Temporal Knowledge Graph Question Answering: A Survey

2024-06-20

arXiv.org

AI Summary

This work addresses two core challenges in temporal knowledge graph question answering (TKGQA): ambiguous definitions of temporal questions and the absence of a systematic taxonomy for existing methods. To tackle these, we propose the first fine-grained temporal question classification scheme, rigorously delineating the semantic boundaries of time-sensitive queries. Methodologically, we introduce a dual-track taxonomic framework—integrating semantic parsing and TKG embedding approaches—to enable the first comprehensive, structured survey of TKGQA methodologies. Through bibliometric analysis and technical evolution tracing, we identify critical research frontiers, including dynamic reasoning and multi-hop temporal modeling. Our contribution is the first authoritative, structured survey in the TKGQA domain, establishing a theoretical foundation and practical roadmap for task standardization and methodological systematization.

Technology Category

Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal DataKnowledge Representation and Reasoning: Geometric, Spatial, and Temporal ReasoningPlanning, Routing, and Scheduling: Temporal Planning

Application Category

Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologiesGraph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphsWeb Mining and Content Analysis: Community question answering

Abstract

Knowledge Base Question Answering (KBQA) has been a long-standing field to answer questions based on knowledge bases. Recently, the evolving dynamics of knowledge have attracted a growing interest in Temporal Knowledge Graph Question Answering (TKGQA), an emerging task to answer temporal questions. However, this field grapples with ambiguities in defining temporal questions and lacks a systematic categorization of existing methods for TKGQA. In response, this paper provides a thorough survey from two perspectives: the taxonomy of temporal questions and the methodological categorization for TKGQA. Specifically, we first establish a detailed taxonomy of temporal questions engaged in prior studies. Subsequently, we provide a comprehensive review of TKGQA techniques of two categories: semantic parsing-based and TKG embedding-based. Building on this review, the paper outlines potential research directions aimed at advancing the field of TKGQA. This work aims to serve as a comprehensive reference for TKGQA and to stimulate further research.

Problem

• Defining ambiguities in temporal questions for TKGQA
• Lacking systematic categorization of TKGQA methods
• Surveying taxonomies and techniques for Temporal Knowledge Graph QA

Innovation

• Taxonomy of temporal questions classification
• Semantic parsing-based TKGQA techniques
• TKG embedding-based question answering