizer
Additional authoring features

Automated turn transitions/feedback
 Must
specify truth-values for responses in context of
an initiation
 Default truth-value is “unknown”
 Override automated turn transitions/feedbacks with a
“say”

Optional steps:
 Skip
if specified condition met in recent dialogue
history

Looping:
 Repeat
the template for a goal until a condition is met
 Globally set condition once set
Looping for a dialogue

Continuous loop on a template: repeat template until all indicated
components covered
T: Okay, great. What should we work on now?
S: Add a loop
T: That’s right. We will have to add a loop. Let’s figure out why. What made
you think of using a loop?
S: .
.
T: Okay. What should we work on now?
.
.
T: So, with that we’re finished with this problem.
(example based on Lane 04)
Script with a loop and semantic labels
in sc
g start
do 76
do 36
do 163
do 58
g 76 loop finished76
say the-first-problem-will-take-about
do prob76
say the-next-problem-will-take-about-3 sem finished76
if yes
else do logout-msg
Configuration section in sc format
config global version "$Revision: 1.75 $" default-language en
# We use several proper nouns in the scenario, so we declare them here, and provide
# morphological info so en-normalizer.py won’t spell-correct them. A different
# normalizer will probably require (and hopefully document) a different format.
config normalizer lexicon-supplement "Python{’en’:
[’springfield n-springfield-’,
’chicago n-chicago-’,
’ontario n-ontario-’,
’illinois n-illinois-’,
’superior n-superior-’,
’huron n-huron-’,
’erie n-erie-’,
’michigan n-michigan-’,
’ontario n-ontario-’
]}"