A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges

TL;DR

This paper surveys recent advances in complex question answering over knowledge bases, highlighting new methods, challenges, and future research directions in the field.

Contribution

It categorizes recent approaches into a taxonomy of retrieval-based and neural semantic parsing-based methods, providing a comprehensive overview.

Findings

Traditional methods rely on templates and rules

Neural approaches are increasingly prominent

Future research directions are discussed

Abstract

Question Answering (QA) over Knowledge Base (KB) aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge bases. In order to make KBQA more applicable in actual scenarios, researchers have shifted their attention from simple questions to complex questions, which require more KB triples and constraint inference. In this paper, we introduce the recent advances in complex QA. Besides traditional methods relying on templates and rules, the research is categorized into a taxonomy that contains two main branches, namely Information Retrieval-based and Neural Semantic Parsing-based. After describing the methods of these branches, we analyze directions for future research and introduce the models proposed by the Alime team.