TY - CHAP

T1 - HySQA: Hybrid Scholarly Question Answering

AU - Taffa, Tilahun

AU - Banerjee, Debayan

AU - Assabie, Yaregal

AU - Usbeck, Ricardo

N1 - Conference code: 21

PY - 2025/8/26

Y1 - 2025/8/26

N2 - Purpose:The heterogeneity of scholarly information in knowledge graphs (KGs) and unstructured textual sources poses challenges in building robust Scholarly Question Answering (SQA) systems. Existing datasets and models typically address a narrow spectrum, focusing exclusively on KGs or unstructured sources and limiting evaluation to simple factoid questions. This gap leaves current systems unable to answer complex, hybrid scholarly questions that require integrating evidence from multiple heterogeneous data sources.Methodology:We introduce HySQA (Hybrid Scholarly Question Answering), a large-scale benchmarking dataset containing hybrid questions over scholarly KGs and Wikipedia text. HySQA contains complex questions that need to traverse facts across structured and unstructured sources. We also develop a baseline model that adaptively decomposes each question into sub-questions, identifies their answer sources, retrieves relevant information from SKGs and Wikipedia, and generates an answer using a hybrid augmented answer generation framework.Findings:The experimental results show that integrating static and adaptive decomposition methods is more effective than static decomposition alone.Value:Introducing HySQA provides the community with resources for evaluating the advancements in scholarly QA research.

AB - Purpose:The heterogeneity of scholarly information in knowledge graphs (KGs) and unstructured textual sources poses challenges in building robust Scholarly Question Answering (SQA) systems. Existing datasets and models typically address a narrow spectrum, focusing exclusively on KGs or unstructured sources and limiting evaluation to simple factoid questions. This gap leaves current systems unable to answer complex, hybrid scholarly questions that require integrating evidence from multiple heterogeneous data sources.Methodology:We introduce HySQA (Hybrid Scholarly Question Answering), a large-scale benchmarking dataset containing hybrid questions over scholarly KGs and Wikipedia text. HySQA contains complex questions that need to traverse facts across structured and unstructured sources. We also develop a baseline model that adaptively decomposes each question into sub-questions, identifies their answer sources, retrieves relevant information from SKGs and Wikipedia, and generates an answer using a hybrid augmented answer generation framework.Findings:The experimental results show that integrating static and adaptive decomposition methods is more effective than static decomposition alone.Value:Introducing HySQA provides the community with resources for evaluating the advancements in scholarly QA research.

KW - Business informatics

KW - Scholarly hybrid questions

KW - Scholarly Question Answering

KW - Hybrid Question Answering

KW - Complex Question Answering

UR - https://ebooks.iospress.nl/ISBN/978-1-64368-616-5

U2 - 10.3233/SSW250024

DO - 10.3233/SSW250024

M3 - Article in conference proceedings

T3 - Studies on the Semantic Web

SP - 247

EP - 263

BT - Linking Meaning: Semantic Technologies Shaping the Future of AI

A2 - Spahiu, Blerina

A2 - Vahdati, Sahar

A2 - Salatino, Angelo

A2 - Pellegrini, Tassilo

A2 - Havur, Giray

PB - IOS Press BV

CY - Amsterdam

T2 - 21st International Conference on Semantic Systems

Y2 - 3 September 2025 through 5 September 2025

ER -