A Structure and Content Prompt-based Method for Knowledge Graph Question Answering over Scholarly Data

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Standard

A Structure and Content Prompt-based Method for Knowledge Graph Question Answering over Scholarly Data. / Jiang, Longquan; Yan, Xi; Usbeck, Ricardo.
Joint Proceedings of Scholarly QALD 2023 and SemREC 2023 co-located with 22nd International Semantic Web Conference ISWC 2023 : Athens, Greece, November 6-10, 2023. ed. / Debayan Banerjee; Ricardo Usbeck; Nandana Mihindukulasooriya; Mohamad Yaser Jaradeh; Sören Auer; Gunjan Singh; Raghava Mutharaju; Pavan Kapanipathi. Vol. 3592 Aachen: Rheinisch-Westfälische Technische Hochschule Aachen, 2023. 3 (CEUR Workshop Proceedings; Vol. 3592).

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Harvard

Jiang, L, Yan, X & Usbeck, R 2023, A Structure and Content Prompt-based Method for Knowledge Graph Question Answering over Scholarly Data. in D Banerjee, R Usbeck, N Mihindukulasooriya, MY Jaradeh, S Auer, G Singh, R Mutharaju & P Kapanipathi (eds), Joint Proceedings of Scholarly QALD 2023 and SemREC 2023 co-located with 22nd International Semantic Web Conference ISWC 2023 : Athens, Greece, November 6-10, 2023. vol. 3592, 3, CEUR Workshop Proceedings, vol. 3592, Rheinisch-Westfälische Technische Hochschule Aachen, Aachen, Scholarly QALD 2023, Athen, Greece, 06.11.23. <https://ceur-ws.org/Vol-3592/paper3.pdf>

APA

Jiang, L., Yan, X., & Usbeck, R. (2023). A Structure and Content Prompt-based Method for Knowledge Graph Question Answering over Scholarly Data. In D. Banerjee, R. Usbeck, N. Mihindukulasooriya, M. Y. Jaradeh, S. Auer, G. Singh, R. Mutharaju, & P. Kapanipathi (Eds.), Joint Proceedings of Scholarly QALD 2023 and SemREC 2023 co-located with 22nd International Semantic Web Conference ISWC 2023 : Athens, Greece, November 6-10, 2023 (Vol. 3592). Article 3 (CEUR Workshop Proceedings; Vol. 3592). Rheinisch-Westfälische Technische Hochschule Aachen. https://ceur-ws.org/Vol-3592/paper3.pdf

Vancouver

Jiang L, Yan X, Usbeck R. A Structure and Content Prompt-based Method for Knowledge Graph Question Answering over Scholarly Data. In Banerjee D, Usbeck R, Mihindukulasooriya N, Jaradeh MY, Auer S, Singh G, Mutharaju R, Kapanipathi P, editors, Joint Proceedings of Scholarly QALD 2023 and SemREC 2023 co-located with 22nd International Semantic Web Conference ISWC 2023 : Athens, Greece, November 6-10, 2023. Vol. 3592. Aachen: Rheinisch-Westfälische Technische Hochschule Aachen. 2023. 3. (CEUR Workshop Proceedings).

Bibtex

@inbook{b31df50ac1f34519ac5a590c8d42d653,
title = "A Structure and Content Prompt-based Method for Knowledge Graph Question Answering over Scholarly Data",
abstract = "Answering scholarly questions is challenging without the help of query-based systems. Thus, we develop a divide-and-conquer approach based on a Large Language Model (LLM) for scholarly Knowledge Graph (KG) Question Answering (QA). Our system integrates the KG ontology into the LLM prompts and leverages a hybrid prompt learning strategy with both query structure and content. Our experiments suggest that given an ontology of a specific KG, LLMs are capable of automatically choosing the corresponding classes or predicates required to generate a target SPARQL query from a natural language question. Our approach shows state-of-the-art results over one scholarly KGQA dataset, namely sciQA [1].",
keywords = "Informatics, Question Answering, KGQA, Scholarly KGQA, Large Language Model",
author = "Longquan Jiang and Xi Yan and Ricardo Usbeck",
note = "Funding Information: This work has been partially supported by grants for the DFG project NFDI4DataScience project (DFG project no. 460234259) and by the Federal Ministry for Economics and Climate Action in the project CoyPu (project number 01MK21007G). Publisher Copyright: {\textcopyright} 2023 CEUR-WS. All rights reserved.; Scholarly QALD 2023 ; Conference date: 06-11-2023 Through 10-11-2023",
year = "2023",
month = dec,
day = "14",
language = "English",
volume = "3592",
series = "CEUR Workshop Proceedings",
publisher = "Rheinisch-Westf{\"a}lische Technische Hochschule Aachen",
editor = "Debayan Banerjee and Ricardo Usbeck and Nandana Mihindukulasooriya and Jaradeh, {Mohamad Yaser} and S{\"o}ren Auer and Gunjan Singh and Raghava Mutharaju and Pavan Kapanipathi",
booktitle = "Joint Proceedings of Scholarly QALD 2023 and SemREC 2023 co-located with 22nd International Semantic Web Conference ISWC 2023",
address = "Germany",
url = "https://ceur-ws.org/Vol-3592/",

}

RIS

TY - CHAP

T1 - A Structure and Content Prompt-based Method for Knowledge Graph Question Answering over Scholarly Data

AU - Jiang, Longquan

AU - Yan, Xi

AU - Usbeck, Ricardo

N1 - Conference code: 1

PY - 2023/12/14

Y1 - 2023/12/14

N2 - Answering scholarly questions is challenging without the help of query-based systems. Thus, we develop a divide-and-conquer approach based on a Large Language Model (LLM) for scholarly Knowledge Graph (KG) Question Answering (QA). Our system integrates the KG ontology into the LLM prompts and leverages a hybrid prompt learning strategy with both query structure and content. Our experiments suggest that given an ontology of a specific KG, LLMs are capable of automatically choosing the corresponding classes or predicates required to generate a target SPARQL query from a natural language question. Our approach shows state-of-the-art results over one scholarly KGQA dataset, namely sciQA [1].

AB - Answering scholarly questions is challenging without the help of query-based systems. Thus, we develop a divide-and-conquer approach based on a Large Language Model (LLM) for scholarly Knowledge Graph (KG) Question Answering (QA). Our system integrates the KG ontology into the LLM prompts and leverages a hybrid prompt learning strategy with both query structure and content. Our experiments suggest that given an ontology of a specific KG, LLMs are capable of automatically choosing the corresponding classes or predicates required to generate a target SPARQL query from a natural language question. Our approach shows state-of-the-art results over one scholarly KGQA dataset, namely sciQA [1].

KW - Informatics

KW - Question Answering

KW - KGQA

KW - Scholarly KGQA

KW - Large Language Model

UR - http://www.scopus.com/inward/record.url?scp=85180545725&partnerID=8YFLogxK

M3 - Article in conference proceedings

VL - 3592

T3 - CEUR Workshop Proceedings

BT - Joint Proceedings of Scholarly QALD 2023 and SemREC 2023 co-located with 22nd International Semantic Web Conference ISWC 2023

A2 - Banerjee, Debayan

A2 - Usbeck, Ricardo

A2 - Mihindukulasooriya, Nandana

A2 - Jaradeh, Mohamad Yaser

A2 - Auer, Sören

A2 - Singh, Gunjan

A2 - Mutharaju, Raghava

A2 - Kapanipathi, Pavan

PB - Rheinisch-Westfälische Technische Hochschule Aachen

CY - Aachen

T2 - Scholarly QALD 2023

Y2 - 6 November 2023 through 10 November 2023

ER -