Due to their predominant use of natural language (NL), requirements are prone to defects like inconsistency and incompleteness. Consequently, quality assurance processes are commonly applied to requirements manually. However, manual execution of these processes can be laborious and may inadvertently overlook critical quality issues due to time and budget constraints. This paper introduces ARIA, an innovative question-answering (QA) approach designed to automate support for stakeholders, including requirements engineers, during the analysis of NL requirements. The ability to pose questions and receive instant answers proves invaluable in proves beneficial in numerous quality-assurance scenarios, particularly in detecting incompleteness. The challenge of automating the answering of requirements-related questions is considerable, given the potential scope of the search for answers extending beyond the provided requirements specification. To overcome this challenge, ARIA integrates support for mining external domain knowledge resources like internet search results. Evaluation on seven diverse use cases drawn from the PURE dataset demonstrates ARIA's robustness and applicability across a range of real-life scenarios, highlighting its potential to significantly improve the quality and effectiveness of requirements analysis processes. This work represents one of the initial endeavors to seamlessly blend QA and external domain knowledge, effectively addressing complexities in requirements engineering.