Title: Explaining Cognitive Assistants that Learn
1Explaining Cognitive Assistants that Learn
- Deborah McGuinness1, Alyssa Glass1,2, Michael
Wolverton2 - 1Knowledge Systems, AI Laboratory
- Stanford University
- dlm glass _at_ksl.stanford.edu
- 1SRI International
- mjw_at_ai.sri.com
- thanks to Paulo Pinheiro da Silva, Li Ding,
Cynthia Chang, Honglei Zeng, Vasco Furtado, Jim
Blythe, Karen Myers, Ken Conley, David Morley
2General Motivation
Provide interoperable knowledge provenance
infrastructure that supports explanations of
sources, assumptions, learned information, and
answers as an enabler for trust.
- Interoperability as systems use varied sources
and multiple information manipulation engines,
they benefit more from encodings that are
shareable interoperable - Provenance if users (humans and agents) are to
use and integrate data from unknown, unreliable,
or evolving sources, they need provenance
metadata for evaluation - Explanation/Justification if information has
been manipulated (i.e., by sound deduction or by
heuristic processes), information manipulation
trace information should be available - Trust if some sources are more trustworthy than
others, representations should be available to
encode, propagate, combine, and (appropriately)
display trust values
3Inference Web Infrastructure primary
collaborators Ding, Chang, Pinheiro da Silva,
Zeng, Fikes
- Framework for explaining question answering tasks
by - abstracting, storing, exchanging,
- combining, annotating, filtering, segmenting,
- comparing, and rendering proofs and proof
fragments - provided by question answerers.
4ICEE Integrated Cognitive Explanation
Environment
- Improve Trust in Cognitive Assistants that learn
by providing transparency concerning
provenance information manipulation
task processing learning
5ICEE Architecture
Collaboration Agent
Task Manager (TM)
Explanation Dispatcher
TM Wrapper
TM Explainer
Justification Generator
6During the demo, notice
- User can ask questions at any time
- Reponses are context-sensitive
- Dependant on current task processing state and on
provenance of underlying process - Explanations generated completely automatically
- No additional work required by user to supply
information - Follow-up questions provide additional detail at
users discretion - Avoids needless distraction
7 8Task Explanation
- Ability to ask why at any point
- Context appropriate follow-up questions are
presented
9Explainer Strategy (for cognitive assistants)
- Present
- Query
- Answer
- Abstraction of justification (using PML
encodings) - Provide access to meta information
- Suggests drill down options (also provides
feedback options)
10Sample Introspective Predicates Provenance
- Author
- Modifications
- Algorithm
- Addition date/time
- Data used
- Collection time span for data
- Author comment
- Delta from previous version
- Link to original
Glass, A., and McGuinness, D.L. 2006.
Introspective Predicates for Explaining Task
Execution in CALO. Technical Report, KSL-06-04,
Knowledge Systems Lab., Stanford Univ.
11Task Action Schema
- Wrapper extracts portions of task intention
structure through introspective predicates - Store extracted information in action schema
- Designed to achieve three criteria
- Salience
- Reusability
- Generality
12SupportsTopLevelGoal(x) IntentionPreconditionMet
(x) TerminationConditionNotMet(x) gt
Executing(x)
TopLevelGoal(y) Supports(x,y) gt
SupportsTopLevelGoal(x)
ParentOf (x,y) Supports(y,z) gt Supports (x,z)
ParentOf (x,y) Supports(y,z) gt Supports (x,z)
GS GetSignature BL BuyLaptop GA GetApproval
Supports (x,x)
13User Trust Study
- Interviewed 10 Critical Learning Period (CLP)
participants - Programmers, researchers, administrators
- Focus of study
- Trust
- Failures, surprises, and other sources of
confusion - Desired questions to ask CALO
- Initial results
- Explanations are required in order to trust
agents that learn - To build trust, users want transparency and
provenance - Identified question types most important to CALO
users --gt motivation for future work
14Future Directions
- We will leverage results from our trust study to
focus and prioritize our strategies explaining
cognitive assistants e.g., learning specific
provenance - We will expand our explanations of learning to
augment learning by instruction and design and
implement explanation of learning by
demonstration (initially focusing on LAPDOG). - We will expand our initial design of explaining
preferences in PTIME - Write up and distribute user trust study to CALO
participants - Consider using conflicts to drive learning and
explanations I have not finished because x
has not completed. - Advanced dialogues exploiting TOWEL and other
CALO components - Potentially exploit our work on IW Trust - a
method for representing, propagating, and
presenting trust within the CALO setting
already have results in intelligence analyst
tools, integration with text analytics,
Wikipedia, likely to be used in IL, etc.
15Explaining Learning by Demonstration
- General Motivation
- LAPDOG (Learning Assistant Procedures from
Demonstration, Observation, and Generalization)
generalizes the users demonstration to learn a
procedure - While LAPDOGs generalization process is designed
to produce reasonable procedures, it will
occasionally get it wrong - Specifically, it will occasionally over
generalize - Generalize the wrong variables, or too many
variables - Produce too general a procedure because of a
coarse-grained type hierarchy - ICEE needs to explain the relevant aspects of the
generalization process in a user-friendly format - To help the user identify and correct over
generalizations - To help the user understand and trust the learned
procedures - Specific elements of LAPDOG reasoning to explain
- Ontology-Based Parameter Generalization
- The variables (elements of the users
demonstration) that LAPDOG chooses to generalize - The type hierarchy on which the generalization is
based - Procedure Completion
- The knowledge-producing actions that were added
to the demonstration - The generalization done on those actions
- Background knowledge that biases the learning
- E.g., rich information about the email, calendar
events, files, web pages, and other objects upon
which it executes it actions - Primarily for future versions of LAPDOG
16Explaining Preferences
- General Motivation
- PLIANT (Preference Learning through Interactive
Advisable Non-intrusive Training) uses
user-elicited preferences and past choices to
learn user scheduling preferences for PTIME,
using a Support Vector Machine. - Inconsistent user preferences, over-constrained
schedules, and necessity of exploring the
preference space result in user confusion about
why a schedule is being presented. - Lack of user understanding of PLIANTs updates
creates confusion, mistrust, and the appearance
that preferences are being ignored. - ICEE needs to provide justifications of PLIANTs
schedule suggestions, in a user-friendly format,
without requiring the user to understand SVM
learning. - Providing Transparency into Preference Learning
- Augment PLIANT to gather additional
meta-information about the SVM itself - Support vectors identified by SVM
- Support vectors nearest to the query point
- Margin to the query point
- Average margin over all data points
- Non-support vectors nearest to the query point
- Kernel transformation used, if any
- Represent SVM learning and meta-information as
justification in PML, using added SVM rules - Design abstraction strategies for presenting
justification to user as a similarity-based
explanation
17Advantages to ICEE Approach
- Unified framework for explaining task execution
and deductive reasoning. - Architecture for reuse among many task execution
systems. - Introspective predicates and software wrapper
that extract explanation-relevant information
from task reasoner. - Reusable action schema for representing task
reasoning. - A version of Inference Web for generating formal
justifications.
18Resources
- Overview of ICEE
- McGuinness, D.L., Glass, A., Wolverton, M., and
Pinheiro da Silva, P. Explaining Task Processing
in Cognitive Assistants that Learn. AAAI 2007
Spring Symposium on Interaction Challenges for
Intelligent Assistants (to appear). (Updated
version will be in FLAIRS 2007). - Introspective predicates
- Glass, A., and McGuinness, D.L. Introspective
Predicates for Explaining Task Execution in CALO.
Technical Report, KSL-06-04, Knowledge Systems,
AI Lab., Stanford University, 2006. - Video demonstration of ICEE
- http//iw.stanford.edu/2006/10/ICEE.640.mov
- Explanation interfaces
- McGuinness, D.L., Ding, L., Glass, A., Chang, C.,
Zeng, H., and Furtado, V. Explanation Interfaces
for the Semantic Web Issues and Models. 3rd
International Semantic Web User Interaction
Workshop (SWUI06). Co-located with the
International Semantic Web Conference, Athens,
Georgia, 2006. - Inference Web (including above publications)
- http//iw.stanford.edu/
19Extra
20How PML Works
isQueryFor
IWBase
Query fooquery1 ltformal internal
structured querygt
Question fooquestion1 ltInput language
questiongt
hasAnswer
Justification Trace
hasLanguage
NodeSet foons1 (hasConclusion )
Language
hasInferencEngine
fromQuery
isConsequentOf
InferenceEngine
hasRule
InferenceStep
InferenceRule
hasAntecendent
Source
NodeSet foons2 (hasConclusion )
hasVariableMapping
Mapping
isConsequentOf
fromAnswer
hasSourceUsage
hasSource
SourceUsage
InferenceStep
usageTime
21Sample Task HierarchyPurchase equipment
- Purchase equipment
- Collect requirements
- Get quotes
- Do research
- Choose set of quotes
- Pick single item
- Get approval
- Place order
22Sample Task HierarchyGet travel authorization
- Get travel authorization
- Collect requirements
- Get approval, if necessary
- Note this conditional step was added to the
original procedure through learning by
instruction - Submit travel paperwork
23PML in Swoop
24Explaining Extracted Entities
Source fbi_01.txt Source Usage span from 01 to
78
Same conclusion from multiple extractors
conflicting conclusion from one extractor
This extractor decided that Person_fbi-01.txt_46
is a Person and not Occupation
25Task Management Framework
Activity Recognizer
Advice
Preferences
Advice
Preferences
Preferences
Time
Time
Task
Task
Manager
Manager
Manager
Manager
Location Estimator
PTIME
PTIME
SPARK
SPARK
Process Models
Process Models
Procedure
Execution Monitor
Execution Monitor
Task Explainer
Task Explainer
Learners
Predictor
Predictor
ICEE
ICEE
Tailor, LAPDOG, PrimTL, PLOW
ProPL
ProPL