TY - CHAP

T1 - SH-CoDE: Scholarly Hybrid Complex Question Decomposition and Execution

AU - Taffa, Tilahun Abedissa

AU - Usbeck, Ricardo

N1 - Conference code: 19

PY - 2025/2/5

Y1 - 2025/2/5

N2 - Our research addresses the challenge of answering complex scholarly hybrid questions, often demanding multi-faceted reasoning and iterative answer retrieval over scholarly knowledge graphs (KGs) and text. The question complexity is simplified by decomposing it into simple questions and utilizing symbolic representation. However, existing scholarly hybrid Question Answering (QA) models lack question decomposition and symbolic representation. In response, we propose SH-CoDE (Scholarly Hybrid Complex Question !!ecomposition and Execution). This approach breaks down questions into simple queries and employs symbolic representations, resulting in a natural and interpretable format - HQ (Hybrid Question) representation. SH-CoDE also includes an HQ-Executor, transforming the HQ representation into a tree structure and executing operations within its nodes. During execution, if the executor encounters symbolic representations such as KGQA or TextQA, it retrieves answers from KG and text data sources, respectively. The KGQA module automatically generates and runs SPARQL queries against the KG SPARQL endpoints. Similarly, the TextQA component employs semantic searching and an FLAN - T5-based reader to answer over text. Our model demonstrates competitive results on the test dataset, showcasing its effectiveness in answering complex scholarly Questions.

AB - Our research addresses the challenge of answering complex scholarly hybrid questions, often demanding multi-faceted reasoning and iterative answer retrieval over scholarly knowledge graphs (KGs) and text. The question complexity is simplified by decomposing it into simple questions and utilizing symbolic representation. However, existing scholarly hybrid Question Answering (QA) models lack question decomposition and symbolic representation. In response, we propose SH-CoDE (Scholarly Hybrid Complex Question !!ecomposition and Execution). This approach breaks down questions into simple queries and employs symbolic representations, resulting in a natural and interpretable format - HQ (Hybrid Question) representation. SH-CoDE also includes an HQ-Executor, transforming the HQ representation into a tree structure and executing operations within its nodes. During execution, if the executor encounters symbolic representations such as KGQA or TextQA, it retrieves answers from KG and text data sources, respectively. The KGQA module automatically generates and runs SPARQL queries against the KG SPARQL endpoints. Similarly, the TextQA component employs semantic searching and an FLAN - T5-based reader to answer over text. Our model demonstrates competitive results on the test dataset, showcasing its effectiveness in answering complex scholarly Questions.

KW - Semantic search

KW - Biological system modeling

KW - Soft sensors

KW - Query processing

KW - Computational modeling

KW - Knowledge graphs

KW - Question answering (information retrieval)

KW - Cognition

KW - Complexity theory

KW - Iterative methods

UR - https://ieeexplore.ieee.org/document/11036317/

U2 - 10.1109/ICSC64641.2025.00024

DO - 10.1109/ICSC64641.2025.00024

M3 - Article in conference proceedings

SN - 979-8-3315-2427-2

SP - 1

EP - 8

BT - 2025 19th International Conference on Semantic Computing (ICSC)

PB - IEEE Canada

T2 - 19th International Conference on Semantic Computing - ICSC 2025

Y2 - 3 February 2025 through 5 February 2025

ER -