Bridge-Generate: Scholarly Hybrid Question Answering

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Standard

Bridge-Generate: Scholarly Hybrid Question Answering. / Taffa, Tilahun Abedissa; Usbeck, Ricardo.
WWW Companion’25: Companion Proceedings of the ACM Web Conference 2025, April 28-May 2, 2025 Sydney, NSW, Australia. Hrsg. / Guodong Long; Michale Blumestein; Yi Chang; Liane Lewin-Eytan; Helen Huang; Elad Yom-Tov. New York: Association for Computing Machinery, Inc, 2025. S. 1321-1325.

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Harvard

Taffa, TA & Usbeck, R 2025, Bridge-Generate: Scholarly Hybrid Question Answering. in G Long, M Blumestein, Y Chang, L Lewin-Eytan, H Huang & E Yom-Tov (Hrsg.), WWW Companion’25: Companion Proceedings of the ACM Web Conference 2025, April 28-May 2, 2025 Sydney, NSW, Australia. Association for Computing Machinery, Inc, New York, S. 1321-1325, ACM Web Conference 2025, Sydney, Australian Capital Territory, Australien, 28.04.25. https://doi.org/10.1145/3701716.3715459

APA

Taffa, T. A., & Usbeck, R. (2025). Bridge-Generate: Scholarly Hybrid Question Answering. In G. Long, M. Blumestein, Y. Chang, L. Lewin-Eytan, H. Huang, & E. Yom-Tov (Hrsg.), WWW Companion’25: Companion Proceedings of the ACM Web Conference 2025, April 28-May 2, 2025 Sydney, NSW, Australia (S. 1321-1325). Association for Computing Machinery, Inc. https://doi.org/10.1145/3701716.3715459

Vancouver

Taffa TA, Usbeck R. Bridge-Generate: Scholarly Hybrid Question Answering. in Long G, Blumestein M, Chang Y, Lewin-Eytan L, Huang H, Yom-Tov E, Hrsg., WWW Companion’25: Companion Proceedings of the ACM Web Conference 2025, April 28-May 2, 2025 Sydney, NSW, Australia. New York: Association for Computing Machinery, Inc. 2025. S. 1321-1325 doi: 10.1145/3701716.3715459

Bibtex

@inbook{4bc9b67dc1414f30b4025327cbb3023a,
title = "Bridge-Generate: Scholarly Hybrid Question Answering",
abstract = "Answering scholarly hybrid questions requires access to bibliographic facts stored in structured data, such as a Knowledge Graph (KG) and textual information. Existing Scholarly Hybrid Question Answering (SHQA) approaches rely on retrieving KG triples and documents from the Wikipedia text corpus and prompt an LLM (Large Language Model) for answers. However, the retrieval is heavily keyword-based, introducing noise into the context. Furthermore, despite detecting the entities in the question, the models do not attempt any question analysis. Therefore, we propose a new SHQA system that employs a bridge-generate approach. During the bridge phase, our system recursively identifies entity-encapsulating phrases within the question and resolves the entities leveraging the underlying KGs. It then formulates assertion statements based on the resolved entities and their corresponding phrases. In the generation phase, the system auto-generates context guided by the question and the assertions. Finally, it returns an answer prompting an LLM with the generated context, the assertions, and the question. Our approach outperforms previous approaches, addressing the identified gaps.",
keywords = "Business informatics",
author = "Taffa, {Tilahun Abedissa} and Ricardo Usbeck",
year = "2025",
doi = "10.1145/3701716.3715459",
language = "English",
pages = "1321--1325",
editor = "Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Helen Huang and Elad Yom-Tov",
booktitle = "WWW Companion{\textquoteright}25",
publisher = "Association for Computing Machinery, Inc",
address = "United States",
note = "ACM Web Conference 2025, WWW 25 ; Conference date: 28-04-2025 Through 02-05-2025",

}

RIS

TY - CHAP

T1 - Bridge-Generate: Scholarly Hybrid Question Answering

AU - Taffa, Tilahun Abedissa

AU - Usbeck, Ricardo

PY - 2025

Y1 - 2025

N2 - Answering scholarly hybrid questions requires access to bibliographic facts stored in structured data, such as a Knowledge Graph (KG) and textual information. Existing Scholarly Hybrid Question Answering (SHQA) approaches rely on retrieving KG triples and documents from the Wikipedia text corpus and prompt an LLM (Large Language Model) for answers. However, the retrieval is heavily keyword-based, introducing noise into the context. Furthermore, despite detecting the entities in the question, the models do not attempt any question analysis. Therefore, we propose a new SHQA system that employs a bridge-generate approach. During the bridge phase, our system recursively identifies entity-encapsulating phrases within the question and resolves the entities leveraging the underlying KGs. It then formulates assertion statements based on the resolved entities and their corresponding phrases. In the generation phase, the system auto-generates context guided by the question and the assertions. Finally, it returns an answer prompting an LLM with the generated context, the assertions, and the question. Our approach outperforms previous approaches, addressing the identified gaps.

AB - Answering scholarly hybrid questions requires access to bibliographic facts stored in structured data, such as a Knowledge Graph (KG) and textual information. Existing Scholarly Hybrid Question Answering (SHQA) approaches rely on retrieving KG triples and documents from the Wikipedia text corpus and prompt an LLM (Large Language Model) for answers. However, the retrieval is heavily keyword-based, introducing noise into the context. Furthermore, despite detecting the entities in the question, the models do not attempt any question analysis. Therefore, we propose a new SHQA system that employs a bridge-generate approach. During the bridge phase, our system recursively identifies entity-encapsulating phrases within the question and resolves the entities leveraging the underlying KGs. It then formulates assertion statements based on the resolved entities and their corresponding phrases. In the generation phase, the system auto-generates context guided by the question and the assertions. Finally, it returns an answer prompting an LLM with the generated context, the assertions, and the question. Our approach outperforms previous approaches, addressing the identified gaps.

KW - Business informatics

UR - https://dl.acm.org/doi/10.1145/3701716.3715459

UR - https://dl.acm.org/action/showFmPdf?doi=10.1145%2F3701716

U2 - 10.1145/3701716.3715459

DO - 10.1145/3701716.3715459

M3 - Article in conference proceedings

SP - 1321

EP - 1325

BT - WWW Companion’25

A2 - Long, Guodong

A2 - Blumestein, Michale

A2 - Chang, Yi

A2 - Lewin-Eytan, Liane

A2 - Huang, Helen

A2 - Yom-Tov, Elad

PB - Association for Computing Machinery, Inc

CY - New York

T2 - ACM Web Conference 2025

Y2 - 28 April 2025 through 2 May 2025

ER -