Please use this identifier to cite or link to this item: doi:10.22028/D291-33514
Volltext verfügbar? / Dokumentlieferung
Title: Using Artificial Neural Networks to Derive Process Model Activity Labels from Process Descriptions
Author(s): Pyrtek, Mirco
Hake, Philip
Loos, Peter
Editor(s): Gronau, Norbert
Heine, Moreen
Krasnova, Hanna
Pousttchi, Key
Language: English
Title: Entwicklungen, Chancen und Herausforderungen der Digitalisierung : Band 1: Proceedings der 15. Internationalen Tagung Wirtschaftsinformatik 2020
Startpage: 1818
Endpage: 1830
Publisher/Platform: GITO-Verlag
Year of Publication: 2020
Place of publication: Berlin
Title of the Conference: WI 2020
Place of the conference: Potsdam, Germany
Publikation type: Conference Paper
Abstract: Recently, Artificial Neural Networks (ANN) have shown high potential in the area of Natural Language Processing (NLP). In the area of sentence compression, the application of ANNs has proven to outperform existing rule-based approaches. Nevertheless, these approaches require a decent amount of training data to achieve high accuracy. In this work, we aim at employing ANNs to derive process model labels from process descriptions. Since the amount of publicly available pairs of text and process model is scarce, we employ a transfer learning approach. While training the compression model on a large corpus consisting of sentence-compression pairs, we transfer the model to the problem of deriving label descriptions. We implement our approach and conduct an experimental evaluation using pairs of process descriptions and models. We found that our transfer learning model keeps high recall while losing performance on precision and compression rate.
DOI of the first publication: 10.30844/wi_2020_r11-pyrtek
URL of the first publication:
Link to this record: hdl:20.500.11880/30858
ISBN: 978-3-95545-335-0
Date of registration: 11-Mar-2021
Faculty: HW - Fakultät für Empirische Humanwissenschaften und Wirtschaftswissenschaft
Department: HW - Wirtschaftswissenschaft
Professorship: HW - Prof. Dr. Peter Loos
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
There are no files associated with this item.

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.