A Qualitative Analysis of the State of the Art in Process Extraction from Text

Oct 24, 2026

Process models in Business Process Management are typically derived from unstructured textual process descriptions, yet turning procedural documents into formal or semi-formal process model diagrams remains time-consuming and costly. This qualitative analysis reviews state-of-the-art approaches and evaluates representative tools on samples from real Standard Operating Procedures with higher complexity. Results show that rule- and heuristic-driven methods lack maturity and cannot perform reliably in realistic scenarios.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Business Process Management and the Need for Process Models

Process Mining and Text-Based Process Extraction

Problem Definition and Challenges

Qualitative Analysis Approach

A Qualitative Analysis of the State of the Art in Process Extraction from Text Patrizio Bellana,b, Mauro Dragonia and Chiara Ghidinia a Fondazione Bruno Kessler, via Sommarive 18, 38050 Povo, Italy b Free University of Bozen-Bolzano, Bolzano, Italy Abstract Within a company, processes are typically documented in form of unstructured textual information. To exploit all the techniques of Business Process Management and Process Mining, process models need to be represented in a formal (or semi-formal) representation, the process model diagram. However, manually obtaining an initial process model out ofa process description document is a time consuming and cost intensive operation. Some initial solutions to address the challenge of process extraction from text have been proposed in the literature. But, the analysis of state of the art contributions reveals that this line of research has not reached its maturity yet and that process extraction from text can be considered an unresolved problem still in an early stage of development. Indeed, these contributions mainly adopt ad-hoc solutions based on rules, word-lists, and heuristics. In this paper, we adopt the instrument of qualitative analysis on state-of-the-art approaches and tools to shed light on current limitations of the process extraction from text area. In addition to an analysis of the main reference papers we test reference tools on samples of text extracted from real documents describing Standard Operating Procedures that exhibit a greater complexity than the publicly available procedural descriptions so far used as reference text by the process extraction from text community. The analysis reveals the inability for those approaches to perform well in real scenarios. The discussion of the results illustrates open points, fundamental challenges to solve, and gaps to fill. It also suggests new ideas on how to tackle some of the identified limitations which we intend to pursue in the future. Keywords Natural Language Processing, Information Extraction, Business Process Model 1. Introduction Business Process Management (BPM) is a discipline that aims to discover, design, analyze, measure, improve, optimize, and manage business processes. A business process is a collection of ordered activities to model a specific business objective (typically represented in diagram) [1] . Process model diagrams are particularly important as most of the methodologies and techniques in the BPM field require them as a mean to analyze the real processes. Unfortunately, the initial elicitation of a process model diagram is a time consuming and cost intensive operation [2] that could require up to the 60% of the time spent in a project [3] . Therefore, there is an interest in discovering novel algorithmic procedures to alleviate the initial creation of process models. AIxIA 2020 Discussion Papers Workshop " [pbellan@fbk.eu](pbellan@fbk.eu) (P. Bellan); [dragoni@fbk.eu](dragoni@fbk.eu) (M. Dragoni); [ghidini@fbk.eu](ghidini@fbk.eu) (C. Ghidini) 􀀒 0000-0002-2971-1872 (P. Bellan); 0000-0003-0380-6571 (M. Dragoni); 0000-0003-1563-4965 (C. Ghidini) © 2020 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0) . CWPEURorkroceshopedings http://ceurISSN 1613-ws-0073.org CEUR Workshop Proceedings ([CEUR-WS.org](CEUR-WS.org)) Process Mining refers to the set of algorithmic methodologies that aim to automatically extract a process model as described in data. Typically these techniques exploit transactional data stored into so-called event-log. The fact that processes are often described as unstructured textual information has originated research efforts devoted to develop techniques able to automatize process extraction from text. Similarly to what has happened in other disciplines, such as for instance, ontology extraction from text [4], these techniques can be then embedded in modeling tools [5] . Proce

FAQs

Why is process extraction from text considered difficult in real settings?

Natural language ambiguity, varying writing styles, and domain variability make it challenging to transform procedural descriptions into accurate process model diagrams. The paper also notes that existing solutions remain immature and often rely on ad-hoc rules and heuristics.

What method does the paper use to evaluate state-of-the-art approaches?

The paper conducts a qualitative analysis of state-of-the-art approaches and tools. It also tests reference tools on text extracted from real Standard Operating Procedures that are more complex than publicly available reference descriptions.

What do the results indicate about current tools?

The analysis shows an inability of current state-of-the-art tools to scale up and perform well in real scenarios. The discussion highlights open points, fundamental challenges, and research gaps to address.

Oct 24, 2026

Upload by Sophia Brooks