A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions

Lan, Yunshi; He, Gaole; Jiang, Jinhao; Jiang, Jing; Zhao, Wayne Xin; Wen, Ji-Rong

doi:10.48550/arxiv.2105.11644

Cited by 12 publications

(12 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ferent communities [Diefenbach et al, 2018, Chakraborty et al, 2021, or take a task-oriented view and focus on a specific branch of KBQA (i.e., KBQA with complex questions [Fu et al, 2020, Lan et al, 2021b), we focus on semantic parsing-based KBQA, the most prevailing KBQA methods, and discuss both challenges and solutions with our proposed taxonomy-therefore a techniqueoriented view-while other methods (e.g., information retrieval based KBQA) are not our focus (see Figure 2). Notably, previous surveys only discuss existing works within the KBQA realm, while no effort has been made to situate KBQA in the broader literature of semantic parsing.…”

Section: Kbqa Our Focusmentioning

confidence: 99%

Knowledge Base Question Answering: A Semantic Parsing Perspective

Gu¹,

Pahuja²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent advances in deep learning have greatly propelled the research on semantic parsing. Improvement has since been made in many downstream tasks, including natural language interface to web APIs, text-to-SQL generation, among others. However, despite the close connection shared with these tasks, research on question answering over knowledge bases (KBQA) has comparatively been progressing slowly. We identify and attribute this to two unique challenges of KBQA, schema-level complexity and fact-level complexity. In this survey, we situate KBQA in the broader literature of semantic parsing and give a comprehensive account of how existing KBQA approaches attempt to address the unique challenges. Regardless of the unique challenges, we argue that we can still take much inspiration from the literature of semantic parsing, which has been overlooked by existing research on KBQA. Based on our discussion, we can better understand the bottleneck of current KBQA research and shed light on promising directions for KBQA to keep up with the literature of semantic parsing, particularly in the era of pre-trained language models.

show abstract

Section: Kbqa Our Focusmentioning

confidence: 99%

Knowledge Base Question Answering: A Semantic Parsing Perspective

Gu¹,

Pahuja²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Semantic parsing based methods convert natural language questions to knowledge base readable queries. Lan et al [23] summarises these methods in the following steps: (1) Using a Question Understanding module to analyze questions semantically and syntactically. Common question analysis techniques include dependency parsing [1], AMR parsing [20] and skeleton parsing [33].…”

Section: Knowledge Graph Question Answeringmentioning

confidence: 99%

Retrieve-then-extract Based Knowledge Graph Querying Using Graph Neural Networks

Gao¹,

Wu²,

Hu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Knowledge graph question answering (i.e., KGQA) based on information retrieval aims to answer a question by retrieving answer from a large-scale knowledge graph. Most existing methods first roughly retrieve the knowledge subgraphs (KSG) that may contain candidate answer, and then search for the exact answer in the subgraph. However, the coarsely retrieved KSG may contain thousands of candidate nodes since the knowledge graph involved in querying is often of large scale. To tackle this problem, we first propose to partition the retrieved KSG to several smaller sub-KSGs via a new subgraph partition algorithm and then present a graph-augmented learning to rank model to select the top-ranked sub-KSGs from them. Our proposed model combines a novel subgraph matching networks to capture global interactions in both question and subgraphs and an Enhanced Bilateral Multi-Perspective Matching model to capture local interactions. Finally, we apply an answer selection model on the full KSG and the top-ranked sub-KSGs respectively to validate the effectiveness of our proposed graph-augmented learning to rank method. The experimental results on multiple benchmark datasets have demonstrated the effectiveness of our approach 1 .

show abstract

“…Observing these problems, we realized that we needed to create a questionanswer system (QA system) to help users save time and effort in getting answers to questions about the Hadith. According to Lan, et al [4], there are two main approaches to QA systems, namely semantic parsing based methods (SP-based methods), and information retrieval based methods (IR-based methods). SPbased methods answer user questions by constructing the logical form of the question and then executing the logical form against a knowledge base to get the answer.…”

Section: Introductionmentioning

confidence: 99%

A Questions Answering System on Hadith Knowledge Graph

et al. 2022

View full text Add to dashboard Cite

Several works have presented the Hadith on different digital platforms, ranging from websites to mobile apps. These works were successful in presenting the text of the Hadith to users, but this does not help them to answer any particular questions about religious matters. Therefore, in this work we propose a question-answering system that was built on a Hadith knowledge graph. To interpret the user questions correctly, we used the Levenshtein distance function, and for storing the Hadith in graph format we used Neo4J as the graph database. Our main findings were: (i) a knowledge graph is suitable for representing the Hadith and also for doing the reasoning task, and (ii) our proposed approach achieved 95% for top-1 accuracy.

show abstract

A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions

Cited by 12 publications

References 50 publications

Knowledge Base Question Answering: A Semantic Parsing Perspective

Knowledge Base Question Answering: A Semantic Parsing Perspective

Retrieve-then-extract Based Knowledge Graph Querying Using Graph Neural Networks

A Questions Answering System on Hadith Knowledge Graph

Contact Info

Product

Resources

About