=Paper=
{{Paper
|id=Vol-2049/08paper
|storemode=property
|title=SmaRT Visualisation of Legal Rules for Compliance
|pdfUrl=https://ceur-ws.org/Vol-2049/08paper.pdf
|volume=Vol-2049
|authors=Selja Seppälä,Marcello Ceci,Hai Huang,Leona O'Brien,Tom Butler
|dblpUrl=https://dblp.org/rec/conf/jurix/SeppalaCHOB17
}}
==SmaRT Visualisation of Legal Rules for Compliance==
https://ceur-ws.org/Vol-2049/08paper.pdf
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
SmaRT Visualisation of Legal Rules for
Compliance
Selja Seppälä, Marcello Ceci? , Hai Huang, Leona O’Brien, and Tom Butler
Governance, Risk, and Compliance Technology Center
University College Cork
13 South Mall, Cork, Ireland
{selja.seppala,marcello.ceci,hai.huang,tbutler,leona.obrien}@ucc.ie
http://www.grctc.com
Abstract. This paper presents a visualization technique to assist legal
experts in formalising their interpretation of legal texts in terms of regu-
latory requirements. (Semi-)automation of compliance processes requires
a machine-readable version of legal requirements in a format that en-
ables effective compliance assessment. The use of a semi-structured con-
trolled natural language as an intermediate step of the translation from
a human-readable text to a machine-readable and understandable for-
mat ensures that the process of interpretation of those requirements is as
simple as possible. However, it does not ensure that the formal represen-
tation resulting from the interpretation faithfully represents the intended
semantics provided by the legal expert. Visualization techniques such as
property graphs in Neo4j could fill this gap, allowing legal experts to un-
derstand and control the formal representation of the result of their act
of interpretation.
Keywords: SBVR, RegTech, Controlled Natural Languages, Neo4j
1 Introduction
Ensuring compliance with regulatory requirements represents a considerable
challenge for industries that deal with large amounts of data across different
jurisdictions. This is particularly true for safety-critical industries such as the
international financial industry, driven by the proliferation and complexity of
the financial regulatory environment in the aftermath of the global financial cri-
sis. The wide acceptance in the industry that traditional Governance, Risk, and
Compliance (GRC) information systems are in deficit is leading to a growing
interest in semantic technologies as a solution [1, 4]. By using such technologies,
compliance of companies’ business policies and processes – and even of their
activities represented by company data – could be assessed automatically. Even
before achieving such an integration, exploration of the regulatory space could
be performed in a very effective way, e.g., by querying the relevant regulatory
?
Corresponding author.
73
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
knowledge base to quickly retrieve all relevant obligations for a certain business
activity.
One of the problems with representing the interpretation of legal rules in
a machine-readable format lies in the lack of understanding and control of the
formal models by legal experts. Some research approaches [9, 17, 10, 13] rely on
formal representations of rules that, despite being very expressive and thus al-
lowing powerful inference, are not provided in a format that is understandable
and manageable by a legal expert. To overcome this, other approaches [16, 12]
suggest the use of controlled natural languages to translate the semantics of a
legal text into a machine-readable representation. Similarly, our approach aims
to define a controlled natural language that has complete coverage of the rele-
vant legal effects of requirements while at the same time constraining the natural
language as little as possible.
The research behind the present paper follows an approach that allows le-
gal experts to interpret a legal statement by rewriting it in a semi-structured
controlled natural language using a dedicated software called SmaRT. The core
translation process relies on the markup and annotation of strings in the rewrit-
ten text in terms of given vocabulary elements. However, this is not sufficient to
put legal experts in control of all the elements that compose the logical formula-
tion of the legal rule. The paper thus presents a possible solution that relies on
property graphs to visualize the interpreted rule and all the relevant elements
in a format that a lawyer can understand and manipulate. This should allow to
ensure that the human-readable text and the machine-readable output of a legal
rule carry the same semantics, thus achieving a semi-automatic translation of
legal requirements for compliance purposes.
The rest of the paper is structured as follows. In the next section, we in-
troduce the Regulatory Interpretation Methodology (RIM) and the controlled
natural language. In Section 3, we look into relevant details of the RIM and the
rule-editing tool SmaRT to understand the visualisation needs for the rule in-
terpretation task. In Section 4, we present a possible visualisation solution that
addresses these needs.
2 The Regulatory Interpretation Methodology
Understanding regulations is a complex task and legal experts face a number of
challenges in interpreting a regulatory text, including: following and fleshing out
references and citations; identifying, delimiting, and disambiguating definitions;
making sense of complex sentences; clarifying ambiguities resulting from legalese;
accounting for exceptions [2]. Our research aims to bridge the gap between the
legal expertise required to interpret the regulatory text and the modelling skills
required to build a semantic knowledge base. The goal is to foster compliance
in the financial sector by supporting corporate lawyers, risk practitioners and
compliance professionals in their role of subject matter experts in making law
more readily consumable and comprehensible by the industry.
74
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
The translation of regulatory text into machine-readable information is artic-
ulated around a methodology that defines a process for transforming a regulatory
text into a formal representation using an intermediate human-readable repre-
sentation in semi-structured English. The process (see Fig. 1) is designed as a
collaborative one, involving the legal expert as a subject matter expert (SME)
and the modeller as a semantic technology expert (STE) through multiple iter-
ations [15].
Fig. 1. The translation process outlined in the Regulatory Interpretation Methodology.
The dashed box identifies the part of the process covered by SmaRT. Currently, the
Semantic Technology Expert is needed to ensure the quality of the output model, but
will not be needed as the software is improved.
The solution allows SMEs to represent the semantics of regulatory require-
ments in a machine-readable format through a SME-friendly process. This is en-
sured through the use of SBVR (Semantic of Business Vocabularies and Business
Rules), a Object Management Group specification based on formal logics and
well known to the industry [14]. In SBVR, a requirement is rewritten in Struc-
tured English, a semi-structured controlled natural language where every term
used in the rules is sourced and specified in a terminological dictionary. SBVR is
a powerful instrument for modelling an area of business activity and for building
a business vocabulary [11], but it is not suitable – as is – for the representation of
legal rules; some SBVR components are not needed or overcomplicate the task
of rule representation (e.g. the logical formulation of a sentence, see [7]), and
some components fall short in capturing legal concepts (e.g. constitutive rules).
To overcome this, our research group at the Governance, Risk, and Com-
pliance Technology Center (GRCTC) has devised a resource called Mercury,
composed of:
– Mercury-SE, a semi-structured English based on SBVR used as an inter-
mediate language between the legal text and the machine-readable format,
and
– Mercury-ML, a persistence model in RDF format, capturing the semantics
of Mercury-SE in a machine-readable format.
75
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
Mercury represents rule statements contained in regulations and describes the
concepts used in those rules in a vocabulary. The process of translation from the
legal text to the Mercury-SE language is manual and tool-assisted. The software,
SmaRT, is specifically designed to make the translation process as intuitive as
possible, while at the same time reducing the user’s time devoted to the most
repetitive work. The reader is invited to refer to [6] for more details on SBVR,
Mercury, and the ways in which the latter enhances the former.
Mercury relies on both (a) technologies from the Semantic Web (SW) stack
at the RDF layer and (b) non-SW technologies (SBVR and the RIM). It relies on
upper SW layers, particularly OWL, for advanced classification and reasoning
on rules and vocabulary. The GRCTC is currently developing a set of ontolo-
gies called FIRO (Financial Industry Regulatory Ontology) to enable semantic
applications such as classification, querying, and reasoning, and has devised a
mapping of all SBVR elements relevant to Mercury into RDF/OWL to assist
the STE in translating Mercury rulebooks and vocabularies [3].
Because of limitation of OWL and Description Logics [5], FIRO does not
involve complete rule-based reasoning but only rule representation. The aim is
to capture relevant information on the regulatory requirements and to be able
to:
– run queries on the resulting RDF/OWL knowledge base;
– perform abstract classification and reasoning on rules and their regulated ac-
tions (e.g., detecting which rules regulate a subset of another rule’s regulated
action);
– validate data representing instances of regulated actions (events) as compli-
ant or breaching one or more rules.
In order to perform these tasks, we need the legal rules – represented in
Mercury-ML – to be complete in terms of semantics and computable. Mercury
being a semi-structured controlled natural language, there is a need for solutions
that allow SMEs to have greater control over the formal representation of their
interpretation of a legal rule without having to learn any specific formalism. We
propose to achieve this by providing a graphical solution that allows the SMEs
to visualise rules in a more schematic way. For example, Fig. 2 shows a graphical
representation of the following rule:
Rule 1. It is obligatory that a market operator that operates a trading venue
makes public credits and debts.
The graph in Fig. 2 makes explicit the information about the logical for-
mulation of the rule that is not immediately apparent in the textual form. For
example, it shows that market operator is the subject of three verb concepts:
market operator operates trading venue, market operator makes public credit, and
market operator makes public debt. It also shows which verb concepts express
the deontic condition of the rule – see the dashed box in red – distinguishing it
from the other verb concept, which expresses the rule’s applicability condition.
Finally, it shows how the former and the latter verb concepts relate to each other
– they are connected via the same subject, market operator.
76
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
Fig. 2. Example of a graphical representation of a legal rule
In the next section, we describe the tasks of the Regulatory Interpretation
Methodology in more detail to specify further our visualization needs.
3 Visualisation Needs
To create a rule from a legal document, SMEs follow the methodology defined
in the RIM. First, they identify a unit of analysis within a given legal document.
Second, they rewrite the text of the unit of analysis, fleshing out references.
Third, they identify and define the noun concepts (i.e., entities) and verb con-
cepts (i.e., actions with their participants and other attributes) and mark the
keywords (e.g., the logical operators) composing the rule. Finally, they specify
the logical formulation of the rule by linking verb concepts to each other. This
logical formulation follows specific patterns for constitutive rules [8] and more
generic ones for regulative rules [6]. Here, we focus on the third and fourth steps
and, more specifically, on the subtasks of (i) creating verb concepts within a rule
and (ii) linking verb concepts to each other to form rules.
All these steps are carried out using SmaRT, our web-based rule editing tool.
Fig. 3 shows the editor window at the first step of the methodology. The original
regulatory text is displayed in the upper box and the text rewritten by the SME
is displayed in the lower box.
3.1 Visualising Noun Concepts and their Links to Verbs
The task of creating verb concepts consists of identifying all the noun concepts
– usually domain-specific terms – and linking them to the appropriate verbs or
verb phrases using one of the roles that specify the semantic relation between a
noun concept and the action denoted by the verb, such as hasSubject, hasObject,
hasIndirectObject, and hasLocation. A verb concept is created when all the rele-
vant noun concepts are linked to the verb concept’s verb with one (and only one)
of these relations. The verb of a verb concept should be captured in its active
form and should account for any of its variant forms, e.g., its passive form.
77
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
Fig. 3. SmaRT editor view displaying the original and the rewritten text
Therefore, the first visualisation requirement to assist the SMEs in the task
of creating verb concepts is to display (i) the building blocks of a verb concept –
the verb and the noun concepts – and (ii) the links representing the roles relating
noun concepts to the verb in a verb concept.
3.2 Visualising Verb Concepts and their Links to Each Other
The second task of connecting verb concepts to each other to form the rules
brings about further requirements for useful visualisation aids. This task consists
of two subtasks:
– Identifying the logical operators (and /or ) forming a conjunction or disjunc-
tion of two or more noun concepts that play the same role with respect to
a verb concept. This results in the creation of two or more verb concepts
denoting two or more actions with their participants and other attributes
(see Fig. 4).
– Identifying noun concepts that play a role in more than one verb concept
(see Fig. 5).
Therefore, the second visualisation requirement to assist the SMEs in the
task of linking verb concepts to each other is to display these larger building
blocks and their links in a user-friendly manner that captures and gives a clear
understanding of the logical structure of a rule (see Fig. 6).
3.3 Limitations of the Current Visualisation Capabilities
To help the SMEs in these tasks, the current version of SmaRT integrates display
functions that address only part of the visualisation needs. The tool allows SMEs
to visualise the different elements of a verb concept as shown in Fig. 7. These are
displayed using color-coded tags that encapsulate the respective text spans using
78
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
Fig. 4. The graph at the top shows a logical operator (and ) connecting two noun
concepts. The original sentence is market operator makes public credits and debts. The
semantics is market operator makes public credits and same market operator makes
public debts. The graph at the bottom shows the semantics of this connection: the
logical operator is really connecting two verb concepts, each of which has a different
noun concept (credit and debt) in the role of object, and the same instance of the same
noun concept (market operator) in the role of subject.
Fig. 5. This graph shows the keyword same connecting two noun concepts each playing
a role in a different verb concept. The original sentence is market operator operating
a trading venue makes public credits. The semantics is market operator makes public
credits and same market operator operates trading venue.
distinct colors for noun concepts (in green) and verbs – verb parts of speech and
verbal phrases – (in blue).
Selecting a verb highlights the entire verb concept, that is, the verb and the
related noun concepts. This is illustrated in Fig. 8, where the verb operates in
the verb concept market operator operates trading venue is marked in blue and
the related noun concepts, market operator and trading venue, in red. However,
the current solution is limited in that the roles played by each noun concept
within a verb concept are not graphically represented in the main window. They
are specified and displayed in a separate pane (see the text box on the right-hand
side of the editor in Fig. 8).
Similarly, the current implementation does not support the visualisation of
more complex relations between verb concepts resulting from conjunctions or
79
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
Fig. 6. This graph shows the entire Rule 1 in a more verbose graph than the one
contained in Fig. 2. The graph was obtained by joining the graphs in Figs. 4 and 5,
and by distinguishing the deontic condition from the applicability condition. In turn,
the applicability condition loses the logical operator and connecting it to the deontic
conditions.
Fig. 7. Visualisation of noun concepts and verbs in SmaRT
Fig. 8. Visualisation of verb concepts in SmaRT
disjunctions of noun concepts – “make public credits AND debts”, nor of how
two or more verb concepts are linked to each other – market operator is the
subject of makes public and of operates and thus links the corresponding verb
concepts.
In sum, the visualisation needs for a seamless execution of these tasks can be
broadly categorized into two types: grouping textual spans at different levels of
granularity and linking these spans to each other in a user-friendly manner that
clarifies and makes the logical structure of a rule explicit. Ideally, the rule-editing
tool would allow the SMEs not only to visualise the rules, but also to interact
with the visual environment to build the rules. Finally, the visualisation solu-
tion should also address end-user needs by providing them with additional query
functions that would allow them to retrieve and display relevant rules for en-
80
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
hanced regulatory compliance verification. To address the current shortcomings
of the tool and improve its user-friendliness, we have explored a visualisation
solution that would meet these needs and assist the SMEs in the rule-editing
task.
4 Graphical Representation of Legal Rules
Graphs are helpful to visualise relationships. In this section, we present a method
to represent vocabularies and legal rules in property graphs and store them in
the graph database management system Neo4j1 that allows for native graph
storage and processing. The property graph contains connected entities (the
nodes) which can hold any number of attributes (key-value pairs). Nodes can be
tagged with labels representing their different roles in a domain. In addition to
contextualizing node and relationship properties, labels may also serve to attach
meta data, index, or constraint information to certain nodes.
Neo4j uses Cypher2 , a declarative, SQL-inspired language for visually de-
scribing patterns in graphs using an ascii-art syntax. Here, Cypher is used to
represent and query graph data.
4.1 Graphical Representation of Noun and Verb Concepts
Graphical Representation of Noun Concepts. Noun concepts constitute
building blocks of legal rules; they can be financial concepts. Each noun concept
includes attributes, such as label, concept type, context type, and their correspond-
ing values. They also include object properties such as hasGeneralConcept, which
indicates a subclass relationship between two noun concepts. We represent each
noun concept as a graph node, with key-value pairs specifying its attributes and
their corresponding values.
Fig. 9 shows an example of a noun concept, investment firm, with some
of its attributes and corresponding values (shown in the bottom bar), and a
relationship hasGeneralConcept between investment firm and the noun concept
company, indicating that the concept investment firm is a subclass of the concept
company.
Graphical Representation of Verb Concepts. Usually, verb concepts de-
note actions contained in rules and describe basic relationships between noun
concepts. Each verb concept includes a subject and a verb or verbal phrase called
verbSymbol. It may also include an object, and indirect object or other types of
relations such as hasLocation. We represent each verb concept as a graph node
that has edges (relationships) such as: hasSubject, hasVerbSymbol, hasObject,
and hasIndirectObject. Fig. 10 shows an example of the verb concept market
operator operates a trading venue.
1
https://neo4j.com/
2
https://neo4j.com/developer/cypher-query-language/
81
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
Fig. 9. Example of graphical representation of noun concepts
Fig. 10. Example of graphical representation of verb concepts
82
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
4.2 Graphical Representation of Rules
Legal rules are more complex than noun and verb concepts. Each rule includes
one or more applicability conditions that determine whether a given action is
relevant to a given rule or not, and one or more deontic conditions that deter-
mine whether a relevant action complies with or breaches a rule. In our current
implementation, we represent a legal rule as a graph node that is connected to
the graph nodes of applicability condition and deontic condition with the edges
hasApplicabilityCondition and hasDeonticCondition. The nodes of applicability
condition and deontic condition have edges associatedWith connecting them to
action (verb concept) nodes.
Fig. 11 shows an example of graphical representation of the rule used through-
out the paper (Rule 1). This rule has key-value pairs containing some basic infor-
mation such as the original regulatory text shown in the bottom bar. The rule1
node connects two deontic condition nodes and one applicability condition node.
Each of them is connected to a verb concept node by the edge associatedWith.
Fig. 11. Example of graphical representation of a rule
4.3 Querying Graph Data
The rules and vocabularies represented in property graphs can be queried and
retrieved by users. Queries over graph databases are often graph patterns. Here,
we use the Cypher language of the Neo4j graph database to formulate graph
patterns and pose the Cypher queries in the graph database to retrieve graph
83
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
data. Note that queries can also be visualised since they are graphs with vari-
ables. We also formulate some common queries as query templates which can
help the users who have no knowledge of Cypher to formulate their queries.
5 Conclusions
This paper presents visualisation needs and enhancements for a rule-editing tool
used by legal experts to achieve a machine-readable interpretation of legal re-
quirements with a semi-structured controlled natural language. The paper pre-
sented knowledge graphs as a way to visualize an interpreted rule and all its
relevant elements in a format that the lawyer can understand and manipulate.
This is meant to ensure that the machine-readable output of the regulation in-
terpretation process is semantically enriched as intended by the legal expert,
thus ensuring the reliability of the interpretation stored in the machine-readable
format. Next steps of the research include further investigation of graphing so-
lutions. We anticipate that this might bring us to reconsider some basic formal-
ization principles derived from SBVR, which in turn might lead us to reconsider
some modelling choices in Mercury.
References
1. EY’s 2015 global governance, risk and compliance survey: Innovat-
ing with RegTech (2015), http://www.ey.com/Publication/vwLUAssets/
EY-Innovating-with-RegTech/\$FILE/EY-Innovating-with-RegTech.pdf
2. Abi-Lahoud, E., O’Brien, L., Butler, T.: On the road to regulatory ontologies:
Interpreting regulations with SBVR. In: AI Approaches to the Complexity of Legal
Systems. Lecture Notes in Artificial Intelligence, vol. 8929, pp. 188–201. Springer
Berlin (2014)
3. Al Khalil, F., Ceci, M., Yapa, K., O’Brien, L.: SBVR to OWL 2 mapping in the
domain of legal rules. In: International Symposium on Rules and Rule Markup
Languages for the Semantic Web. pp. 258–266. Springer (2016)
4. Arner, D.W., Barberis, J., Buckley, R.P., et al.: The emergence of RegTech 2.0:
From know your customer to know your data. Journal of Financial Transformation
44, 79–86 (2016)
5. Baader, F., Calvanese, D., McGuinness, D., Nardi, D., Patel-Schneider, P.: The
description logic handbook: Theory, implementations and applications. Cambridge
U. Press, Cambridge, England (2003)
6. Ceci, M., Al Khalil, F., O’Brien, L.: Making sense of regulations with SBVR. In:
Proceedings of the RuleML 2016 Challenge, Doctoral Consortium and Industry
Track (2016)
7. Ceci, M., Al Khalil, F., O’Brien, L., Butler, T.: Requirements for an intermediate
language bridging legal text and rules. In: Workshop on ‘MIning and REasoning
with Legal texts’ (MIREL). Nice, France (2016)
8. Ceci, M., Butler, T., O’Brien, L., Al Khalil, F.: Legal patterns for different consti-
tutive rules. In: Workshop on ‘MIning and REasoning with Legal texts’ (MIREL).
pp. 1–11. Kings College, London (2017)
84
Proceedings of the 1st Workshop on Technologies for Regulatory Compliance
9. Gordon, T., Governatori, G., Rotolo, A.: Rules and norms: Requirements for rule
interchange languages in the legal domain. Rule interchange and applications pp.
282–296 (2009)
10. Governatori, G., Shek, S.: Rule based business process compliance. In: RuleML (2)
(2012)
11. van Haarst, R.: SBVR made easy: Business vocabulary and rules as a critical asset.
Conceptual Heaven, Amsterdam (2013)
12. Höfler, S., Bünzli, A.: Designing a controlled natural language for the representa-
tion of legal norms. In: Second Workshop on Controlled Natural Languages (2010)
13. Maranhao, J.S.: A logical architecture for dynamic legal interpretation. In: 16th
International Conference on Artificial Intelligence and Law (ICAIL) (2017)
14. Object Management Group (OMG): Semantics of Business Vocabulary and Rules
(SBVR). Specifications (May 2017), http://www.omg.org/spec/SBVR/1.4/
15. O’Brien, L., Abi-Lahoud, E., Lombard, J.: Using business natural language to
capture financial regulations in a collaborative ontology development process. In:
Law Via the Internet. Jersey (26-27 September 2013)
16. Siena, A., Mylopoulos, J., Perini, A., Susi, A.: From laws to requirements. In:
Requirements Engineering and Law (RELAW’08). pp. 6–10 (2008)
17. Wyner, A., Peters, W.: On rule extraction from regulations. In: JURIX. vol. 11,
pp. 113–122 (2011)
85