Survey on challenges of Question Answering in the Semantic Web

TLDR

Semantic Question Answering eliminates the need for mastering SPARQL and specific vocabularies, but its natural‑language complexity creates significant challenges, and the lack of shared components leads to redundant redevelopment. The survey aims to identify common challenges, structure solutions, and provide recommendations for future SQA systems. The authors systematically selected 62 SQA systems, yielding 72 publications from 1960 candidates using predefined inclusion/exclusion criteria, covering works from 2010 to 2015 and comparing them to earlier surveys. The survey reveals that many essential components are independently redeveloped, highlighting inefficiencies, and offers a structured set of solutions and recommendations for future systems.

Abstract

Semantic Question Answering (SQA) removes two major access requirements to the Semantic Web: the mastery of a formal query language like SPARQL and knowledge of a specific vocabulary. Because of the complexity of natural language, SQA presents difficult challenges and many research opportunities. I nstead of a shared effort, however, many essential components are redeveloped, which is an inefficient use of researcher’s time and resources. This survey analyzes 62 different SQA systems, which are systematically and manually selected using predefined inclusion and exclusion criteria, leading to 72 selected publications out of 1960 candidates. We identify common challenges, structure solutions, and provide recommendations for future systems. This work is based on publications from the end of 2010 to July 2015 and is also compared to older but similar surveys.