Assisted declarative process creation from natural language descriptions

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

Assisted declarative process creation from natural language descriptions. / Lopez, Hugo A.; Marquard, Morten; Muttenthaler, Lukas; Stromsted, Rasmus.

Proceedings - 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop, EDOCW 2019. IEEE, 2019. s. 96-99 8907309.

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Lopez, HA, Marquard, M, Muttenthaler, L & Stromsted, R 2019, Assisted declarative process creation from natural language descriptions. i Proceedings - 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop, EDOCW 2019., 8907309, IEEE, s. 96-99, 23rd IEEE International Enterprise Distributed Object Computing Workshop, EDOCW 2019, Paris, Frankrig, 28/10/2019. https://doi.org/10.1109/EDOCW.2019.00027

APA

Lopez, H. A., Marquard, M., Muttenthaler, L., & Stromsted, R. (2019). Assisted declarative process creation from natural language descriptions. I Proceedings - 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop, EDOCW 2019 (s. 96-99). [8907309] IEEE. https://doi.org/10.1109/EDOCW.2019.00027

Vancouver

Lopez HA, Marquard M, Muttenthaler L, Stromsted R. Assisted declarative process creation from natural language descriptions. I Proceedings - 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop, EDOCW 2019. IEEE. 2019. s. 96-99. 8907309 https://doi.org/10.1109/EDOCW.2019.00027

Author

Lopez, Hugo A. ; Marquard, Morten ; Muttenthaler, Lukas ; Stromsted, Rasmus. / Assisted declarative process creation from natural language descriptions. Proceedings - 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop, EDOCW 2019. IEEE, 2019. s. 96-99

Bibtex

@inproceedings{a63207f5f19a4e2cac3681e2fa4a8664,
title = "Assisted declarative process creation from natural language descriptions",
abstract = "In this paper, we report recent advances on user support for declarative process generation from natural language descriptions. The Process Highlighter is a hybrid-modelling tool that facilitates the (manual) creation of Dynamic Response Condition (DCR) graphs directly from text documents, supporting non-technical users in the adoption of declarative process models. While some process descriptions are a few paragraphs long, others, such as the ones coming from municipal governments and legal bodies might contain several pages. Some aspects that undermine the adoption of hybrid modelling techniques and their promised one-to-one correspondence between texts and process models are the length of the texts, the inconsistent use of terms, and the difficulty in identifying textual elements that correspond to elements in a declarative process model. To mitigate these risks, we have implemented major additions in the Process Highlighter for industrial usage. The principal change is the inclusion of Natural Language Processing (NLP) techniques to support users in the identification of roles, activities and constraints. This, combined with the modelling, simulation and verification tools already existing in the framework, support the users in providing process models that are better aligned with their specifications, in a shorter time. These features are motivated from empirical observations of the use of the Process Highlighter in groups of caseworkers and students of process engineering in Danish universities.",
keywords = "Business Process Management, Business Process Recognition, DCR graphs, Declarative Process Models, Natural Language Processing",
author = "Lopez, {Hugo A.} and Morten Marquard and Lukas Muttenthaler and Rasmus Stromsted",
year = "2019",
month = oct,
doi = "10.1109/EDOCW.2019.00027",
language = "English",
pages = "96--99",
booktitle = "Proceedings - 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop, EDOCW 2019",
publisher = "IEEE",
note = "23rd IEEE International Enterprise Distributed Object Computing Workshop, EDOCW 2019 ; Conference date: 28-10-2019 Through 31-10-2019",

}

RIS

TY - GEN

T1 - Assisted declarative process creation from natural language descriptions

AU - Lopez, Hugo A.

AU - Marquard, Morten

AU - Muttenthaler, Lukas

AU - Stromsted, Rasmus

PY - 2019/10

Y1 - 2019/10

N2 - In this paper, we report recent advances on user support for declarative process generation from natural language descriptions. The Process Highlighter is a hybrid-modelling tool that facilitates the (manual) creation of Dynamic Response Condition (DCR) graphs directly from text documents, supporting non-technical users in the adoption of declarative process models. While some process descriptions are a few paragraphs long, others, such as the ones coming from municipal governments and legal bodies might contain several pages. Some aspects that undermine the adoption of hybrid modelling techniques and their promised one-to-one correspondence between texts and process models are the length of the texts, the inconsistent use of terms, and the difficulty in identifying textual elements that correspond to elements in a declarative process model. To mitigate these risks, we have implemented major additions in the Process Highlighter for industrial usage. The principal change is the inclusion of Natural Language Processing (NLP) techniques to support users in the identification of roles, activities and constraints. This, combined with the modelling, simulation and verification tools already existing in the framework, support the users in providing process models that are better aligned with their specifications, in a shorter time. These features are motivated from empirical observations of the use of the Process Highlighter in groups of caseworkers and students of process engineering in Danish universities.

AB - In this paper, we report recent advances on user support for declarative process generation from natural language descriptions. The Process Highlighter is a hybrid-modelling tool that facilitates the (manual) creation of Dynamic Response Condition (DCR) graphs directly from text documents, supporting non-technical users in the adoption of declarative process models. While some process descriptions are a few paragraphs long, others, such as the ones coming from municipal governments and legal bodies might contain several pages. Some aspects that undermine the adoption of hybrid modelling techniques and their promised one-to-one correspondence between texts and process models are the length of the texts, the inconsistent use of terms, and the difficulty in identifying textual elements that correspond to elements in a declarative process model. To mitigate these risks, we have implemented major additions in the Process Highlighter for industrial usage. The principal change is the inclusion of Natural Language Processing (NLP) techniques to support users in the identification of roles, activities and constraints. This, combined with the modelling, simulation and verification tools already existing in the framework, support the users in providing process models that are better aligned with their specifications, in a shorter time. These features are motivated from empirical observations of the use of the Process Highlighter in groups of caseworkers and students of process engineering in Danish universities.

KW - Business Process Management

KW - Business Process Recognition

KW - DCR graphs

KW - Declarative Process Models

KW - Natural Language Processing

UR - http://www.scopus.com/inward/record.url?scp=85075978401&partnerID=8YFLogxK

U2 - 10.1109/EDOCW.2019.00027

DO - 10.1109/EDOCW.2019.00027

M3 - Article in proceedings

AN - SCOPUS:85075978401

SP - 96

EP - 99

BT - Proceedings - 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop, EDOCW 2019

PB - IEEE

T2 - 23rd IEEE International Enterprise Distributed Object Computing Workshop, EDOCW 2019

Y2 - 28 October 2019 through 31 October 2019

ER -

ID: 235145080