SlideShare a Scribd company logo
.lusoftware verification & validation
VVS
Automated
Recommendation of Templates
for Legal Requirements
September 3rd, 2020
Amin Sleimi ∗, Marcello Ceci ∗, Mehrdad Sabetzadeh ¶∗, Lionel C. Briand ∗¶, John Dann §
∗ SnT Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg
¶ School of EECS, University of Ottawa, Canada
§ Central Legislative Service (SCL), Ministry of State, Luxembourg
Context
2
Requirements
Analyst
Legislation
Legal
Requirements
Industry Standards
Competitive Pressure
Market Research
Requirements
Template
Stakeholder
Requirements
Technical
Requirements
Collaboration with the Govt. of Luxembourg
Better understanding of the law through:
• Smart search
• Question Answering systems
• Legal requirements elicitation and
elaboration
RE 2018 paper on automated extraction
of semantic legal metadata
RE 2019 paper on a query system for the
extraction of requirements-related
information
How can we use these metadata items
for legal requirements elicitation?3
Can we use these metadata items to
recommend templates of legal
requirements?
Statement
Fact
Definition
Reference
Condition
Target
Reason
Penalty
Permission
Exception
Obligation
Prohibition
Time
Auxiliary Party
Violation
Agent
Location
Constraint
Modality
Action
Situation
Artifact
Actor
SanctionResult
Statement-level
Concepts
Phrase-level
Concepts
Challenge
• For compliance-rule elicitation, requirement analysts are
interested in writing permissions and obligations.
• A legal text can present several types of statements as we
witnessed in our previous work
• Prior work by Breaux et al. [RE’06] establishes the importance
of balancing rights and duties for legal RE
4
Illustrative Example
…,an individual has a right of access to inspect… a copy of
protected health information …
• Requirement1: An individual shall be able to access to inspect
a copy of protected health information.
• Requirement2: The system shall provide access to inspect a
copy of protected health information to the individual.
5
Problem Description
Possible multiple viewpoints on legal statements:
• Right and obligation
• Permission and obligation
• Power statement and obligation
• Penalty statement (violation) and prohibition …
T. D. Breaux, M. W. Vail, and A. I. Antón, “Towards regulatory compliance: Extracting rights and obligations to align requirements
with regulations,” in Proceedings of the 14th IEEE International Requirements Engineering Conference (RE’06), 2006, pp. 46–55.
P. Darke and G. Shanks, “Stakeholder viewpoints in requirements definition: A framework for understanding viewpoint
development approaches,” Requirements Engineering, vol. 1, no. 2, pp. 88–105, 1996.
W. N. Hohfeld, “Fundamental legal conceptions as applied in judicial reasoning,” The Yale Law Journal, vol. 26, no. 8, pp. 710–770,
1917.
6
Research Questions
• RQ1: Can we come up with a sufficiently expressive set of
patterns for legal requirements, focusing on permissions and
obligations?
• RQ2: Can one define template-recommendation rules over
linguistic cues from legal texts?
• RQ3: If so, how accurate are the template recommendations
made automatically based on linguistic cues?
7
Contribution
• A list of legal requirements templates pertinent to legal RE
• A set of NLP-based rules for template recommendation
8
Related Work
9
Related Work
Support for ≠
stakeholders
Support for ≠
data objects
Textual
Template
Balancing
Viewpoints
Easy Approach To Requirements
Syntax ✘ ✘ ✘
Yoshida et al.'s Functional
Requirements Templates ✘ ✘
Young and Anton's Templates for
Legal Requirements ✘ ✘
Legal Requirement Specification
Language ✘ ✘ ✘
Breaux et al.'s patterns ✘
All these strands of work consider
the manual selection of a template
No Automation
Legal Requirements Templates
10
Proposed Template
Classification of Provisions
in Breaux et al. [RE’06]
Statement with no counterpart Straightforward Provisions
Statement with correlative counterpart Direct Provisions
Statement with implied counterpart
Delegations
Indirect Provisions*
Legal Requirements Templates
11
Template Category Proposed Template Example
Statement with no
counterpart
Actor <modality> Action
A covered entity shall document a
restriction in accordance with §160.530(j)
of this subchapter.
The system <modality> Action
The system shall document a restriction in
accordance with §160.530(j) of this
subchapter.
Statement with correlative
statement
Actor_1 <modality_1> Action_1 to Actor_2
The data subject shall be able to obtain
confirmation as to whether or not personal
data concerning him or her are being
processed from the controller.
Actor_2 <modality_2> Action_2 to Actor_1
The controller shall provide confirmation
as to whether or not personal data
concerning him or her are being processed
to the data subject.
Statement with implied
statement
Actor_1 <modality> Delegation_Action Actor_2
A consumer shall have the right to request
to a business that they disclose to that
consumer the sale of personal
information.
Actor_2 <modality_2> Action_2 to Actor_1 if R1
A business shall disclose the sale of
personal information to the consumer if
requested by the consumer.
Structure of the Proposed
Templates
• Permission with no counterpart
• Permission with correlative counterpart
• Permission with implied counterpart
12
Statement type:
Permission
Verbenet + Metax Cues
Approach
1. Extract the statement type of the legal provision
2. Process the main verb
3. Recommend the legal requirement template
13
Rules for Requirements
Templates Recommendation
14
Recommendation Rule Example
IF (“correlative verb” == False
AND statement type = type1 )
Then type1 with no counterpart
A covered entity shall document a restriction in
accordance with §160.530(j) of this subchapter.
IF (“correlative verb” == TRUE
AND “implied trigger” == False
AND statement type = type2 )
Then type2 with correlative
The data subject shall be able to obtain confirmation as to
whether or not personal data concerning him or her are
being processed from the controller.
IF (“correlative verb” == TRUE
AND “implied trigger” == TRUE
AND statement type = type2 )
Then type2 with implied
A consumer shall have the right to request to a business
that they disclose to that consumer the sale of personal
information.
Illustrative Example (1/2)
• The national health service may obtain all the information
relevant to the processing of a patient’s case from the health
service provider
• Main Verb: obtain
• Frame: obtain-13.5 : Agent Verb Theme [organization or
animate] {for} Asset
• Requirement: The health service provider shall communicate
all the information relevant to the processing of a patient’s
case to the national health service
15
Illustrative Example (2/2)
• The court may order a commission to verify the accounting
books
• Main Verb: order
• Frame: order-60 : Agent Verb Recipient Topic
• Requirement: The commission shall verify the accounting
books if the court orders to do so.
16
Selection of the Training Corpus
• We conducted a preliminary study on 7 legal domains (i.e.,
commerce, environment, health, labor, penal, traffic, taxation)
• The labor and health laws presented a high occurrence of
statements (20%) with correlative and implied statements in
comparison with other laws
17
Qualitative Study
• We reviewed the list of verbs for our dataset and validated the
presence of a corresponding trigger (we excluded 83 verbs
and 2 phrasal verbs)
• We selected a dataset (500 statements from the labor law and
another 500 for health law respectively) and we evaluated our
approach using standard accuracy metrics (i.e., precision and
recall) for class of template suggestion
18
Evaluation
19
Corpus
Template
Category
Ground Truth
Results
Correct (TP)
Misclassified
(FP)
Missed (FN) Precision Recall
Labor
Statement with
no counterpart
96 80 11 16 87,9% 83,3%
Statement with
correlative
statement
47 41 15 6 73,2% 87,2%
Statement with
implied
statement
13 9 1 4 90,0% 69,2%
Subtotal 156 130 27 26 82,8% 83,3%
Health
Statement with
no counterpart
107 84 14 23 85,7% 78,5%
Statement with
correlative
statement
37 32 22 5 59,3% 86,5%
Statement with
implied
statement
16 14 3 2 82,4% 87,5%
Subtotal 160 130 39 30 76,9% 81,3%
Total 316 260 66 56 79,8% 82,3%
Error Analysis
• Nominalization: the main action is nominalized
e.g., “the investigation shall be conducted for breaches”
• Phrasal verbs: e.g, “to take effect” is the actual main verb not
“take”
• Legal terminology: e.g, the verb “to suspend” has a
commencement meaning
• We devised heuristics to deal with the aforementioned cases.
However, the lists we constructed from the qualitative study
are still incomplete
20
Lessons Learned
• Incorporating human feedback identifies more accurately
suitable requirements templates (recall of 94,3% and precision of
90,6% )
• Identifying the main action in the statement is key to detect the
presence of multiple viewpoints
• Domain knowledge is crucial for the recommendation of
templates for requirements
• Handling multiple viewpoints is a paramount step for
requirements elicitation
21
.lusoftware verification & validation
VVS
Automated
Recommendation of Templates
for Legal Requirements
September 3rd, 2020
Amin Sleimi ∗, Marcello Ceci ∗, Mehrdad Sabetzadeh ¶∗, Lionel C. Briand ∗¶, John Dann §
∗ SnT Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg
¶ School of EECS, University of Ottawa, Canada
§ Central Legislative Service (SCL), Ministry of State, Luxembourg

More Related Content

What's hot

Disclosure, Exposure and the "Right to be Forgotten" After Google Spain
Disclosure, Exposure and the "Right to be Forgotten" After Google SpainDisclosure, Exposure and the "Right to be Forgotten" After Google Spain
Disclosure, Exposure and the "Right to be Forgotten" After Google Spain
David Erdos
 
European Data Protection and Social Networking
European Data Protection and Social NetworkingEuropean Data Protection and Social Networking
European Data Protection and Social Networking
David Erdos
 
Hildebrandt baker robbins presentation for coo roundtable 2010 by dave cunn...
Hildebrandt baker robbins presentation for coo roundtable 2010   by dave cunn...Hildebrandt baker robbins presentation for coo roundtable 2010   by dave cunn...
Hildebrandt baker robbins presentation for coo roundtable 2010 by dave cunn...
David Cunningham
 

What's hot (20)

Bruce, T. R., and Richards, R. C. (2011). Adapting Specialized Legal Metadata...
Bruce, T. R., and Richards, R. C. (2011). Adapting Specialized Legal Metadata...Bruce, T. R., and Richards, R. C. (2011). Adapting Specialized Legal Metadata...
Bruce, T. R., and Richards, R. C. (2011). Adapting Specialized Legal Metadata...
 
UK GDPR: What New Direction?
UK GDPR:  What New Direction?UK GDPR:  What New Direction?
UK GDPR: What New Direction?
 
Disclosure, Exposure and the "Right to be Forgotten" After Google Spain
Disclosure, Exposure and the "Right to be Forgotten" After Google SpainDisclosure, Exposure and the "Right to be Forgotten" After Google Spain
Disclosure, Exposure and the "Right to be Forgotten" After Google Spain
 
The GDPR, Brexit, the UK and adequacy
The GDPR, Brexit, the UK and adequacyThe GDPR, Brexit, the UK and adequacy
The GDPR, Brexit, the UK and adequacy
 
Quantitative Methods for Lawyers - Class #1 - Why Quantitative Methods + Res...
Quantitative Methods for Lawyers - Class #1 -  Why Quantitative Methods + Res...Quantitative Methods for Lawyers - Class #1 -  Why Quantitative Methods + Res...
Quantitative Methods for Lawyers - Class #1 - Why Quantitative Methods + Res...
 
The UK and EU Personal Data Regime After Brexit: Another Switzerland?
The UK and EU Personal Data Regime After Brexit: Another Switzerland?The UK and EU Personal Data Regime After Brexit: Another Switzerland?
The UK and EU Personal Data Regime After Brexit: Another Switzerland?
 
Didier Reynders letter to the EU Parliament
Didier Reynders letter to the EU ParliamentDidier Reynders letter to the EU Parliament
Didier Reynders letter to the EU Parliament
 
How to get started with being GDPR compliant
How to get started with being GDPR compliantHow to get started with being GDPR compliant
How to get started with being GDPR compliant
 
Regulation of Medical Research under European Data Protection
Regulation of Medical Research under European Data ProtectionRegulation of Medical Research under European Data Protection
Regulation of Medical Research under European Data Protection
 
GDPR - A practical guide
GDPR - A practical guideGDPR - A practical guide
GDPR - A practical guide
 
A quick look at gdpr
A quick look at gdprA quick look at gdpr
A quick look at gdpr
 
GDPR Training Course - Training Express
GDPR Training Course - Training ExpressGDPR Training Course - Training Express
GDPR Training Course - Training Express
 
Data Protection and Journalism: The Changing Landscape
Data Protection and Journalism: The Changing LandscapeData Protection and Journalism: The Changing Landscape
Data Protection and Journalism: The Changing Landscape
 
Brexit Data Protection Update: The EU, US and UK Perspective
Brexit Data Protection Update: The EU, US and UK PerspectiveBrexit Data Protection Update: The EU, US and UK Perspective
Brexit Data Protection Update: The EU, US and UK Perspective
 
European Data Protection and Social Networking
European Data Protection and Social NetworkingEuropean Data Protection and Social Networking
European Data Protection and Social Networking
 
Measure Twice, Cut Once - Solving the Legal Profession Biggest Challenges Tog...
Measure Twice, Cut Once - Solving the Legal Profession Biggest Challenges Tog...Measure Twice, Cut Once - Solving the Legal Profession Biggest Challenges Tog...
Measure Twice, Cut Once - Solving the Legal Profession Biggest Challenges Tog...
 
Replacement standard contractual clauses
Replacement standard contractual clausesReplacement standard contractual clauses
Replacement standard contractual clauses
 
Hildebrandt baker robbins presentation for coo roundtable 2010 by dave cunn...
Hildebrandt baker robbins presentation for coo roundtable 2010   by dave cunn...Hildebrandt baker robbins presentation for coo roundtable 2010   by dave cunn...
Hildebrandt baker robbins presentation for coo roundtable 2010 by dave cunn...
 
Practical Guide to GDPR 2017
Practical Guide to GDPR 2017Practical Guide to GDPR 2017
Practical Guide to GDPR 2017
 
GDPR: A Threat or Opportunity? www.normanbroadbent.
GDPR: A Threat or Opportunity? www.normanbroadbent.GDPR: A Threat or Opportunity? www.normanbroadbent.
GDPR: A Threat or Opportunity? www.normanbroadbent.
 

Similar to Automated Recommendation of Templates for Legal Requirements

You will conduct system selection, which requires completion of .docx
You will conduct system selection, which requires completion of .docxYou will conduct system selection, which requires completion of .docx
You will conduct system selection, which requires completion of .docx
jeffevans62972
 
EKovacevich-IT697-Phase 5 IP
EKovacevich-IT697-Phase 5 IPEKovacevich-IT697-Phase 5 IP
EKovacevich-IT697-Phase 5 IP
EDDY KOVACEVICH
 

Similar to Automated Recommendation of Templates for Legal Requirements (20)

Legal & Regulatory Update SPeRS 2.0
Legal & Regulatory Update SPeRS 2.0Legal & Regulatory Update SPeRS 2.0
Legal & Regulatory Update SPeRS 2.0
 
Fun Writing Paper
Fun Writing PaperFun Writing Paper
Fun Writing Paper
 
Fun Writing Paper
Fun Writing PaperFun Writing Paper
Fun Writing Paper
 
Fun Writing Paper. Online assignment writing service.
Fun Writing Paper. Online assignment writing service.Fun Writing Paper. Online assignment writing service.
Fun Writing Paper. Online assignment writing service.
 
Understanding basics of software development and healthcare
Understanding basics of software development and healthcareUnderstanding basics of software development and healthcare
Understanding basics of software development and healthcare
 
Employee Background Checks: Avoid the Pitfalls
Employee Background Checks: Avoid the PitfallsEmployee Background Checks: Avoid the Pitfalls
Employee Background Checks: Avoid the Pitfalls
 
Regulatory Instability, BPM Technology, and BPM Skill Configurations
Regulatory Instability, BPM Technology, and BPM Skill ConfigurationsRegulatory Instability, BPM Technology, and BPM Skill Configurations
Regulatory Instability, BPM Technology, and BPM Skill Configurations
 
Artificial Intelligence and Law - 
A Primer
Artificial Intelligence and Law - 
A Primer Artificial Intelligence and Law - 
A Primer
Artificial Intelligence and Law - 
A Primer
 
The Future of Legal Services, NCSB Committee to Study Regulatory Reform, July...
The Future of Legal Services, NCSB Committee to Study Regulatory Reform, July...The Future of Legal Services, NCSB Committee to Study Regulatory Reform, July...
The Future of Legal Services, NCSB Committee to Study Regulatory Reform, July...
 
Therapist Case Report
Therapist Case ReportTherapist Case Report
Therapist Case Report
 
Law homework help
Law homework helpLaw homework help
Law homework help
 
Law homework help
Law homework helpLaw homework help
Law homework help
 
Terminology Matching of Requirements Specification Documents and Regulations ...
Terminology Matching of Requirements Specification Documents and Regulations ...Terminology Matching of Requirements Specification Documents and Regulations ...
Terminology Matching of Requirements Specification Documents and Regulations ...
 
How To Write An Argumentative Essay Step By Step For Ielts
How To Write An Argumentative Essay Step By Step For IeltsHow To Write An Argumentative Essay Step By Step For Ielts
How To Write An Argumentative Essay Step By Step For Ielts
 
Child Labour Essay In English Very Simple - YouTube
Child Labour Essay In English Very Simple - YouTubeChild Labour Essay In English Very Simple - YouTube
Child Labour Essay In English Very Simple - YouTube
 
You will conduct system selection, which requires completion of .docx
You will conduct system selection, which requires completion of .docxYou will conduct system selection, which requires completion of .docx
You will conduct system selection, which requires completion of .docx
 
EKovacevich-IT697-Phase 5 IP
EKovacevich-IT697-Phase 5 IPEKovacevich-IT697-Phase 5 IP
EKovacevich-IT697-Phase 5 IP
 
5 lexis nexis legal innovation powered by ai_min chen
5 lexis nexis legal innovation powered by ai_min chen5 lexis nexis legal innovation powered by ai_min chen
5 lexis nexis legal innovation powered by ai_min chen
 
Artificial Intelligence and Machine Learning
Artificial Intelligence and Machine LearningArtificial Intelligence and Machine Learning
Artificial Intelligence and Machine Learning
 
Malware analysis
Malware analysisMalware analysis
Malware analysis
 

More from Lionel Briand

Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-...
Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-...Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-...
Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-...
Lionel Briand
 
Data-driven Mutation Analysis for Cyber-Physical Systems
Data-driven Mutation Analysis for Cyber-Physical SystemsData-driven Mutation Analysis for Cyber-Physical Systems
Data-driven Mutation Analysis for Cyber-Physical Systems
Lionel Briand
 
Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems
Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled SystemsMany-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems
Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems
Lionel Briand
 
ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolu...
ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolu...ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolu...
ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolu...
Lionel Briand
 
Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction ...
Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction ...Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction ...
Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction ...
Lionel Briand
 
Revisiting the Notion of Diversity in Software Testing
Revisiting the Notion of Diversity in Software TestingRevisiting the Notion of Diversity in Software Testing
Revisiting the Notion of Diversity in Software Testing
Lionel Briand
 
Applications of Search-based Software Testing to Trustworthy Artificial Intel...
Applications of Search-based Software Testing to Trustworthy Artificial Intel...Applications of Search-based Software Testing to Trustworthy Artificial Intel...
Applications of Search-based Software Testing to Trustworthy Artificial Intel...
Lionel Briand
 
Autonomous Systems: How to Address the Dilemma between Autonomy and Safety
Autonomous Systems: How to Address the Dilemma between Autonomy and SafetyAutonomous Systems: How to Address the Dilemma between Autonomy and Safety
Autonomous Systems: How to Address the Dilemma between Autonomy and Safety
Lionel Briand
 
Mathematicians, Social Scientists, or Engineers? The Split Minds of Software ...
Mathematicians, Social Scientists, or Engineers? The Split Minds of Software ...Mathematicians, Social Scientists, or Engineers? The Split Minds of Software ...
Mathematicians, Social Scientists, or Engineers? The Split Minds of Software ...
Lionel Briand
 
Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results ...
Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results ...Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results ...
Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results ...
Lionel Briand
 
On Systematically Building a Controlled Natural Language for Functional Requi...
On Systematically Building a Controlled Natural Language for Functional Requi...On Systematically Building a Controlled Natural Language for Functional Requi...
On Systematically Building a Controlled Natural Language for Functional Requi...
Lionel Briand
 
Efficient Online Testing for DNN-Enabled Systems using Surrogate-Assisted and...
Efficient Online Testing for DNN-Enabled Systems using Surrogate-Assisted and...Efficient Online Testing for DNN-Enabled Systems using Surrogate-Assisted and...
Efficient Online Testing for DNN-Enabled Systems using Surrogate-Assisted and...
Lionel Briand
 
Guidelines for Assessing the Accuracy of Log Message Template Identification ...
Guidelines for Assessing the Accuracy of Log Message Template Identification ...Guidelines for Assessing the Accuracy of Log Message Template Identification ...
Guidelines for Assessing the Accuracy of Log Message Template Identification ...
Lionel Briand
 
A Theoretical Framework for Understanding the Relationship between Log Parsin...
A Theoretical Framework for Understanding the Relationship between Log Parsin...A Theoretical Framework for Understanding the Relationship between Log Parsin...
A Theoretical Framework for Understanding the Relationship between Log Parsin...
Lionel Briand
 

More from Lionel Briand (20)

Precise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalPrecise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive Goal
 
Large Language Models for Test Case Evolution and Repair
Large Language Models for Test Case Evolution and RepairLarge Language Models for Test Case Evolution and Repair
Large Language Models for Test Case Evolution and Repair
 
Metamorphic Testing for Web System Security
Metamorphic Testing for Web System SecurityMetamorphic Testing for Web System Security
Metamorphic Testing for Web System Security
 
Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-...
Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-...Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-...
Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-...
 
Fuzzing for CPS Mutation Testing
Fuzzing for CPS Mutation TestingFuzzing for CPS Mutation Testing
Fuzzing for CPS Mutation Testing
 
Data-driven Mutation Analysis for Cyber-Physical Systems
Data-driven Mutation Analysis for Cyber-Physical SystemsData-driven Mutation Analysis for Cyber-Physical Systems
Data-driven Mutation Analysis for Cyber-Physical Systems
 
Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems
Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled SystemsMany-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems
Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems
 
ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolu...
ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolu...ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolu...
ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolu...
 
Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction ...
Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction ...Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction ...
Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction ...
 
PRINS: Scalable Model Inference for Component-based System Logs
PRINS: Scalable Model Inference for Component-based System LogsPRINS: Scalable Model Inference for Component-based System Logs
PRINS: Scalable Model Inference for Component-based System Logs
 
Revisiting the Notion of Diversity in Software Testing
Revisiting the Notion of Diversity in Software TestingRevisiting the Notion of Diversity in Software Testing
Revisiting the Notion of Diversity in Software Testing
 
Applications of Search-based Software Testing to Trustworthy Artificial Intel...
Applications of Search-based Software Testing to Trustworthy Artificial Intel...Applications of Search-based Software Testing to Trustworthy Artificial Intel...
Applications of Search-based Software Testing to Trustworthy Artificial Intel...
 
Autonomous Systems: How to Address the Dilemma between Autonomy and Safety
Autonomous Systems: How to Address the Dilemma between Autonomy and SafetyAutonomous Systems: How to Address the Dilemma between Autonomy and Safety
Autonomous Systems: How to Address the Dilemma between Autonomy and Safety
 
Mathematicians, Social Scientists, or Engineers? The Split Minds of Software ...
Mathematicians, Social Scientists, or Engineers? The Split Minds of Software ...Mathematicians, Social Scientists, or Engineers? The Split Minds of Software ...
Mathematicians, Social Scientists, or Engineers? The Split Minds of Software ...
 
Reinforcement Learning for Test Case Prioritization
Reinforcement Learning for Test Case PrioritizationReinforcement Learning for Test Case Prioritization
Reinforcement Learning for Test Case Prioritization
 
Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results ...
Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results ...Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results ...
Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results ...
 
On Systematically Building a Controlled Natural Language for Functional Requi...
On Systematically Building a Controlled Natural Language for Functional Requi...On Systematically Building a Controlled Natural Language for Functional Requi...
On Systematically Building a Controlled Natural Language for Functional Requi...
 
Efficient Online Testing for DNN-Enabled Systems using Surrogate-Assisted and...
Efficient Online Testing for DNN-Enabled Systems using Surrogate-Assisted and...Efficient Online Testing for DNN-Enabled Systems using Surrogate-Assisted and...
Efficient Online Testing for DNN-Enabled Systems using Surrogate-Assisted and...
 
Guidelines for Assessing the Accuracy of Log Message Template Identification ...
Guidelines for Assessing the Accuracy of Log Message Template Identification ...Guidelines for Assessing the Accuracy of Log Message Template Identification ...
Guidelines for Assessing the Accuracy of Log Message Template Identification ...
 
A Theoretical Framework for Understanding the Relationship between Log Parsin...
A Theoretical Framework for Understanding the Relationship between Log Parsin...A Theoretical Framework for Understanding the Relationship between Log Parsin...
A Theoretical Framework for Understanding the Relationship between Log Parsin...
 

Recently uploaded

AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
Alluxio, Inc.
 
Prosigns: Transforming Business with Tailored Technology Solutions
Prosigns: Transforming Business with Tailored Technology SolutionsProsigns: Transforming Business with Tailored Technology Solutions
Prosigns: Transforming Business with Tailored Technology Solutions
Prosigns
 

Recently uploaded (20)

Studiovity film pre-production and screenwriting software
Studiovity film pre-production and screenwriting softwareStudiovity film pre-production and screenwriting software
Studiovity film pre-production and screenwriting software
 
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
 
Using IESVE for Room Loads Analysis - Australia & New Zealand
Using IESVE for Room Loads Analysis - Australia & New ZealandUsing IESVE for Room Loads Analysis - Australia & New Zealand
Using IESVE for Room Loads Analysis - Australia & New Zealand
 
AI/ML Infra Meetup | Perspective on Deep Learning Framework
AI/ML Infra Meetup | Perspective on Deep Learning FrameworkAI/ML Infra Meetup | Perspective on Deep Learning Framework
AI/ML Infra Meetup | Perspective on Deep Learning Framework
 
iGaming Platform & Lottery Solutions by Skilrock
iGaming Platform & Lottery Solutions by SkilrockiGaming Platform & Lottery Solutions by Skilrock
iGaming Platform & Lottery Solutions by Skilrock
 
AI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAG
AI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAGAI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAG
AI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAG
 
SOCRadar Research Team: Latest Activities of IntelBroker
SOCRadar Research Team: Latest Activities of IntelBrokerSOCRadar Research Team: Latest Activities of IntelBroker
SOCRadar Research Team: Latest Activities of IntelBroker
 
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoamOpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
 
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.ILBeyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
 
Prosigns: Transforming Business with Tailored Technology Solutions
Prosigns: Transforming Business with Tailored Technology SolutionsProsigns: Transforming Business with Tailored Technology Solutions
Prosigns: Transforming Business with Tailored Technology Solutions
 
Accelerate Enterprise Software Engineering with Platformless
Accelerate Enterprise Software Engineering with PlatformlessAccelerate Enterprise Software Engineering with Platformless
Accelerate Enterprise Software Engineering with Platformless
 
Corporate Management | Session 3 of 3 | Tendenci AMS
Corporate Management | Session 3 of 3 | Tendenci AMSCorporate Management | Session 3 of 3 | Tendenci AMS
Corporate Management | Session 3 of 3 | Tendenci AMS
 
Cyaniclab : Software Development Agency Portfolio.pdf
Cyaniclab : Software Development Agency Portfolio.pdfCyaniclab : Software Development Agency Portfolio.pdf
Cyaniclab : Software Development Agency Portfolio.pdf
 
top nidhi software solution freedownload
top nidhi software solution freedownloadtop nidhi software solution freedownload
top nidhi software solution freedownload
 
Breaking the Code : A Guide to WhatsApp Business API.pdf
Breaking the Code : A Guide to WhatsApp Business API.pdfBreaking the Code : A Guide to WhatsApp Business API.pdf
Breaking the Code : A Guide to WhatsApp Business API.pdf
 
How Does XfilesPro Ensure Security While Sharing Documents in Salesforce?
How Does XfilesPro Ensure Security While Sharing Documents in Salesforce?How Does XfilesPro Ensure Security While Sharing Documents in Salesforce?
How Does XfilesPro Ensure Security While Sharing Documents in Salesforce?
 
Agnieszka Andrzejewska - BIM School Course in Kraków
Agnieszka Andrzejewska - BIM School Course in KrakówAgnieszka Andrzejewska - BIM School Course in Kraków
Agnieszka Andrzejewska - BIM School Course in Kraków
 
TROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERROR
TROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERRORTROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERROR
TROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERROR
 
WSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital Transformation
WSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital TransformationWSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital Transformation
WSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital Transformation
 
Designing for Privacy in Amazon Web Services
Designing for Privacy in Amazon Web ServicesDesigning for Privacy in Amazon Web Services
Designing for Privacy in Amazon Web Services
 

Automated Recommendation of Templates for Legal Requirements

  • 1. .lusoftware verification & validation VVS Automated Recommendation of Templates for Legal Requirements September 3rd, 2020 Amin Sleimi ∗, Marcello Ceci ∗, Mehrdad Sabetzadeh ¶∗, Lionel C. Briand ∗¶, John Dann § ∗ SnT Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg ¶ School of EECS, University of Ottawa, Canada § Central Legislative Service (SCL), Ministry of State, Luxembourg
  • 2. Context 2 Requirements Analyst Legislation Legal Requirements Industry Standards Competitive Pressure Market Research Requirements Template Stakeholder Requirements Technical Requirements
  • 3. Collaboration with the Govt. of Luxembourg Better understanding of the law through: • Smart search • Question Answering systems • Legal requirements elicitation and elaboration RE 2018 paper on automated extraction of semantic legal metadata RE 2019 paper on a query system for the extraction of requirements-related information How can we use these metadata items for legal requirements elicitation?3 Can we use these metadata items to recommend templates of legal requirements? Statement Fact Definition Reference Condition Target Reason Penalty Permission Exception Obligation Prohibition Time Auxiliary Party Violation Agent Location Constraint Modality Action Situation Artifact Actor SanctionResult Statement-level Concepts Phrase-level Concepts
  • 4. Challenge • For compliance-rule elicitation, requirement analysts are interested in writing permissions and obligations. • A legal text can present several types of statements as we witnessed in our previous work • Prior work by Breaux et al. [RE’06] establishes the importance of balancing rights and duties for legal RE 4
  • 5. Illustrative Example …,an individual has a right of access to inspect… a copy of protected health information … • Requirement1: An individual shall be able to access to inspect a copy of protected health information. • Requirement2: The system shall provide access to inspect a copy of protected health information to the individual. 5
  • 6. Problem Description Possible multiple viewpoints on legal statements: • Right and obligation • Permission and obligation • Power statement and obligation • Penalty statement (violation) and prohibition … T. D. Breaux, M. W. Vail, and A. I. Antón, “Towards regulatory compliance: Extracting rights and obligations to align requirements with regulations,” in Proceedings of the 14th IEEE International Requirements Engineering Conference (RE’06), 2006, pp. 46–55. P. Darke and G. Shanks, “Stakeholder viewpoints in requirements definition: A framework for understanding viewpoint development approaches,” Requirements Engineering, vol. 1, no. 2, pp. 88–105, 1996. W. N. Hohfeld, “Fundamental legal conceptions as applied in judicial reasoning,” The Yale Law Journal, vol. 26, no. 8, pp. 710–770, 1917. 6
  • 7. Research Questions • RQ1: Can we come up with a sufficiently expressive set of patterns for legal requirements, focusing on permissions and obligations? • RQ2: Can one define template-recommendation rules over linguistic cues from legal texts? • RQ3: If so, how accurate are the template recommendations made automatically based on linguistic cues? 7
  • 8. Contribution • A list of legal requirements templates pertinent to legal RE • A set of NLP-based rules for template recommendation 8
  • 9. Related Work 9 Related Work Support for ≠ stakeholders Support for ≠ data objects Textual Template Balancing Viewpoints Easy Approach To Requirements Syntax ✘ ✘ ✘ Yoshida et al.'s Functional Requirements Templates ✘ ✘ Young and Anton's Templates for Legal Requirements ✘ ✘ Legal Requirement Specification Language ✘ ✘ ✘ Breaux et al.'s patterns ✘ All these strands of work consider the manual selection of a template No Automation
  • 10. Legal Requirements Templates 10 Proposed Template Classification of Provisions in Breaux et al. [RE’06] Statement with no counterpart Straightforward Provisions Statement with correlative counterpart Direct Provisions Statement with implied counterpart Delegations Indirect Provisions*
  • 11. Legal Requirements Templates 11 Template Category Proposed Template Example Statement with no counterpart Actor <modality> Action A covered entity shall document a restriction in accordance with §160.530(j) of this subchapter. The system <modality> Action The system shall document a restriction in accordance with §160.530(j) of this subchapter. Statement with correlative statement Actor_1 <modality_1> Action_1 to Actor_2 The data subject shall be able to obtain confirmation as to whether or not personal data concerning him or her are being processed from the controller. Actor_2 <modality_2> Action_2 to Actor_1 The controller shall provide confirmation as to whether or not personal data concerning him or her are being processed to the data subject. Statement with implied statement Actor_1 <modality> Delegation_Action Actor_2 A consumer shall have the right to request to a business that they disclose to that consumer the sale of personal information. Actor_2 <modality_2> Action_2 to Actor_1 if R1 A business shall disclose the sale of personal information to the consumer if requested by the consumer.
  • 12. Structure of the Proposed Templates • Permission with no counterpart • Permission with correlative counterpart • Permission with implied counterpart 12 Statement type: Permission Verbenet + Metax Cues
  • 13. Approach 1. Extract the statement type of the legal provision 2. Process the main verb 3. Recommend the legal requirement template 13
  • 14. Rules for Requirements Templates Recommendation 14 Recommendation Rule Example IF (“correlative verb” == False AND statement type = type1 ) Then type1 with no counterpart A covered entity shall document a restriction in accordance with §160.530(j) of this subchapter. IF (“correlative verb” == TRUE AND “implied trigger” == False AND statement type = type2 ) Then type2 with correlative The data subject shall be able to obtain confirmation as to whether or not personal data concerning him or her are being processed from the controller. IF (“correlative verb” == TRUE AND “implied trigger” == TRUE AND statement type = type2 ) Then type2 with implied A consumer shall have the right to request to a business that they disclose to that consumer the sale of personal information.
  • 15. Illustrative Example (1/2) • The national health service may obtain all the information relevant to the processing of a patient’s case from the health service provider • Main Verb: obtain • Frame: obtain-13.5 : Agent Verb Theme [organization or animate] {for} Asset • Requirement: The health service provider shall communicate all the information relevant to the processing of a patient’s case to the national health service 15
  • 16. Illustrative Example (2/2) • The court may order a commission to verify the accounting books • Main Verb: order • Frame: order-60 : Agent Verb Recipient Topic • Requirement: The commission shall verify the accounting books if the court orders to do so. 16
  • 17. Selection of the Training Corpus • We conducted a preliminary study on 7 legal domains (i.e., commerce, environment, health, labor, penal, traffic, taxation) • The labor and health laws presented a high occurrence of statements (20%) with correlative and implied statements in comparison with other laws 17
  • 18. Qualitative Study • We reviewed the list of verbs for our dataset and validated the presence of a corresponding trigger (we excluded 83 verbs and 2 phrasal verbs) • We selected a dataset (500 statements from the labor law and another 500 for health law respectively) and we evaluated our approach using standard accuracy metrics (i.e., precision and recall) for class of template suggestion 18
  • 19. Evaluation 19 Corpus Template Category Ground Truth Results Correct (TP) Misclassified (FP) Missed (FN) Precision Recall Labor Statement with no counterpart 96 80 11 16 87,9% 83,3% Statement with correlative statement 47 41 15 6 73,2% 87,2% Statement with implied statement 13 9 1 4 90,0% 69,2% Subtotal 156 130 27 26 82,8% 83,3% Health Statement with no counterpart 107 84 14 23 85,7% 78,5% Statement with correlative statement 37 32 22 5 59,3% 86,5% Statement with implied statement 16 14 3 2 82,4% 87,5% Subtotal 160 130 39 30 76,9% 81,3% Total 316 260 66 56 79,8% 82,3%
  • 20. Error Analysis • Nominalization: the main action is nominalized e.g., “the investigation shall be conducted for breaches” • Phrasal verbs: e.g, “to take effect” is the actual main verb not “take” • Legal terminology: e.g, the verb “to suspend” has a commencement meaning • We devised heuristics to deal with the aforementioned cases. However, the lists we constructed from the qualitative study are still incomplete 20
  • 21. Lessons Learned • Incorporating human feedback identifies more accurately suitable requirements templates (recall of 94,3% and precision of 90,6% ) • Identifying the main action in the statement is key to detect the presence of multiple viewpoints • Domain knowledge is crucial for the recommendation of templates for requirements • Handling multiple viewpoints is a paramount step for requirements elicitation 21
  • 22. .lusoftware verification & validation VVS Automated Recommendation of Templates for Legal Requirements September 3rd, 2020 Amin Sleimi ∗, Marcello Ceci ∗, Mehrdad Sabetzadeh ¶∗, Lionel C. Briand ∗¶, John Dann § ∗ SnT Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg ¶ School of EECS, University of Ottawa, Canada § Central Legislative Service (SCL), Ministry of State, Luxembourg