Academic Software Tool

Are you working on the intersection of Machine Learning and Model Driven Engineering? We have three domain-independent encodings that can help you to achieve better results: The Source Encoding: this encoding is based on the main concepts and relations of a domain...

Latent Dirichlet Allocation (LDA) is one of the most popular topic modeling methods. Topic modeling is a popular and promising information retrieval technique that represents topics by word probabilities. Here you cand find our open-source implementation of the LDA...

The search space can be huge when searching in model artifacts (magnitudes of around 10150 for models of 500 elements). By handling the nonconforming individuals, the search space can be drastically reduced. We present a set of nine generic strategies for...

In the combination of Model-Driven Engineering (MDE) and Search-Based Software Engineering (SBSE), genetic operations are one of the key ingredients. Our work proposes a novel adaptation of automatic query reformulations as genetic operations that leverage...

EMoGen generates software models that are comparable in quality to the models created by human developers. Automatically generating human-competitive software models is a challenging task. Fully achieving it spans the creation of model elements, the...

TLR-ELtoR recovers traceability links between a requirement and a model through the combination of evolutionary computation and machine learning techniques, generating as a result a ranking of model fragments that can realize the requirement. Our public online...

Current traceability approaches evaluate methods in the source code of a software product as atomic units. CODFREL (Code Fragment-based Requirement Location) is our approach to fine-grained requirement traceability, which lies in an evolutionary algorithm and includes...

Often, when requirements are written, parts of the domain knowledge are assumed by the domain experts and not formalized in writing, but nevertheless used to build software artifacts. This issue, known as tacit knowledge, affects the performance of Traceability Links...

Feature location is one of the most important and common activities performed by developers during software maintenance and evolution. Features must be located across families of products and the software artifacts that realize each feature must be identified....

Latent Semantic Indexing is a powerful machinery to calculate similitude among texts. Our implementation is complaint with the theoretical results of the “Gold Tucks” example.  

Our encoding and genetic operations enable the production of crossed and mutated model fragments. The resulting model fragments are still part of an original product model, and therefore, they keep the conformance to the metamodel