Marianne Huchard

Metamodel Matching for Automatic Model Transformation Generation

Applying Model-Driven Engineering (MDE) leads to the creation of a large number of metamodels, since MDE recommends an intensive use of models defined by metamodels. Metamodels with similar objectives are then inescapably created. A recurrent issue is thus to turn compatible models conforming to similar metamodels, for example to use them in the same tool. The issue is classically solved developing ad hoc model transformations. In this paper, we propose an approach that automatically detects mappings between two metamodels and uses them to generate an alignment between those metamodels. This alignment needs to be manually checked and can then be used to generate a model transformation. Our approach is built on the Similarity Flooding algorithm used in the fields of schema matching and ontology alignment. Experimental results comparing the effectiveness of the application of various implementations of this approach on real-world metamodels are given.

Relational concept discovery in structured datasets

Relational datasets, i.e., datasets in which individuals are described both by their own features and by their relations to other individuals, arise from various sources such as databases, both relational and object-oriented, knowledge bases, or software models, e.g., UML class diagrams. When processing such complex datasets, it is of prime importance for an analysis tool to hold as much as possible to the initial format so that the semantics is preserved and the interpretation of the final results eased. Therefore, several attempts have been made to introduce relations into the formal concept analysis field which otherwise generated a large number of knowledge discovery methods and tools. However, the proposed approaches invariably look at relations as an intra-concept construct, typically relating two parts of the concept description, and therefore can only lead to the discovery of coarse-grained patterns. As an approach towards the discovery of finer-grain relational concepts, we propose to enhance the classical (object × attribute) data representations with a new dimension that is made out of inter-object links (e.g., spouse, friend, manager-of, etc.). Consequently, the discovered concepts are linked by relations which, like associations in conceptual data models such as the entity-relation diagrams, abstract from existing links between concept instances. The borders for the application of the relational mining task are provided by what we call a relational context family, a set of binary data tables representing individuals of various sorts (e.g., human beings, companies, vehicles, etc.) related by additional binary relations. As we impose no restrictions on the relations in the dataset, a major challenge is the processing of relational loops among data items. We present a method for constructing concepts on top of circular descriptions which is based on an iterative approximation of the final solution. The underlying construction methods are illustrated through their application to the restructuring of class hierarchies in object-oriented software engineering, which are described in UML.

On automatic class insertion with overloading

Several algorithms [Cas92, MS89, Run92, DDHL94a, DDHL95, GMM95] have been proposed to automatically insert a class into an inheritance hierarchy. But actual hierarchies all include overriden and overloaded properties that these algorithms handle either very partially or not at all. Partially handled means handled provided there is a separate given function f able to compare overloaded properties [DDHL95, GMM95].In this paper, we describe a new version of our algorithm (named Ares) which handles automatic class insertion more efficiently using such a function f. Although impossible to fully define, this function can be computed for a number of well defined cases of overloading and overriding. We give a classification of such cases and describe the computation process for a well-defined set of nontrivial cases.The algorithm preserves these important properties:- preservation of the maximal factorization of properties- preservation of the underlying structure (Galois lattice) of the input hierarchy- conservation of relevant classes of the input hierarchy with their properties.

A proposal for combining formal concept analysis and description logics for mining relational data

Recent advances in data and knowledge engineering have emphasized the need for formal concept analysis (FCA) tools taking into account structured data. There are a few adaptations of the classical FCA methodology for handling contexts holding on complex data formats, e.g. graph-based or relational data. In this paper, relational concept analysis (RCA) is proposed, as an adaptation of FCA for analyzing objects described both by binary and relational attributes. The RCA process takes as input a collection of contexts and of inter-context relations, and yields a set of lattices, one per context, whose concepts are linked by relations. Moreover, a way of representing the concepts and relations extracted with RCA is proposed in the framework of a description logic. The RCA process has been implemented within the Galicia platform, offering new and efficient tools for knowledge and software engineering.

Automatic Extraction of a WordNet-Like Identifier Network from Software

A large part of the time allocated to software maintenance is dedicated to the program comprehension. Many approaches that uses the program structure or the external documentation have been created to assist program comprehension. However, the identifiers of the program are an important source of information that is still not widely used for this purpose. In this article, we propose an approach, based upon Natural Language Processing techniques, that automatically extracts and organizes concepts from software identifiers in a WordNet-like structure that we call \textit{lexical views}. These lexical views give useful insight on an overall software architecture and can be used to improve results of many software engineering tasks. The proposal is evaluated against a corpus of 24 open source programs.

Monotonic conflict resolution mechanisms for inheritance

The main topic of this paper is multiple inheritance and conflict resolution methods in Object Oriented Programming. Our aim is to develop sound mechanisms easily understandable to any user. For this purpose, coherent behaviors of conflict resolution methods for multiple inheritance (such as supporting incrementality-monotonicity and stability under link subdivision) are introduced. We present interesting examples in which multiple inheritance known linearization algorithms (such as in CLOS [2] and LOOPS [19]) behave badly. Then we carefully study the conditions (on the inheritance graph) which assure good linearizations. We end with some suggestions for an incremental inheritance algorithm.

Improving Generalization Level in UML Models Iterative Cross Generalization in Practice

FCA has been successfully applied to software engineering tasks such as source code analysis and class hierarchy re-organization. Most notably, FCA puts mathematics behind the mechanism of abstracting from a set of concrete software artifacts. A key limitation of current FCA-based methods is the lack of support for relational information (e.g., associations between classes of a hierarchy): the focus is exclusively on artifact properties whereas inter-artifact relationships may encode crucial information. Consequently, feeding-in relations into the abstraction process may substantially improve its precision and thus open the access to qualitatively new generalizations. In this paper, we elaborate on ICG, an FCA-based methodology for extracting generic parts out of software models that are described as UML class diagrams. The components of ICG are located within the wider map of an FCA framework for relational data. A few experimental results drawn from an industrial project are also reflected on.

Selection of Composable Web Services Driven by User Requirements

Building a composite application based on Web services has become a real challenge regarding the large and diverse service space nowadays. Especially when considering the various functional and non-functional capabilities that Web services may afford and users may require. In this paper, we propose an approach for facilitating Web service selection according to user requirements. These requirements specify the needed functionality and expected QoS, as well as the composability between each pair of services. The originality of our approach is embodied in the use of Relational Concept Analysis (RCA), an extension of Formal Concept Analysis (FCA). Using RCA, we classify services by their calculated QoS levels and composability modes. We use a real case study of 901 services to show how to accomplish an efficient selection of services satisfying a specified set of functional and non-functional requirements.

Proposal for a monotonic multiple inheritance linearization

Previous studies concerning multiple inheritance convinced us that a better analysis of conflict resolution mechanisms was necessary. In [DHHM92], we stated properties that a sound mechanism has to respect. Among them, a monotonicity principle plays a critical role, ensuring that the inheritance mechanism behaves “naturally” relative to the incremental design of the inheritance hierarchy. We focus here on linearizations and present an intrinsically monotonic linearization, whereas currently used linearizations are not. This paper describes the algorithm in detail, explains the design choices, and compares it to other linearizations, with LOOPS and CLOS taken as references. In particular, this new linearization extends CLOS and LOOPS linearizations, producing the same results when these linearizations are sound.

Generation of operational transformation rules from examples of model transformations

Model transformation by example (MTBE) aims at defining a model transformation according to a set of examples of this transformation. Examples are given in the form of pairs, each having an input model and its corresponding output transformed model, with the transformation traces. The transformation rules are then automatically extracted from the examples. In this paper, we propose a two-step approach to generate the transformation rules. In a first step, transformation patterns are learned from the examples through a classification of the model elements of the examples, and a classification of the transformation links using Formal Concept Analysis. In a second step, those transformation patterns are analyzed in order to select the more pertinent ones and to transform them into operational transformation rules written for the Jess rule engine. The generated rules are then executed on examples to evaluate their relevance through classical precision/recall measures.