Bridge-Generate: Scholarly Hybrid Question Answering
Publikation: Beiträge in Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
Standard
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 Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
Harvard
APA
Vancouver
Bibtex
}
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 -