prikaz prve stranice dokumenta A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing
  Download
PDF 473.97 KB
undergraduate thesis
A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing
Pula: University of Pula, 2023. urn:nbn:hr:137:105792
Licardo, Josip Tomo
University of Pula
Faculty of Informatics in Pula

Institutional repository: Digital Repository Juraj Dobrila University of Pula

Cite this document

Licardo, J. T. (2023). A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing (Undergraduate thesis). Pula: University of Pula. Retrieved from https://urn.nsk.hr/urn:nbn:hr:137:105792

Licardo, Josip Tomo. "A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing." Undergraduate thesis, University of Pula, 2023. https://urn.nsk.hr/urn:nbn:hr:137:105792

Licardo, Josip Tomo. "A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing." Undergraduate thesis, University of Pula, 2023. https://urn.nsk.hr/urn:nbn:hr:137:105792

Licardo, J. T. (2023). 'A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing', Undergraduate thesis, University of Pula, accessed 29 April 2024, https://urn.nsk.hr/urn:nbn:hr:137:105792

Licardo JT. A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing [Undergraduate thesis]. Pula: University of Pula; 2023 [cited 2024 April 29] Available at: https://urn.nsk.hr/urn:nbn:hr:137:105792

J. T. Licardo, "A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing", Undergraduate thesis, University of Pula, Pula, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:137:105792

Metadata
TitleA Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing
Title (croatian)Metoda ekstrakcije BPMN modela iz tekstualnih opisa obradom prirodnog jezika
AuthorJosip Tomo Licardo
MentorNikola Tanković (mentor)
MentorDarko Etinger (komentor)
Committee memberSnježana Babić (predsjednik povjerenstva)
Committee memberNikola Tanković (član povjerenstva)
Committee memberDarko Etinger (član povjerenstva)
Committee memberRobert Šajina (član povjerenstva)
Committee memberRomeo Šajina (član povjerenstva)
GranterUniversity of Pula
(Faculty of Informatics in Pula)
Pula
Defense date and country2023-09-21, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Information Systems and Information Science
Abstract
Business Process Model and Notation (BPMN) is a standard for formally modeling complex business processes. Manual creation of BPMN models can be time-consuming and error-prone, prompting a need for automation. Existing approaches, such as rule-based methods, machine learning, and machine translation, have progressed but face accuracy and real-world applicability challenges. In this research paper, we propose a novel method for automated extraction of BPMN models from textual descriptions using natural language processing (NLP) tools and deep learning models, including the spaCy library for text processing, a fine-tuned BERT model, and state-of-the-art large language models like GPT-3.5-Turbo and GPT-4. We utilize Graphviz, an open-source graph visualization software, to visualize the extracted processes. Our method supports the visualization of tasks, exclusive gateways, parallel gateways, and start and end events in the generated BPMN models.
Abstract (croatian)
Business Process Model and Notation (BPMN) je standard za formalno modeliranje poslovnih procesa. Ručna izrada BPMN modela može biti dugotrajan proces podložan pogreškama, što dovodi do potrebe za automatizacijom. Postojeći pristupi, kao što su metode bazirane na pravilima, strojno učenje i strojno prevođenje, napredovale su, ali se susreću sa izazovima u aspektima točnosti generiranih modela i primjenjivošću u stvarnom svijetu. Kako bi se riješila ova ograničenja, ovaj rad predlaže novu metodu za automatizirano izdvajanje BPMN modela iz tekstualnih opisa pomoću alata za obradu prirodnog jezika i modela dubokog učenja, uključujući spaCy biblioteku za obradu prirodnog jezika, fino podešeni BERT model i najsuvremenije velike jezične modele kao što su GPT-3.5-Turbo i GPT-4. Ekstrahirani procesi vizualiziraju se pomoću Graphviza, softvera za vizualizaciju grafova. Naša metoda podržava vizualizaciju zadataka, ekskluzivnih skretnica (eng. exclusive gateways), paralelnih skretnica (eng. parallel gateways), te početnih i završnih događaja u generiranim BPMN modelima.
Keywords
Keywords (croatian)
Languageenglish
URN:NBNurn:nbn:hr:137:105792
Study programmeTitle: Informatics
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-09-21 18:16:25