SlideShare a Scribd company logo
1 of 26
Download to read offline
1
Legal Vocabulary and its Transformation Evaluation
using Competency Questions
15th International Conference on AI and Law- ICAIL 2015
11-June 2015
San Diego, CA, USA
Shashishekar Ramakrishna, Łukasz Górski and Adrian Paschke
2
In-C Tests : Processing Model
2
Introduction
Legal
Expert
System
3
In-C Tests : Processing Model
3
Model Driven Architecture approach to Legal KR
► OMG : Object Management Group (OMG)
► Founded in 1989 by 11 companies (IBM, Apple, Sun Microsystems etc.)
► Not-for-profit computer industry standards consortium
►Model Driven Architecture
4
Informal to Semi-Formal via Legal Decision Models
35 U.S.C. 112, 1st Paragraph,- Specification
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear,
concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and
use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
[Ramakrishna , Gorski and Paschke: ESWC Workshop 2015]
5
In-C Tests : Processing Model
5
Semi-Formal Legal KR via SBVR
SBVR: Semantics of Business Vocabulary and Business Rules
► Sits on CIM layer of OMG’s MDA (OMG’s standard since 2005, )
► To support computationalindependent modeling of business rules by
business people in business language
Two Meta-models defined in Form of vocabularies
► Vocabulary for Describing Business Vocabularies
► Vocabulary for Describing Business Rules
6
In-C Tests : Processing Model
6
SBVR in Legal Domain:
► Legal Concept: (individual concept, object type )
► e.g. patent, claim, examiner
► Fact type: denoting some relationship b/w 2 or more noun concept
► e.g. patent includes claim
► Legal (procedural/substantive) rule: a rule under legal jurisdiction
► e.g. It is obligatory that a patent includes atleast 1 claim.
7
Semi-Formal Representation
¶ 7.33.01 Rejection : Claim [1] rejected under 35 U.S.C. 112, first paragraph, as based on a disclosure which is not enabling. [2] critical or
essentialto the practice of the invention, but not included in the claim(s) is not enabled by the disclosure.
1. This rejection must be preceded by form paragraph 7.30.01 or 7.103.
2. In bracket 2, recite the subject matter omitted from the claims.
Legal Concepts
Claim, office_action, Paragraphs, essential_subject_matter_requirement, Paragarph_7_33_01
Enables identification of associated context information and relations between them.
Context information
for each legal concept
E.g.:
KR4IPLaw Legal Concept
Recommender System
8
In-C Tests : Processing Model
8
Semi-Formal Representation contd…
Legal Facts (verb concepts are defined in blue)
office_action includes paragraphs
claim is_rejected_under essential_subject_matter_requirement
office_action include statement
applicant conceals effective_feature
effective_feature is_about the invention
examiner applies Paragraph_7_33_01
examiner rejects the claim
Legal (procedural) rules (for ¶ 7.33.01) in Structured English:
1. It is obligatory that examiner rejects the claim and office_action includes paragraphs
Paragraph_7_33_01 if claim is_rejected_under essential_subject_matter_requirement
2. It is obligatory that office_action include statement and argument and date and
drawing if claim is_rejected_under Paragraph_7_33_01
3. It is necessary that examiner applies Paragraph_7_33_01 if applicant conceals
effective_feature and effective_feature is_about the invention
9
In-C Tests : Processing Model
9
Semi-Formal to Formal Representation
Legal Rules in SBVR-SELegal Facts
OWL2
10
In-C Tests : Processing Model
10
Legal Vocabulary Evaluation ?
Increases confidence in using the inferred knowledge in the form of legal arguments.
Goal is to eliminate black boxes (from end-users perspective) in a (Semi-/) automated decision support
systems.
11
Competency Question Design: Actors
Content Specialist
Design Specialist
Interviewer
Respondent
Legal practitioner
Knowledge Modeler
Ontology query engine
Ontology
Creates a set of competency questions
defined in semi-formal language.
Performs the translation into formal
query language
12
Building the
system right
Accuracy
Adaptability
Clarity
Completeness
Computational
Efficiency
Conciseness
Consistency
Organizational
fitness
Legal Vocabulary Evaluation: Verification
13
Verification
Accuracy
Adaptability
Clarity
Completeness
Computational
Efficiency
Conciseness
Consistency
Organizational
fitness
Verification contd…
14
Building the
right system
(In-)
consistency
(In-)
completeness
(In-)
conciseness
(In-)
sensitiveness
Legal Vocabulary Evaluation :Validation
15
Validation
(In-)
consistency
(In-)
completeness
(In-)
conciseness
(In-)
sensitiveness
Validation contd…
16
CQ-Based Evaluation: The Process
17
CQ based Evaluation: Formal Definition
Then:
Each CQ should address two generalized conditions:
Formal CQs can be defined formally as entailment or consistency problem wrt axioms in ontology
If
Tontology = a set of axioms
Tground = a set of ground literals
Q = a first-order legal sentence in the language of Tontology
a) Determine
if Tontology ∪ Tground ⊨ Q?
b) Determine
if Tontology ∪ Tground ⊭ ¬Q?
=> Transformation is correct and verifiable
18
Sample CQs Pattern
Selection Question Module
What is a claim? Define a X
Where is the language of a claim W is/are the X of Y (W ∈ {Where, What, Who}
What is a relation between claim and a patent What is a relation between X and Y?
What does patent include What does X R?
Binary Question Module
Is the patent application filed in US? Is/Are X relation Y?
Does the patent application include a claim? Do/Does X relation Y?
Counting Question Module
What is the minimum number of claims in a patent
application?
The Q of X in Y? (Q∈{number, min, max}
CQs and Patterns
19
Formal CQ Pattern
Selection Question Module
[skos:definition][CE]? SELECT ?LegalConcept ?definition
WHERE { ?LegalConcept a owl:Class;
Define a claim skos:definition ?definition . }
[OPE][CE1][CE2]? processQuery("PREFIX : <abc#> n" + "SELECT ?x ?y
WHERE {n" + PropertyValue(?x,:OPE, ?y)"+"}")
[CE1][OPE]=[CE2]? SELECT { ?y WHERE {n" + PropertyValue(CE1,:OPE,
?y)"+"};
Binary Question Module
[OPE][CE1][CE2]=Y/N? ASK {:OPE rdfs:domain :CE1 ; rdfs:range :CE2.}
Counting Question Module
[OPE@min/maxCardinality][CE1][CE2]? SELECT ?cardinality
WHERE { <http://abc> owl:equivalentClass ?c. ?c
owl:qualifiedCardinality ?cardinality }
Formal CQs mapped to DL based queries
20
Experimental Results
Overall knowledge (in)completeness within the legal vocabulary for our consideredexample
Legal vocabulary may be regarded as incomplete, if the legal concepts do not contain of all
the necessary definitions, some defined formally and some via its annotation properties
21
Experimental Results
Legal knowledge (in-)completeness for indvidual legal concepts
22
Experimental Results
Permissible sensitivity inversely proportional to Threshold
E.g. : offce_action central legal concept
Modification to legal concept office_action → effects several other concepts
23
Legal Rules: Platform Independent Layer: KR4IPLaw
24
Legal Rules: Platform Specific Layer: Prova
Rule Engine
A rule is evaluated only if guard conditions are evaluated to be True
Verification and Validation of legal knowledge increases the clarity of legal arguments generated by a
Legal Expert System
25
Further Reading:
• Ramakrishna, Gorski and Paschke, 2015. The Role of Pragmatics in Legal Norm Representation. International Workshop On
Legal Domain And Semantic Web Applications, ESWC 2015
• Ramakrishna, Paschke 2014 . A Process for Knowledge Transformation and Knowledge Representation of Patent Law.
RuleML – 2014
• Paschke, 2006 . Verification, validation and integrity of distributed and interchanged rule based policies and contracts
in the semantic web.
• Ramakrishna and Paschke. Semi-Automated Vocabulary Building for Structured Legal English. In RuleML 2014, volume
8620 of LNCS. Springer, 2014.
26
Thank you
Shashishekar Ramakrishna
Free University of Berlin,
Dept of Mathematics and Computer Science
shashi792@gmail.com
Łukasz Górski
Nicolaus Copernicus University
lgorski@mat.umk.pl
Adrian Paschke
Free University of Berlin,
Dept of Mathematics and Computer Science
paschke@inf-fu-berlin.de

More Related Content

Similar to Legal Vocabulary and its Transformation Evaluation using Competency Questions

DPCL: a Language Template for Normative Specifications
DPCL: a Language Template for Normative SpecificationsDPCL: a Language Template for Normative Specifications
DPCL: a Language Template for Normative SpecificationsGiovanni Sileno
 
Software requirementspecification
Software requirementspecificationSoftware requirementspecification
Software requirementspecificationoshin-japanese
 
Compliance driven process development with DCR graphs
Compliance driven process development with DCR graphsCompliance driven process development with DCR graphs
Compliance driven process development with DCR graphsHugo Andrés López
 
Ch 1-Introduction.ppt
Ch 1-Introduction.pptCh 1-Introduction.ppt
Ch 1-Introduction.pptbalewayalew
 
Ch 2-RE-process.pptx
Ch 2-RE-process.pptxCh 2-RE-process.pptx
Ch 2-RE-process.pptxbalewayalew
 
Software engg. pressman_ch-6 & 7
Software engg. pressman_ch-6 & 7Software engg. pressman_ch-6 & 7
Software engg. pressman_ch-6 & 7Dhairya Joshi
 
License DSL translation in COMPAS framework
License DSL translation in COMPAS frameworkLicense DSL translation in COMPAS framework
License DSL translation in COMPAS frameworkCuddle.ai
 
SE2023 0201 Software Analysis and Design.pptx
SE2023 0201 Software Analysis and Design.pptxSE2023 0201 Software Analysis and Design.pptx
SE2023 0201 Software Analysis and Design.pptxBharat Chawda
 
6. ch 5-understanding requirements
6. ch 5-understanding requirements6. ch 5-understanding requirements
6. ch 5-understanding requirementsDelowar hossain
 
Hl7 V3 Reference Models 20091123
Hl7 V3 Reference Models 20091123Hl7 V3 Reference Models 20091123
Hl7 V3 Reference Models 20091123Abdul-Malik Shakir
 
software requirement and architecture.pdf
software requirement and architecture.pdfsoftware requirement and architecture.pdf
software requirement and architecture.pdfwajoce8790
 
Verification and validation of knowledge bases using test cases generated by ...
Verification and validation of knowledge bases using test cases generated by ...Verification and validation of knowledge bases using test cases generated by ...
Verification and validation of knowledge bases using test cases generated by ...Waqas Tariq
 
Knowledge representation and reasoning
Knowledge representation and reasoningKnowledge representation and reasoning
Knowledge representation and reasoningMaryam Maleki
 
Chapter 2 SRS_241222135554.ppt
Chapter 2 SRS_241222135554.pptChapter 2 SRS_241222135554.ppt
Chapter 2 SRS_241222135554.pptHaviQueen
 

Similar to Legal Vocabulary and its Transformation Evaluation using Competency Questions (20)

DPCL: a Language Template for Normative Specifications
DPCL: a Language Template for Normative SpecificationsDPCL: a Language Template for Normative Specifications
DPCL: a Language Template for Normative Specifications
 
3Requirements.ppt
3Requirements.ppt3Requirements.ppt
3Requirements.ppt
 
Software requirementspecification
Software requirementspecificationSoftware requirementspecification
Software requirementspecification
 
Compliance driven process development with DCR graphs
Compliance driven process development with DCR graphsCompliance driven process development with DCR graphs
Compliance driven process development with DCR graphs
 
Day01 01 software requirement concepts
Day01 01 software requirement conceptsDay01 01 software requirement concepts
Day01 01 software requirement concepts
 
Ch 1-Introduction.ppt
Ch 1-Introduction.pptCh 1-Introduction.ppt
Ch 1-Introduction.ppt
 
Software patents
Software patents Software patents
Software patents
 
Intro-Soft-Engg-2.pptx
Intro-Soft-Engg-2.pptxIntro-Soft-Engg-2.pptx
Intro-Soft-Engg-2.pptx
 
Ch 2-RE-process.pptx
Ch 2-RE-process.pptxCh 2-RE-process.pptx
Ch 2-RE-process.pptx
 
Software engg. pressman_ch-6 & 7
Software engg. pressman_ch-6 & 7Software engg. pressman_ch-6 & 7
Software engg. pressman_ch-6 & 7
 
License DSL translation in COMPAS framework
License DSL translation in COMPAS frameworkLicense DSL translation in COMPAS framework
License DSL translation in COMPAS framework
 
SE2023 0201 Software Analysis and Design.pptx
SE2023 0201 Software Analysis and Design.pptxSE2023 0201 Software Analysis and Design.pptx
SE2023 0201 Software Analysis and Design.pptx
 
6. ch 5-understanding requirements
6. ch 5-understanding requirements6. ch 5-understanding requirements
6. ch 5-understanding requirements
 
Hl7 V3 Reference Models 20091123
Hl7 V3 Reference Models 20091123Hl7 V3 Reference Models 20091123
Hl7 V3 Reference Models 20091123
 
software requirement and architecture.pdf
software requirement and architecture.pdfsoftware requirement and architecture.pdf
software requirement and architecture.pdf
 
Verification and validation of knowledge bases using test cases generated by ...
Verification and validation of knowledge bases using test cases generated by ...Verification and validation of knowledge bases using test cases generated by ...
Verification and validation of knowledge bases using test cases generated by ...
 
Knowledge representation and reasoning
Knowledge representation and reasoningKnowledge representation and reasoning
Knowledge representation and reasoning
 
3-Requirements.ppt
3-Requirements.ppt3-Requirements.ppt
3-Requirements.ppt
 
Test design techniques
Test design techniquesTest design techniques
Test design techniques
 
Chapter 2 SRS_241222135554.ppt
Chapter 2 SRS_241222135554.pptChapter 2 SRS_241222135554.ppt
Chapter 2 SRS_241222135554.ppt
 

Recently uploaded

Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024The Digital Insurer
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 

Recently uploaded (20)

Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 

Legal Vocabulary and its Transformation Evaluation using Competency Questions

  • 1. 1 Legal Vocabulary and its Transformation Evaluation using Competency Questions 15th International Conference on AI and Law- ICAIL 2015 11-June 2015 San Diego, CA, USA Shashishekar Ramakrishna, Łukasz Górski and Adrian Paschke
  • 2. 2 In-C Tests : Processing Model 2 Introduction Legal Expert System
  • 3. 3 In-C Tests : Processing Model 3 Model Driven Architecture approach to Legal KR ► OMG : Object Management Group (OMG) ► Founded in 1989 by 11 companies (IBM, Apple, Sun Microsystems etc.) ► Not-for-profit computer industry standards consortium ►Model Driven Architecture
  • 4. 4 Informal to Semi-Formal via Legal Decision Models 35 U.S.C. 112, 1st Paragraph,- Specification The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention. [Ramakrishna , Gorski and Paschke: ESWC Workshop 2015]
  • 5. 5 In-C Tests : Processing Model 5 Semi-Formal Legal KR via SBVR SBVR: Semantics of Business Vocabulary and Business Rules ► Sits on CIM layer of OMG’s MDA (OMG’s standard since 2005, ) ► To support computationalindependent modeling of business rules by business people in business language Two Meta-models defined in Form of vocabularies ► Vocabulary for Describing Business Vocabularies ► Vocabulary for Describing Business Rules
  • 6. 6 In-C Tests : Processing Model 6 SBVR in Legal Domain: ► Legal Concept: (individual concept, object type ) ► e.g. patent, claim, examiner ► Fact type: denoting some relationship b/w 2 or more noun concept ► e.g. patent includes claim ► Legal (procedural/substantive) rule: a rule under legal jurisdiction ► e.g. It is obligatory that a patent includes atleast 1 claim.
  • 7. 7 Semi-Formal Representation ¶ 7.33.01 Rejection : Claim [1] rejected under 35 U.S.C. 112, first paragraph, as based on a disclosure which is not enabling. [2] critical or essentialto the practice of the invention, but not included in the claim(s) is not enabled by the disclosure. 1. This rejection must be preceded by form paragraph 7.30.01 or 7.103. 2. In bracket 2, recite the subject matter omitted from the claims. Legal Concepts Claim, office_action, Paragraphs, essential_subject_matter_requirement, Paragarph_7_33_01 Enables identification of associated context information and relations between them. Context information for each legal concept E.g.: KR4IPLaw Legal Concept Recommender System
  • 8. 8 In-C Tests : Processing Model 8 Semi-Formal Representation contd… Legal Facts (verb concepts are defined in blue) office_action includes paragraphs claim is_rejected_under essential_subject_matter_requirement office_action include statement applicant conceals effective_feature effective_feature is_about the invention examiner applies Paragraph_7_33_01 examiner rejects the claim Legal (procedural) rules (for ¶ 7.33.01) in Structured English: 1. It is obligatory that examiner rejects the claim and office_action includes paragraphs Paragraph_7_33_01 if claim is_rejected_under essential_subject_matter_requirement 2. It is obligatory that office_action include statement and argument and date and drawing if claim is_rejected_under Paragraph_7_33_01 3. It is necessary that examiner applies Paragraph_7_33_01 if applicant conceals effective_feature and effective_feature is_about the invention
  • 9. 9 In-C Tests : Processing Model 9 Semi-Formal to Formal Representation Legal Rules in SBVR-SELegal Facts OWL2
  • 10. 10 In-C Tests : Processing Model 10 Legal Vocabulary Evaluation ? Increases confidence in using the inferred knowledge in the form of legal arguments. Goal is to eliminate black boxes (from end-users perspective) in a (Semi-/) automated decision support systems.
  • 11. 11 Competency Question Design: Actors Content Specialist Design Specialist Interviewer Respondent Legal practitioner Knowledge Modeler Ontology query engine Ontology Creates a set of competency questions defined in semi-formal language. Performs the translation into formal query language
  • 17. 17 CQ based Evaluation: Formal Definition Then: Each CQ should address two generalized conditions: Formal CQs can be defined formally as entailment or consistency problem wrt axioms in ontology If Tontology = a set of axioms Tground = a set of ground literals Q = a first-order legal sentence in the language of Tontology a) Determine if Tontology ∪ Tground ⊨ Q? b) Determine if Tontology ∪ Tground ⊭ ¬Q? => Transformation is correct and verifiable
  • 18. 18 Sample CQs Pattern Selection Question Module What is a claim? Define a X Where is the language of a claim W is/are the X of Y (W ∈ {Where, What, Who} What is a relation between claim and a patent What is a relation between X and Y? What does patent include What does X R? Binary Question Module Is the patent application filed in US? Is/Are X relation Y? Does the patent application include a claim? Do/Does X relation Y? Counting Question Module What is the minimum number of claims in a patent application? The Q of X in Y? (Q∈{number, min, max} CQs and Patterns
  • 19. 19 Formal CQ Pattern Selection Question Module [skos:definition][CE]? SELECT ?LegalConcept ?definition WHERE { ?LegalConcept a owl:Class; Define a claim skos:definition ?definition . } [OPE][CE1][CE2]? processQuery("PREFIX : <abc#> n" + "SELECT ?x ?y WHERE {n" + PropertyValue(?x,:OPE, ?y)"+"}") [CE1][OPE]=[CE2]? SELECT { ?y WHERE {n" + PropertyValue(CE1,:OPE, ?y)"+"}; Binary Question Module [OPE][CE1][CE2]=Y/N? ASK {:OPE rdfs:domain :CE1 ; rdfs:range :CE2.} Counting Question Module [OPE@min/maxCardinality][CE1][CE2]? SELECT ?cardinality WHERE { <http://abc> owl:equivalentClass ?c. ?c owl:qualifiedCardinality ?cardinality } Formal CQs mapped to DL based queries
  • 20. 20 Experimental Results Overall knowledge (in)completeness within the legal vocabulary for our consideredexample Legal vocabulary may be regarded as incomplete, if the legal concepts do not contain of all the necessary definitions, some defined formally and some via its annotation properties
  • 21. 21 Experimental Results Legal knowledge (in-)completeness for indvidual legal concepts
  • 22. 22 Experimental Results Permissible sensitivity inversely proportional to Threshold E.g. : offce_action central legal concept Modification to legal concept office_action → effects several other concepts
  • 23. 23 Legal Rules: Platform Independent Layer: KR4IPLaw
  • 24. 24 Legal Rules: Platform Specific Layer: Prova Rule Engine A rule is evaluated only if guard conditions are evaluated to be True Verification and Validation of legal knowledge increases the clarity of legal arguments generated by a Legal Expert System
  • 25. 25 Further Reading: • Ramakrishna, Gorski and Paschke, 2015. The Role of Pragmatics in Legal Norm Representation. International Workshop On Legal Domain And Semantic Web Applications, ESWC 2015 • Ramakrishna, Paschke 2014 . A Process for Knowledge Transformation and Knowledge Representation of Patent Law. RuleML – 2014 • Paschke, 2006 . Verification, validation and integrity of distributed and interchanged rule based policies and contracts in the semantic web. • Ramakrishna and Paschke. Semi-Automated Vocabulary Building for Structured Legal English. In RuleML 2014, volume 8620 of LNCS. Springer, 2014.
  • 26. 26 Thank you Shashishekar Ramakrishna Free University of Berlin, Dept of Mathematics and Computer Science shashi792@gmail.com Łukasz Górski Nicolaus Copernicus University lgorski@mat.umk.pl Adrian Paschke Free University of Berlin, Dept of Mathematics and Computer Science paschke@inf-fu-berlin.de