CoopIS-DT 2024 Abstracts

Area 1 - Process Analytics and Technology

Short Papers

Paper Nr:	6
Title:	Nala2BPMN: Automating BPMN Model Generation with Large Language Models
Authors:	Ali Nour Eldin, Nour Assy, Olan Anesini, Benjamin Dalmas and Walid Gaaloul
Abstract:	Nala2BPMN is a web-based tool that automates the generation of business process models from textual descriptions using large language models (LLMs). It employs a hybrid approach, breaking down tasks into steps to improve accuracy and reduce errors. The tool efficiently handles both simple and complex descriptions, as well as incomplete inputs. A qualitative evaluation by experts found Nala2BPMN to produce accurate and understandable models, highlighting its effectiveness in dealing with diverse process description complexities.

Paper Nr:	7
Title:	TeaPie: A Tool for Efficient Annotation of Process Information Extraction Data
Authors:	Julian Neuberger, Jannic Herrmann, Martin Käppel, Han van der Aa and Stefan Jablonski
Abstract:	Machine-learning based generation of process models from natural language text process descriptions is severely restrained by a lack of datasets. This lack of data can be attributed to, among other things, an absence of proper tool assistance for dataset creation, resulting in high workloads and inferior data quality. We address these shortcomings with a tool for annotating textual process descriptions. Compared to other, existing data annotation tools, ours implements a multi-step workflow specifically designed for extracting process information, including supporting features that have been shown to reduce workloads and improve data quality.

Area 2 - Services and Cloud in Information Systems

Short Papers

Paper Nr:	5
Title:	LabelIT: A Multi-Cloud Resource Label Unification Tool
Authors:	Jeremy Mechouche, Marwa Mokni and Yann Ramusat
Abstract:	In cloud environments, labels are often defined by cloud architects to categorise and describe their resources, such as virtual machines, storage and network components. These labels play a crucial role in organising, managing and tracking resources, making it easier to identify and analyse them. However, these labels are often inconsistent, abbreviated, or misspelled, leading to potential mismanagement of cloud resources. In this demonstration, we present LABELIT Kubernetes-based tool designed to standardize resource labels for improved cloud resource management. The label unification tool system is built using NLP (Natural Language Processing) based analysis methods that combine syntactic and semantic similarity processing for accurate unification.