An LLM-Aided Enterprise Knowledge Graph (EKG) Engineering Process. Laurenzi, E., Mathys, A., & Martin, A. Proceedings of the AAAI Symposium Series, 3(1):148–156, May, 2024. Number: 1![An LLM-Aided Enterprise Knowledge Graph (EKG) Engineering Process [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper Paper doi abstract bibtex 2 downloads Conventional knowledge engineering approaches aiming to create Enterprise Knowledge Graphs (EKG) still require a high level of manual effort and high ontology expertise, which hinder their adoption across industries. To tackle this issue, we explored the use of Large Language Models (LLMs) for the creation of EKGs through the lens of a design-science approach. Findings from the literature and from expert interviews led to the creation of the proposed artefact, which takes the form of a six-step process for EKG development. Scenarios on how to use LLMs are proposed and implemented for each of the six steps. The process is then evaluated with an anonymised data set from a large Swiss company. Results demonstrate that LLMs can support the creation of EKGs, offering themselves as a new aid for knowledge engineers.
@article{laurenzi_llm-aided_2024,
title = {An {LLM}-{Aided} {Enterprise} {Knowledge} {Graph} ({EKG}) {Engineering} {Process}},
volume = {3},
copyright = {Copyright (c) 2024 Association for the Advancement of Artificial Intelligence},
issn = {2994-4317},
url = {https://ojs.aaai.org/index.php/AAAI-SS/article/view/31194},
doi = {10.1609/aaaiss.v3i1.31194},
abstract = {Conventional knowledge engineering approaches aiming to create Enterprise Knowledge Graphs (EKG) still require a high level of manual effort and high ontology expertise, which hinder their adoption across industries. To tackle this issue, we explored the use of Large Language Models (LLMs) for the creation of EKGs through the lens of a design-science approach. Findings from the literature and from expert interviews led to the creation of the proposed artefact, which takes the form of a six-step process for EKG development. Scenarios on how to use LLMs are proposed and implemented for each of the six steps. The process is then evaluated with an anonymised data set from a large Swiss company. Results demonstrate that LLMs can support the creation of EKGs, offering themselves as a new aid for knowledge engineers.},
language = {en},
number = {1},
urldate = {2024-05-24},
journal = {Proceedings of the AAAI Symposium Series},
author = {Laurenzi, Emanuele and Mathys, Adrian and Martin, Andreas},
month = may,
year = {2024},
note = {Number: 1},
pages = {148--156},
url_paper={https://api.zotero.org/users/1325684/publications/items/SU6ZI8MW/file/view}
}
Downloads: 2
{"_id":"TNTsGSwg7js6Gvnqo","bibbaseid":"laurenzi-mathys-martin-anllmaidedenterpriseknowledgegraphekgengineeringprocess-2024","author_short":["Laurenzi, E.","Mathys, A.","Martin, A."],"bibdata":{"bibtype":"article","type":"article","title":"An LLM-Aided Enterprise Knowledge Graph (EKG) Engineering Process","volume":"3","copyright":"Copyright (c) 2024 Association for the Advancement of Artificial Intelligence","issn":"2994-4317","url":"https://ojs.aaai.org/index.php/AAAI-SS/article/view/31194","doi":"10.1609/aaaiss.v3i1.31194","abstract":"Conventional knowledge engineering approaches aiming to create Enterprise Knowledge Graphs (EKG) still require a high level of manual effort and high ontology expertise, which hinder their adoption across industries. To tackle this issue, we explored the use of Large Language Models (LLMs) for the creation of EKGs through the lens of a design-science approach. Findings from the literature and from expert interviews led to the creation of the proposed artefact, which takes the form of a six-step process for EKG development. Scenarios on how to use LLMs are proposed and implemented for each of the six steps. The process is then evaluated with an anonymised data set from a large Swiss company. Results demonstrate that LLMs can support the creation of EKGs, offering themselves as a new aid for knowledge engineers.","language":"en","number":"1","urldate":"2024-05-24","journal":"Proceedings of the AAAI Symposium Series","author":[{"propositions":[],"lastnames":["Laurenzi"],"firstnames":["Emanuele"],"suffixes":[]},{"propositions":[],"lastnames":["Mathys"],"firstnames":["Adrian"],"suffixes":[]},{"propositions":[],"lastnames":["Martin"],"firstnames":["Andreas"],"suffixes":[]}],"month":"May","year":"2024","note":"Number: 1","pages":"148–156","url_paper":"https://api.zotero.org/users/1325684/publications/items/SU6ZI8MW/file/view","bibtex":"@article{laurenzi_llm-aided_2024,\n\ttitle = {An {LLM}-{Aided} {Enterprise} {Knowledge} {Graph} ({EKG}) {Engineering} {Process}},\n\tvolume = {3},\n\tcopyright = {Copyright (c) 2024 Association for the Advancement of Artificial Intelligence},\n\tissn = {2994-4317},\n\turl = {https://ojs.aaai.org/index.php/AAAI-SS/article/view/31194},\n\tdoi = {10.1609/aaaiss.v3i1.31194},\n\tabstract = {Conventional knowledge engineering approaches aiming to create Enterprise Knowledge Graphs (EKG) still require a high level of manual effort and high ontology expertise, which hinder their adoption across industries. To tackle this issue, we explored the use of Large Language Models (LLMs) for the creation of EKGs through the lens of a design-science approach. Findings from the literature and from expert interviews led to the creation of the proposed artefact, which takes the form of a six-step process for EKG development. Scenarios on how to use LLMs are proposed and implemented for each of the six steps. The process is then evaluated with an anonymised data set from a large Swiss company. Results demonstrate that LLMs can support the creation of EKGs, offering themselves as a new aid for knowledge engineers.},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2024-05-24},\n\tjournal = {Proceedings of the AAAI Symposium Series},\n\tauthor = {Laurenzi, Emanuele and Mathys, Adrian and Martin, Andreas},\n\tmonth = may,\n\tyear = {2024},\n\tnote = {Number: 1},\n\tpages = {148--156},\n\turl_paper={https://api.zotero.org/users/1325684/publications/items/SU6ZI8MW/file/view}\n}\n\n\n\n","author_short":["Laurenzi, E.","Mathys, A.","Martin, A."],"key":"laurenzi_llm-aided_2024","id":"laurenzi_llm-aided_2024","bibbaseid":"laurenzi-mathys-martin-anllmaidedenterpriseknowledgegraphekgengineeringprocess-2024","role":"author","urls":{"Paper":"https://ojs.aaai.org/index.php/AAAI-SS/article/view/31194"," paper":"https://api.zotero.org/users/1325684/publications/items/SU6ZI8MW/file/view"},"metadata":{"authorlinks":{}},"downloads":2},"bibtype":"article","biburl":"https://bibbase.org/zotero-mypublications/andreasmartin","dataSources":["cEgnxBqYRFNdjfnYF"],"keywords":[],"search_terms":["llm","aided","enterprise","knowledge","graph","ekg","engineering","process","laurenzi","mathys","martin"],"title":"An LLM-Aided Enterprise Knowledge Graph (EKG) Engineering Process","year":2024,"downloads":2}