Explore our projects & studies
Explore our projects & studies
From Artificial Intelligence to Human-Computer Interaction and Software Architecture, our research team tackles complex problems across many domains. We seek at providing the best of modern technology for public services, health-care and industry.
Integrating 3D geospatial data
Being able to create unified views of all kinds of geospatial data (2D, 3D, and semantic data) from the BIM and CIM domains is essential for decision-making in urban development projects and in a CMMS context. Our objective is to provide users with integrated and navigable views of available representation
Not all Hallucinations are Good to Throw Away When it Comes to Legal Abstractive Summarization
The extensive use of Large Language Models (LLMs) for summarization tasks brings new challenges. One of the most important is related to the LLMs’ tendency to generate hallucinations, i.e., texts that give the impression of being fluid and natural, despite their lack of fidelity and nonsensical nature. Hallucinations can be
Extracting services from legacy software system
Let’s explore together the recent poster created by Soufyane Labsari and published about extracting services from legacy software systems. This work is done in collaboration with Inria.
Improved comment generation by LLMs
In the world of programming, creating efficient and functional software is a top priority, but it’s not just about writing lines of code. An essential part of the software development process is documentation, which includes the creation of explanatory comments that help to understand the operation and logic of the
Federated Learning, the security asset for local maintenance of your data
Predictive maintenance, coupled with the Internet of Things (IoT) and Artificial Intelligence (AI), represents a revolutionary approach to equipment maintenance. Traditionally, maintenance has been performed on a fixed schedule or in response to failures, leading to inefficiencies and downtime. Predictive maintenance aims to address these shortcomings by leveraging IoT sensors
Information extraction from Berger-Levrault books and articles
Historically, Berger-Levrault has been a publisher of legal and practical books and articles. The articles are on line and come from Légibases. Exploiting the knowledge contained in these texts is difficult. This is why it is necessary to structure the knowledge so that it can be accessed quickly. Berger-Levrault develops
A Modest first step in Test Generation
In the field of software development, code testing is a paramount task that should never be overlooked. At Berger-Levrault, we take this responsibility seriously and enforce a strict policy that includes the establishment of continuous integration (CI) and quality gates in our SonarQube server. Testing not only supports various developer
Classification of business documents to aid extraction: the use of typed and weighted lexical-semantic relations
I’ve been a member of the Berger-Levrault research team since 2020. I’m working on a CIFRE thesis on methods and models for the automated construction of multi-domain ontology databases, in collaboration with the Montpellier Laboratory of Computer Science, Robotics and Microelectronics (LIRMM). This work was presented at the PFIA (Plate-forme
Integrate Software Engineering into the everyday world
I have been a member of the Berger-Levrault research team for 6 years. And, one of our main challenges is integrating our innovation into the day-to-day world of the company. There are several ways to incorporate innovation: as an external code library, providing schema, teaching how to use new tools,
Equipment 3D visualization in a CMMS application-2nd part
Find the first part of this article by following this link Navigation in the context of a CMMS asset using geometric and semantic data Our goal is to provide the user contextual views of an asset, thus to allow him to visualize the asset at different scale or using the
