=Paper=
{{Paper
|id=Vol-1620/paper7
|storemode=property
|title=Making Sense of Regulations with SBVR
|pdfUrl=https://ceur-ws.org/Vol-1620/paper7.pdf
|volume=Vol-1620
|authors=Marcello Ceci, Firas Al Khalil, Leona O'Brien
|dblpUrl=https://dblp.org/rec/conf/ruleml/CeciKO16
}}
==Making Sense of Regulations with SBVR==
https://ceur-ws.org/Vol-1620/paper7.pdf
Making Sense of Regulations with SBVR
Marcello Ceci, Firas Al Khalil, Leona O’Brien
Governance, Risk, and Compliance Technology Center
University College Cork
13 South Mall, Cork, Ireland
{marcello.ceci,firas.alkhalil,leona.obrien}@ucc.ie
Abstract - The continuous increase in quantity and depth of regulation following
the financial crisis has left the financial industry in dire need of making its com-
pliance assessment activities more effective. The field of AI & Law provides
models that, despite being fit for the representation of semantics of requirements,
do not share the approach favoured by the industry which relies on business vo-
cabularies such as SBVR. This paper presents Mercury, a solution for represent-
ing the requirements and vocabulary contained in a regulatory text (or business
policy) in a SME-friendly way, for the purpose of determining compliance. Mer-
cury includes a structured language based on SBVR, with a rulebook, containing
the regulative and constitutive rules, and a vocabulary, containing the actions and
factors that determine a rule’s applicability and its legal effect. Mercury includes
an XML persistence model and is mapped to an OWL ontology called FIRO,
enabling semantic applications.
Keywords. AI & Law, GRC, SBVR, statutory interpretation, factors, fintech.
1 Introduction
Ensuring compliance with new regulatory requirements as well as with existing ones
continues to be a challenge of herculean proportions for the international financial in-
dustry, driven by the proliferation and complexity of the financial regulatory environ-
ment in the aftermath of the global financial crisis. The wide acceptance in the industry
that traditional Governance, Risk, and Compliance (GRC) information systems are de-
ficient is leading to a growing interest in semantic technologies. The research at the
Governance, Risk and Compliance Technology Centre (GRCTC) is a complementary
set of projects tackling the challenges for the Financial Industry that arise from multi-
layered, multi-jurisdictional and ever-changing regulation.
Understanding regulations is a complex task for both non-trained human agents and
machines. Legal experts face a number of challenges in interpreting a regulatory text,
including: following and fleshing out references and citations; identifying, delineating,
and disambiguating definitions; making sense of complex sentences; clarifying ambi-
guities resulting from legalese; accounting for exceptions (Abi-Lahoud et al. 2014a).
The research presented in this paper devises an approach to bridge the gap between the
legal expertise required to interpret the regulatory text and the modeling 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 SMEs in making law more readily consumable and comprehensible by
the industry, but differently from the Ergo platform (Grosof et al. 2015). The process
of translation is articulated around a Regulatory compliance Interpretation Methodol-
ogy (RIM) that defines a process for transforming a regulatory text into a representation
in structured English en route to enabling semantic applications. The process is envis-
aged as a collaborative one, involving the legal expert as a Subject Matter Expert (SME)
and the modeler as a Semantic Technology Expert (STE) through multiple iterations.
The solution allows the SME to represent the semantics of regulatory requirements
in a machine-readable format through a SME-friendly process. This is ensured through
the use of SBVR, a OMG specification based on formal logics and well known to the
industry. In SBVR, a requirement is re-written in Structured English, a loosely struc-
tured Controlled Natural Language where every term used in the rules is sourced and
specified in a terminological dictionary. SBVR is a powerful instrument for modeling
an area of business activity and for building a business vocabulary (van Haarst 2013, p.
14), 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), and some components are lacking.
To overcome this, GRCTC research has devised an artifact called Mercury, com-
posed of a structured English based on SBVR and persisted in an XML Schema cap-
turing rulebook and vocabulary entries. Mercury represents rule statements contained
in regulations and describes the concepts used in those rules in a terminological dic-
tionary. The most important change that Mercury brings to SBVR – and the object of
this paper – is a different way to manage the logical formulation of the SBVR rule that
overcomes the limitations of SBVR original logical formulation in representing legal
interpretation. The financial regulations to be represented for GRC purposes are often
very detailed, containing requirements rather than high-level legal principles or general
prescriptions. Therefore, for their interpretation value judgments (Bench-Capon and
Sartor 2003, Grabmair and Ashley 2011) play a minor role in comparison to the lin-
guistic element. A significant part of the relations between the regulated entities is in
fact specified in the rule itself, and the important concepts are explicitly defined in the
same regulation. SBVR, with its vocabulary and rulebook components, seems best
suited to capture this.
The current phase of the research does not involve advanced rule-based reasoning
but only rule representation. The aim is to capture relevant information on the regula-
tory requirements and to be able to:
Run queries on the resulting knowledge base;
Perform abstract classification and reasoning on rules and their regulated actions
(e.g. detecting which rules regulate a subset of another rule’s regulated action);
Validate data representing instances of regulated actions (events) as compliant or
breaching one or more rules.
Mercury exploits technologies from the Semantic Web (SW) stack at the XML layer
as well as non-SW technologies (SBVR and the RIM). It relies on upper SW layers,
particularly OWL, for advanced classification and reasoning on rules and vocabulary.
(Al Khalil et al. 2016) for an explanation of GRCTC’s mapping from SBVR to OWL.
The rest of the paper is structured as follows: Section 2 describes statutory interpre-
tation and the issues related to its representation with SBVR, Section 3 introduces Mer-
cury and its main elements, and Section 4 explains its model for representing regulative
rules. Section 5 concludes with final remarks, a proof of concept, and the further steps
of the research.
2 The Semantics of Regulatory Requirements
The present paper addresses the AI & Law subjects of statutory interpretation and
rule representation. The concept of legal interpretation, highly debated in legal philos-
ophy (Aracziewicz 2013), consists in our account in determining the extension of stat-
utory terms. We thus focus on the part of legal interpretation concerned with the con-
ceptual analysis, typical of domestic law in civil law countries.
Since its inception, the AI & Law community has devoted notable efforts in model-
ing legal rules and regulations (Sergot et al. 1986, Pashke et al. 2007), but only few of
them were aimed at devising an intermediate format for describing legal rules, the Legal
Knowledge Interchange Format (LKIF) (Boer et al. 2008) being a first systematic at-
tempt in this direction. Most of the research in the field was instead directed towards
the representation of legislative documents (the speech acts rather than the provisions
they contain) through XML languages, among which we cite CEN MetaLex (Boer et
al. 2009) and Akoma Ntoso (Vitali and Zeni 2007). The present research relies on
Akoma Ntoso to enhance the semantics of the legal source, enabling Regulatory
Change Management, temporal reasoning, and standard representation of metadata
such as jurisdiction and issuing authority (O’Brien et al. 2016).
Legal rules are mostly debated in AI & Law in relation to the notions of legal argu-
mentation (Prakken 2008) and case-based legal reasoning (see Section 3.2). The prob-
lem of statutory interpretation is relatively underrepresented in AI & Law research, with
recent exceptions from the civil law tradition (Araszkiewicz 2013). The research
showed notable results, e.g. Gordon et al. (2009) setting the requirements for the rep-
resentation of legal rules and Wyner and Peters (2011) covering the automatic extrac-
tion of rules from regulation exploiting NLP techniques. LegalRuleML has all the de-
sired features to capture legal regulation, but it does not rely on a terminological dic-
tionary like SBVR, and lacks specific focus on compliance.
2.1 Case-based Legal Reasoning
Legal reasoning can be classified in two main categories: abstract reasoning on the
relationship between rules and/or the concepts they express, and concrete reasoning on
the rules applicable to a given fact. The first type of reasoning is the Rechtsdogmatik
and is typical (but not exclusive) of civil law systems, and is also called doctrinal legal
interpretation (Wroblewski 1992). The second type of reasoning corresponds to case-
based legal reasoning and is typical (but not exclusive) of common law systems, and
is also called operative legal interpretation.
Case-based legal reasoning has made for very prolific research in AI & Law. The
original purpose, especially in the works of K. D. Ashley (1990) and his scholars
(Aleven 1997) was to support legal classes providing a way to explore concepts such
as analogy and precedent. Their research resulted in two computer programs aimed at
representing case-based argumentation in a computable way:
The first, HYPO, enables comparison between precedents by means of dimensions:
characteristics of the precedents are thus represented as points (positions) within gra-
dients which are not themselves built to favor one solution to the case, rather
strengthening or wakening the claim of each party to the dispute according to the
position in the dimension (Ashley 1990 p. 112).
The second, CATO, includes a simplified structure of dimensions where particular
points (positions) are represented as factors, unequivocally supporting one party to
the case. Factors as employed in CATO are unary, in the sense that those factors
either apply to a given case, or they do not apply (Aleven 1997).
In AI and Law, factors are seen as mere indicators that enable argumentation and
comparison without necessarily leading to the promoted judicial outcome, even in ab-
sence of reasons to the contrary (Sartor 2005). More recently, research focused on for-
mal models of legal argumentation, with analytical concepts such as dimensions and
factors being replaced by more high-level figures such as values (Bench-Capon and
Sartor 2003), argumentation schemes (Gordon and Walton 2006), and intermediate le-
gal concepts (Grabmair and Ashley 2011). The use of factors to capture statutory inter-
pretation has been already discussed (Araszkiewicz 2011, Ceci and Gangemi 2016),
and the research presented in this paper builds upon that experience.
2.2 SBVR
The Object Management Group (OMG) created the Semantics of Business Vocabu-
laries and Business Rules specification (SBVR 2013) to define business concepts and
rules using a controlled natural language, SBVR Structured English (SBVR SE). It is
meant to be used by business people to describe their business activities, hence its adop-
tion in GRCTC: it allows non-technical experts (SMEs) to define rules using a con-
trolled language (as opposed to legalese).
SBVR SE is composed of a rulebook and of a terminological dictionary (vocabu-
lary). The rulebook contains operative rules, introduced by deontic modalities (it is
obligatory that, it is permitted that, it is prohibited that), and structural rules, intro-
duced by alethic modalities (it is necessary that, it is possible that, it is impossible that).
These two categories correspond to regulative rules and constitutive rules (Searle
1969). The present paper focuses on operative rules such as the following:
It is obligatory that each market operator that operates a trading venue makes
public bid price for share.
All the terms of the SBVR rule except keywords and modality (both in bold in the
rule above) are declared in the SBVR vocabulary. The vocabulary contains entries for
noun concepts (underlined) and verb concepts. Verb concepts include one verb sym-
bol (italic) and one or more verb concept roles (underlined in the entry below) covered
by noun concepts (see Figure 1).
RULE VC (C)
VCR VCR
modality VC (B) VCR
VCR
VC (A)
VCR VCR
obligation NC VS NC VS NC VS NC
It is obligatory that each market operator that operates a trading venue makes public bid price for share.
Fig. 1. – Elements of an SBVR rule. NC = Noun Concept, VS = Verb Symbol, VCR= Verb
Concept Role, VC= Verb Concept (the letters refer to the table below and to Figure 6).
Let us consider for example the following verb concept entry in the vocabulary:
market operator operates trading venue
This verb concept includes one verb symbol, “operates”, and two noun concepts,
“market operator” and “trading venue”, as verb concept roles. Each vocabulary entry
contains a list of attributes (metadata) for semantic enrichment.
SBVR defines a means to capture the semantics expressed in a rule. Semantic for-
mulations, as described in the SBVR specification, are not representations or expres-
sions of meaning. Rather, they are structures of meaning – the logical composition of
meaning. Although adequate, the logical formulation of a sentence is not suitable to
represent the composition of a legal rule: it is too verbose and complex. A simpler
model to capture the semantics of a legal rule can be more advantageous, since it deals
with the legal nature of the rules directly, not in an abstract logical manner.
2.3 Making Sense of SBVR: Introducing Mercury
In order to design a model of legal rules for compliance, we need to define a data
format that the machine can use to perform such type of reasoning, starting from what
an SME can be expected to achieve: the SBVR-SE format of the rule. In Mercury (Fig-
ure 2), regulative rules are thus presented as SBVR sentences, with an operative mo-
dality and a net of verb concepts, connected by verb concepts roles shared among them.
The verb concepts as used in the rule to represent the regulated actions or states of
affairs, or, in other words, are the “conditions” of the rule. In the example rule the fol-
lowing verb concepts can be identified:
Verb Concept Role Verb Symbol Verb Concept Role
A market operator operates trading venue
B market operator makes public bid price
C share has bid price
Statutory Interpretation
Rulebook Vocabulary
Noun Verb
Regulative Rules Constitutive Rules
Concepts Concepts
Applicability Deontic Constitu- Constitu- Grammatical
Subject Conditions Context Factors Comple-
Conditions tive Token tive Type
ments
Fig. 2. – The elements of statutory interpretation as represented in Mercury-SE. Constitutive
rules and its elements are not covered in the present paper.
Each of these verb concepts represent abstract actions that determine relevance under
the rule. In LKIF (Boer et al. 2008), rules are seen as qualifiers, and regulated actions
or state of affairs as qualified things. Under this perspective, the core semantics of com-
pliance (the semantics of compliance and breach) can be treated as semantics of a
“qualified” entity, as regulative rules qualify actions as “compliant to” or “breaching”
the rule itself. In SBVR, a rule’s semantics is specified through its verb concepts, and
in the noun concept entries that correspond to those verb concepts’ roles. Verb concepts
thus represent the qualified (“compliant” or “breaching”) actions, and verb concept
roles are the links that express the semantics of this qualification.
The next section presents Mercury, a bridge language built on top of SBVR to pro-
vide the necessary hooks for legal reasoning. Mercury enriches the semantics of SBVR
rulebook by introducing the concept of condition, a “qualified” verb concept.
3 Mercury: A Bridge Language for Regulatory Requirements
Mercury is a bridge language for translating regulatory requirements in a machine-
readable way. It includes two components:
A structured natural language called Mercury Structured English (Mercury-SE,
based on SBVR, presented in the next section);
A persistence model in XML called Mercury Markup Language (HgML, pre-
sented in Section 4.5).
3.1 Actions, Events, and Factors
Mercury-SE is composed of a rulebook and a vocabulary (terminological diction-
ary), both similar to their SBVR counterparts. Mercury extends the terminology of
SBVR by identifying an additional layer of semantics to the vocabulary entries. Thus,
the entries that are defined in SBVR as (a) verb concepts and (b) verb concept roles
express abstract entities that are captured in Mercury under the labels of (a) action and
(b) factor (see Figure 3).
RULE A (C)
O S
modality S
A (B) O
A (A)
S O
obligation F V F F V F
V
It is obligatory that each market operator that operates a trading venue makes public bid price for share.
Fig. 3. – An SBVR rule with actions (A) and factors (F) as identified by Mercury. Gram-
matical complements are also indicated (S = Subject, O = Object).
Definition of Action: an action is an abstract category of events that is
defined arbitrarily. It is the result of the interpretation on the behaviour
required by the rule. Actions are expressed by SBVR verb concepts.
Definition of Event. an event is a concrete manifestation of an abstract
action.
Definition of Factor: a factor is a (generic or specific) entity that plays a
role in one or more actions contained in the same rule. It is a result of the
interpretation of the entities involved in the rule. Factors are expressed by
SBVR verb concept roles.
3.2 Grammatical Complements and Conditions
For reasons of simplicity, in the present paragraph we will describe a Mercury rule
stripped of its deontic modality:
market operator that operates a trading venue makes public bid price for share.
Each verb symbol (in italics) corresponds to one or more verb concepts, depending
on the noun concepts present as verb concept roles and on the keywords. Each of the
verb concepts contained in the rule represents an abstract action. The sum of the verb
concepts contained in the rule constitutes the structure diagram of that rule (Figure 4).
makes public
market operator bid price
operates trading venue Share has price
Fig. 4. – Implicit ontology in the sample rule in an SBVR structure di-
agram (van Haarst 2013, chapter 7). Boxes represent noun concepts;
arrows represent verb symbols.
The reader will notice that some verb concept roles are present in more than one
verb concept. In Mercury, we say that some factors are present in more than one ac-
tion. These factors could independently identify different instances of the same cate-
gory (i.e. two different market operators or two different bid prices) or instead they
could identify the same instance (i.e. the same market operator must be the subject of
action A and B, the same bid price must be the object of actions B and C). In the latter
case, for an action or event to be classified under the more general event the same
instance must appear in all factors. E. g. for a market operator (or a category of market
operators) to be relevant to the statement above, it is necessary that he operates a trad-
ing venue and also that he makes public a bid price for a share. Keywords such as
same as and that determine the identity of factors among different actions in a rule.
With SBVR, the logical formulation of the sentence is too verbose and complex.
Being unable to extract the logical formulation, however, means being unable to de-
termine the relevance of events or actions to rule statements. To overcome this limi-
tation, Mercury implements its own solution of expressing the logical formulation. It
introduces grammatical complements, an attribute of verb concept entries used to de-
scribe the grammatical role that verb concept roles play in the sentence.
Definition of grammatical complement: a grammatical complement is
an attribute of a factor expressing the grammatical role played by it in the
verb concept. The grammatical complements in Mercury are: subject, ob-
ject, indirect object, location, time, comparison, value, and mode.
With Mercury, every factor is specified under the perspective of the grammatical
complement that it covers for that verb concept. So, for example:
subject verb object
A market operator operates trading venue
B market operator makes public bid price
C share has bid price
Figure 5 shows how these complements enrich the logical formulation. Please note
that, despite the example being very simple (all actions having the same comple-
ments), verb concepts can vary: they can have only one factor (the subject) or more
than two, and logical connectors such as and/or can duplicate them.
Mercury distinguishes between verb concepts as they appear in the vocabulary and
as they appear in the rulebook: in the first case they are called Actions, while in the
latter they are called conditions. Conditions can be seen as “qualified” actions, where
one or more factors of the action correspond to factor(s) in other action(s). Keywords
such as that or same are indicators that a factor is involved in more than one action.
Subject makes public Object
market operator bid price
Subject Object
Object
operates trading venue Share has price
Subject
Fig. 5. – Implicit ontology in the sample rule in Mercury formulation.
Definition of Condition: a condition is an action used in a rule. A condi-
tion shares the same properties of its general action and may restrict fac-
tors by specifying:
1. its scope or value, or
2. The role it plays in another condition (grammatical complement).
The following Section describes how Mercury uses actions, factors and conditions
to enrich the semantics of regulations.
4 Representing Requirements in Mercury
4.1 Anatomy of a Regulative Norm
According to Biagioli (2009) regulations can be seen as a set of provisions (seman-
tics) carried by speech acts (structure). Performing the legal interpretation of a regula-
tion means in our account to describe those provisions.
From a formal logics perspective, a regulative norm can be represented with the fol-
lowing formula (Kelsen 1991, Sartor 2005) (please note that in formal logics we use
the operator “Forb”, for “forbidden”, instead of “prohibited”):
A (A1, A2, ..., An) → [Obl;Forb;Perm]B
The first element, “A”, is called applicability condition (Gordon et al. 2009). The
second element, “[Obl;Forb;Perm]B”, is often called legal effect, but for the purposes of the
present research it is called deontic condition. In our model, this element shares the
same structure as the applicability condition, with the addition of a deontic modality.
Definition of Applicability Condition. It is a condition that determines if
a given event is relevant to a given rule, or not.
Definition of Deontic Condition. It is a condition that determines if a
relevant event complies/breaches a rule.
4.2 Reasoning on Compliance and Breach
In a Mercury rule, abstract compliance is represented through the verb concepts con-
tained in the rule. As explained in Section 3.1, SBVR’s verb concepts constitute the
actions of Mercury, central to the present approach. Its abstract characteristics are de-
scribed in the attributes of the verb concept in the Mercury vocabulary: an action is thus
composed of a verb symbol and one or more grammatical complements. The action
becomes a condition when it is used (as a “deontically qualified action”) in a Mercury
rule sentence. A rule sentence includes zero or more applicability conditions and one
deontic condition. In this way, the abstract compliance to a rule can be described as a
sum of conditions, and the way the complements of these conditions intertwine pro-
vides fundamental information that unlocks powerful reasoning on compliance, just
like CATO’s factors (see Section 2.1) enable reasoning on case law
Concrete events (instances of actions) can be classified under the abstract conditions
of the Mercury rule using factors. An event is relevant for the rule (i.e. the rule applies
to the event) if the factors of the event can be classified as factors of the applicability
conditions of the rule. In addition, if the factors of the event can be also classified as
factors of the deontic condition of the rule, the event is classified depending on the
rule’s deontic modality: if the rule is an obligation, the event complies with it; if the
rule is a prohibition, the event breaches it. If, instead, the factors of the event do not
match all applicability conditions, the event is classified as “not relevant” to that rule
(see Figure 6). Concrete compliance to rule is thus similar to matching a new case (the
event) to the factors of a precedent (the sum of conditions of the rule).
Because this solution attributes explicit semantics (labels such as breach, compliant,
relevant) to the actions, the concept of factor is preferable over dimension: factors
(Aleven 1997) are unary concepts, susceptible of attribution of Boolean values, and
thus ideal to represent such semantics. In Mercury, factors are represented by the ele-
ments of the structured language, i.e. verb concept roles. The semantic value added to
them is given not only by their actual value, or by the vocabulary entry of that term, or
of the verb concept that contains it, but mostly by the role they play in other verb con-
cepts of the same rule (see next Section).
Compliance complies Event 1
with α x(A), y(B), z(C)
Actions: A, B, C
Rule α relevant Event 2
Deontic
Obligation l(B), m(C)
Condition: A
Applicability not relevant
Conditions: B, C
Event 3
i(A), j(B)
Fig. 6. – Relationship between rules and regulated events. Letters in italics represent events
as instances of actions (A, B, C). Those events compose the complex events: 1, 2, 3. Event
1 complies with rule α because it matches all applicability conditions (B and C) and the
deontic condition (A); event 2 is relevant but we have no information on compliance because
it does not match deontic condition A (on detecting deontic opposites see Section 4.4); event
3 is not relevant (rule α is not applicable) because it does not match action C.
4.3 Representing a Mercury Rule
This section describes the approach for representing operative rules in Mercury. The
approach relies on a list of rules and a terminological dictionary to explain the terms
used in them. The dictionary is particularly helpful in managing the open-textured char-
acter of statutory concepts. For more on this topic see Hart (1961).
The rule is first identified in the source, and re-written in plain English, fleshing out
all references, using a limited set of keywords to express logical elements (e.g. each,
and, that), resolving syntactic ambiguities by referring every term in the rule to a verb
or noun concept in the vocabulary, and indicating, explicitly and at the beginning of the
rule, its deontic modality (Abi-Lahoud et al. 2014b). Despite any future implementation
of a contrario reasoning (see Section 4.4), the modality chosen by the SME will con-
stitute the “main” modality, upon which more straightforward reasoning is possible.
Following is an example of a Mercury rule, with the deontic modality in bold:
It is obligatory that each market operator that operates a trading venue makes
public bid price for share.
Representing the conditions of the rule.
As explained in Section 3, action designates the vocabulary entry of the verb con-
cept, while condition designates the verb concept as it appears in the rule. A condition
specifies an action either by (a)specifying the value of some of its factors (verb concept
roles), or (b) specifying the role, in terms of grammatical complement, that they must
cover in other conditions.
The Deontic condition is a particular kind of condition: it describes the action that
determines the compliance to the rule. The deontically relevant part of such condition
resides in one (or more) of its factors. Such deontically relevant parts must be high-
lighted by the SME in the rule representation to allow the reasoner to distinguish be-
tween applicability conditions and deontic conditions. The part underlined in the rule
above (market operator makes public bid price) identifies the deontic condition. In or-
der for an event to be classified as compliant to this rule, its factors must correspond to
the factors in the other conditions of the rule.
4.4 Deontic Opposites
Reasoning on the direct legal effect of a deontic statement means to detect the events
that are compliant to an obligation, or that breach a prohibition, or that are allowed by
a permission. In order to enable reasoning on the main deontic modality, it is not nec-
essary to distinguish between deontic and applicability conditions. In this limited sce-
nario, such distinction is only useful to reason about legal relevance of a rule even when
the information on the deontic modality is missing (that is, we do not know if the event
breaches or complies with the rule because we have no information on the deontic con-
dition, but we know that the event is relevant for the rule because it matches all its
applicability conditions). The distinction between applicability and deontic condition
is instead important to enable reasoning on the deontic opposite of the rule.
We define a deontic opposite as the obligation implied by a prohibition, or a prohi-
bition implied by an obligation or permission. In legal theory, the deontic opposites are
known since Hohfeld’s definition of the deontic qualifications obligatory and prohib-
ited as complete, in the sense that they determine the deontic status of both (a) the action
or state of affairs they are concerned with and (b) the complement of such action or
state of affairs. Hence, to say that the action or state of affairs A is obligatory is equiv-
alent to saying that ¬A is prohibited, and to say that A is prohibited is equivalent to say
that ¬A is obligatory (Cook 1918). To reason on a deontic opposite thus means to detect
breach of an obligation or permission and compliance to a prohibition. In order to clas-
sify such events, the reasoner needs to match them to the “opposite” of the direct deon-
tic condition, for example:
It is prohibited that each market operator that operates a trading venue does not
make public bid price for share.
If an event matches such deontic condition, it is classified as a breach.
In the literature concerning the interpretation of statutory text using negation as fail-
ure (Sergot et al. 1986) and the a contrario argument (Peczenik 2008), legal theory
defines the determination of those “deontic opposites” as far from automatic (Araszkie-
wicz 2011). The process of deriving deontic opposites must thus be a semi-automated
process led by the SME. It is one of the intended future developments of the research
and not covered further in the present paper.
4.5 Mercury-ML
Mercury-ML is the persistent XML model for Mercury, representing the vocabulary
and the rulebook. The following XML covers a short version of our example rule:
...
Market Operator
...
Bid Price
...
Share
...
makes public
...
has
...
It is obligatory that market operator makes
public bid price for share.
...
In this example, we show the markup used to model a rule in Mercury-ML. In the
vocabulary section, we declare (through the 'id' attribute) three distinct noun concepts
and two verb concepts. The verb concepts define exactly one verb symbol and multiple
distinct (through the 'id' attribute) verb roles each of which referencing (through the 'ref'
attribute) a previously declared noun concept. The deontic condition is identified with
the attribute “deontic” attached to the verb symbol. In the rulebook section, we define
a legal rule (an obligation). The rule is written in Mercury-SE (in the expression tag).
A rule also has a 'placeholderList' that binds elements of the 'expression' to components
of verb concepts, i.e. 'placeholderList' has a list of placeholders, each of which binds
(through the 'signifier' attribute) to a verb concept role or a verb symbol.
In our example, the placeholders of rule ID12 bind 'Market Operator', 'makes public',
and 'Bid Price' to the subject, verb symbol, and object (ID5, ID7, and ID6 respectively)
of the verb concept 'Market Operator makes public Bid Price' (ID4). We also have sim-
ilar bindings for 'Share has Bid Price' (ID8). Notice that Bid Price has two bindings:
one as the object of ID4, and as the object of ID8. This example shows that we can
execute, in a straightforward fashion, some complex queries: we can retrieve the rules
that include certain actions, specifying how these actions must be concatenated. For
example, we can ask for "all rules that have a Bid Price that is the object of [a verb
concept] AND the object of [another verb concept]".
5 Conclusions
The present paper describes the legal framework behind the applied research per-
formed by the GRC Technology Centre. The solution devised by the research is Mer-
cury, enabling machine-readable representation of regulatory requirements in a SME-
friendly way. Mercury is an extension of a subset of SBVR that allows the SME to
maintain the precision of legal knowledge, its specific semantics, and the importance
of the legal source when transforming the regulatory text in a format that (a) allows
specification of the model of business activity and of the business vocabulary in com-
pliance to SBVR, and (b) unlocks the potential of semantic web technologies.
On the latter, the GRCTC is currently developing a set of OWL ontologies called
FIRO (Financial Industry Regulatory Ontology) to enable semantic applications such
as classification, querying and reasoning. The research has also devised a mapping of
all SBVR elements relevant to Mercury into OWL, to facilitate the STE in translating
Mercury rulebooks and vocabularies. This mapping differs significantly from the liter-
ature and results in a different SBVR structure diagram than the one suggested in Figure
4 (van Haarst 2013, chapter 7). The reader is invited to refer to Al Khalil et al. (2016)
for further details on FIRO and the mapping. More research efforts are being directed
towards Natural Language Processing techniques for automatic extraction of require-
ments from legal texts (Asooja et al. 2015).
The solutions presented in the present paper could be applied beyond the limit of
description logics and OWL. The current phase of the research, however, excludes rule-
based reasoning capabilities, limiting itself to rule representation: as noted previously,
the principal goal of the research is to exploit the expressive power of the SBVR vo-
cabulary to enhance the semantics of concepts such as requirement, compliance, breach,
source, legal definition, and context. Mapping of such semantics from Mercury to Le-
galRuleML is only partially possible because of Mercury’s bipartite structure (rulebook
+ vocabulary) following SBVR. Mapping is quite straightforward for conditions, less
so for factors and the links they establish across conditions, because LegalRuleML
lacks a vocabulary.
One may argue that a mapping from the logical formulation, as defined by SBVR,
to the Mercury model can be achieved: a correct, yet unpractical observation. The ex-
traction of the legal formulation of a sentence is not evident, and the lack of tooling
discouraged us from taking this route. Bypassing the logical formulation proved to be
advantageous for both 1) understanding the rule by the SME and the STE due to its
simplicity, and 2) mapping legal rules to FIRO (Al Khalil et al. 2016).
The Ergo platform (Grosof et. al. 2015) shares the goal of GRCTC research and has
a similar approach, the main differences consisting in the use of a bridge language
(Mercury, based on SBVR) and in the creation of a Regulatory Interpretation Method-
ology, that focuses the attention on the technique of translation as well as on the tech-
nologies, thus enabling the semi-automatic and collaborative translation process.
From a legal theory point of view, the research faces the issue of representing statu-
tory interpretation by adopting a solution coming from another area of AI & Law,
namely from the concept of factors as used in computational models for lecturing on
case-based reasoning. This research therefore treats the computer as a (not particularly
brilliant) legal student, which does not grasp the notions of pure legal theory
(Rechtsdogmatik) but rather reasons in terms of classifying actions and things under
abstract legal categories.
A Proof of Concept of the RIM has been conducted on MiFIR (Regulation No.
600/2014 of the European Union), as two SMEs used the protocol to transform articles
3 and 14 into Mercury. The purpose of the proof of concept was to measure the time it
takes and the size of the resulting knowledge base, rather than to measure the capabili-
ties of the resulting knowledge base. The two outputs for Article 3 were a document of
12 pages containing 13 rules and 37 vocabulary entries, and a document of 25 pages
with 5 rules and 63 vocabulary entries. This difference is caused by the fact that the two
SMEs used different structures to represent some complex concepts and articulated re-
quirements. This variation in the output shows the degree of freedom that Mercury al-
lows in the representation of legal concepts, which is clearly desirable, as the opposite
would instead increase the risk of inaccurate representation of legal concepts and of
loss of details, which in turn leads to (potentially costly) mistakes in the application of
the law.
The next steps for the research will involve extensive testing of Mercury from the
point of view of its suitability to represent any kind of regulatory statement. The testing
will also involve the user experience of the supporting tool (called Ganesha, currently
under development) that will accompany the SME during the process of transformation
of legal requirements from regulatory text to Mercury. In the future, the application of
the legal knowledge base built with Mercury will be extended further up the semantic
web stack of technologies, past ontologies into defeasible rule-based reasoning such as
LegalRuleML (Palmirani et al. 2011), agent-based reasoning (Boella et al. 2013), and
legal argumentation relying e.g. on the Carneades engine (Gordon and Walton 2006).
6 Acknowledgements
This work is financed and supported by Enterprise Ireland (EI) and the Irish Devel-
opment Authority (IDA) under the Government of Ireland Technology Centre Pro-
gramme.
7 References
1. 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 (Vol.8929),
Lecture Notes in Artificial Intelligence, Springer Berlin, pp. 188-201 (2014)
2. Abi-Lahoud, E., Butler, T., O’Brien, L.: A Hermeneutic Approach to Solving the Translation
Problem in Designing Ontologies. In: 22nd European Conference on Information Systems
(ECIS) (2014)
3. Aleven, V.: Teaching Case-Based Argumentation Through a Model and Examples. PhD
Dissertation, University of Pittsburgh (1997)
4. Al Khalil, F., Ceci, M., Yapa, K., O’Brien, L.: SBVR to OWL 2 Mapping in the Domain of
Legal Rules. In: RuleML 2016 (accepted) (2016)
5. Araszkiewicz, M.: Analogy, Similarity and Factors. In: Ashley, K. D., Van Engers, T. (eds.):
ICAIL 2011: Proceedings of the Thirteenth International Conference on Artificial Intelli-
gence and Law, ACM, New York, pp. 101-105 (2011)
6. Araszkiewicz, M.: Towards Systematic Research on Statutory Interpretation in AI and Law.
In: Ashley, K. (ed.): JURIX 2013: The Twenty-Sixth Annual Conference, IOS Press, Am-
sterdam, pp. 15-24 (2013)
7. Ashley, K. D.: Modeling Legal Argument: Reasoning with Cases and Hypotheticals. MIT
Press, Cambridge, MA (1990)
8. Asooja, K., Bordea, G., Vulcu, G., O’Brien, L., Espinoza, A., Abi-Lahoud, E., Buitelaar, P.,
Butler, T.: Semantic Annotation of Finance Regulatory Text using Multilabel Classification.
In: LeDASWAn workshop 2015, co-located with ESWC 2015, Portorož, Slovenia (2015)
9. Bench-Capon, T., Sartor, G.: A Model of Legal Reasoning with Cases Incorporating Theo-
ries and Values. In: Artificial Intelligence 150, pp. 97-142 (2003)
10. Biagioli, C.: Modelli Funzionali delle Leggi: Verso Testi Legislativi Autoesplicativi. Euro-
pean Press Academic Publishing (2009)
11. Boella, G., Janssen, M., Hulstijn, J., Humphreys, L., van der Torre, L.: Managing Legal
Interpretation in Regulatory Compliance. In: Proceedings of the Fourteenth International
Conference on Artificial Intelligence and Law, ACM, pp. 23-32 (2013)
12. Boer, A., Hoekstra, R., de Maat, E., Hupkes, E., Vitali, F., Palmirani, M., and Rátai, B.:
CEN Metalex Workshop Agreement. http://www.metalex.eu/WA/proposal (2009)
13. Boer, A., Winkels, R., Vitali, F.: MetaLex XML and the Legal Knowledge Interchange For-
mat. In: Computable Models of the Law. Lecture Notes in Artificial Intelligence 4884,
Springer Verlag, Berlin, pp. 21-41 (2008)
14. Ceci, M., Gangemi, A.: An OWL Ontology Library Representing Judicial Interpretations.
In: Semantic Web, IOS Press, vol. 7, no. 3, pp. 229-253 (2016)
15. Cook, W. W.: Hohfeld's Contribution to the Science of Law. In Yale Law Journal 721 (1918)
16. Gordon, T. F., and Walton, D.: The Carneades argumentation framework: Using presump-
tions and exceptions to model critical questions. In: 6th computational models of natural
argument workshop (CMNA), ECAI, Italy, pp. 5-13 (2006)
17. Gordon, T. F., Governatori, G., Rotolo, A.: Rules and Norms: Requirements for Rule Inter-
change Languages in the Legal Domain. In: Governatori, G., Hall, J., Paschke, A. (eds.):
RuleML 2009, LNCS, vol. 5858, Springer, Heidelberg, pp. 282-296 (2009)
18. Grabmair, M., Ashley, K.: Facilitating Case Comparison Using Value Judgments and Inter-
mediate Legal Concepts. In: Ashley, K. D., Van Engers, T. (eds.): ICAIL 20111: proceed-
ings of the 13th Int. Conference on A. I. and Law, ACM, New York, pp. 161-170 (2011)
19. Hart, H. L. A.: The Concept of Law. Clarendon Law Series, Oxford (1961)
20. Kelsen, H.: General Theory of Norms. Clarendon, Oxford (1991)
21. O’Brien, L., Ceci, M., and Al-Khalil, F.: An Akoma Ntoso Compliant System for Capturing
Regulatory Requirements. In: Proceedings of the 1st International Akoma Ntoso Conference
(IANC 2015), George Mason Univ., Arlington, VA (pending publication) (2016)
22. Palmirani, M., Governatori, G., Rotolo, A., Tabet, S., Boley H., Paschke, A.: LegalRuleML:
XML-Based Rules and Norms. In: RuleML 2011, pp. 298-312 (2011)
23. Paschke, A., Kozlenkov, A., Boley, H.: A Homogeneous Reaction Rule Language for Com-
plex Event Processing. In: Proceedings of the 2nd International Workshop on Event Drive
Architecture and Event Processing Systems (2007)
24. Peczenik, A.: On Law and Reason. 2nd ed., Springer, Berlin (2007)
25. Prakken, H.: Combining Modes of Reasoning: An Application of Abstract Argumentation.
In: Proceedings of the 11th European conference on Logics in Artificial Intelligence (vol.
5293), LNAI, Springer, Berlin, pp. 349-361 (2008)
26. Sartor, G.: Legal Reasoning: A Cognitive Approach to the Law. In: Pattaro, E., Rottleuthner,
H., Shiner, R., Peczenik, A., Sartor, G. (eds.): A Treatise of Legal Philosophy and General
Jurisprudence, volume 5, Springer (2005)
27. Searle, J. R.: Speech Acts: An Essay in the Philosophy of Language. Cambridge U. P. (1969)
28. Semantics of Business Vocabulary and Business Rules (SBVR) Version 1.2 (Apr 2013),
http://www.omg.org/spec/SBVR/1.2/PDF
29. Sergot, M., Sadri, F.,Kowalski, R., Kriwaczek, F., Hammond, P., Cory, H. T.: The British
Nationality Act as a Logic Program. In: Communications ACM 29, pp. 370-386 (1986)
30. van Haarst, R.: SBVR Made Easy – Business Vocabulary and Rules as a Critical Asset.
Conceptual Heaven, Amsterdam (2013)
31. Vitali, F. and Zeni, F.: Towards a country-independent data format: The Akoma Ntoso ex-
perience. In Proceedings of the V legislative XML workshop. Florence, Italy: European
Press Academic Publishing, pp. 67-86 (2007)
32. Wroblewski, J.: The Judicial Application of Law, Springer (1992)
33. Wyner A., Peters W.: On Rule Extraction from Regulations. In: Atkinson, K. (ed.): Legal
Knowledge and Information Systems - JURIX 2011: The Twenty-Fourth Annual Confer-
ence, University of Vienna, Austria, 14th-16th December 2011. Frontiers in Artificial Intel-
ligence and Applications 235, IOS Press (2011)