Print Email Facebook Twitter Complex Knowledge Base Question Answering Title Complex Knowledge Base Question Answering: A Survey Author Lan, Yunshi (East China Normal University) He, G. (TU Delft Web Information Systems) Jiang, Jinhao (Renmin University of China) Jiang, Jing (Singapore Management University) Xin Zhao, Wayne (Renmin University of China) Wen, Ji Rong (Renmin University of China) Date 2022 Abstract Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Early studies mainly focused on answering simple questions over KBs and achieved great success. However, their performances on complex questions are still far from satisfactory. Therefore, in recent years, researchers propose a large number of novel methods, which looked into the challenges of answering complex questions. In this survey, we review recent advances in KBQA with the focus on solving complex questions, which usually contain multiple subjects, express compound relations, or involve numerical operations. In detail, we begin with introducing the complex KBQA task and relevant background. Then, we present two mainstream categories of methods for complex KBQA, namely semantic parsing-based (SP-based) methods and information retrieval-based (IR-based) methods. Specifically, we illustrate their procedures with flow designs and discuss their difference and similarity. Next, we summarize the challenges that these two categories of methods encounter when answering complex questions, and explicate advanced solutions as well as techniques used in existing work. After that, we discuss the potential impact of pre-trained language models (PLMs) on complex KBQA. To help readers catch up with SOTA methods, we also provide a comprehensive evaluation and resource about complex KBQA task. Finally, we conclude and discuss several promising directions related to complex KBQA for future research. Subject CognitionCompoundsKnowledge baseknowledge base question answeringKnowledge based systemsnatural language processingquestion answeringQuestion answering (information retrieval)SemanticssurveyTask analysisTV To reference this document use: http://resolver.tudelft.nl/uuid:c510dee7-5e9b-479b-acfc-4dde6d0eb50c DOI https://doi.org/10.1109/TKDE.2022.3223858 Embargo date 2023-10-26 ISSN 1041-4347 Source IEEE Transactions on Knowledge & Data Engineering, 35 (11), 11196 - 11215 Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2022 Yunshi Lan, G. He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, Ji Rong Wen Files PDF Complex_Knowledge_Base_Qu ... Survey.pdf 2.45 MB Close viewer /islandora/object/uuid:c510dee7-5e9b-479b-acfc-4dde6d0eb50c/datastream/OBJ/view