Self-Wiring Question Answering Systems
This addresses the problem of tedious and time-consuming QA system development for researchers and companies, though it appears incremental as it builds on existing component reuse concepts.
The paper tackles the challenge of accelerating the creation of novel or tailored question answering (QA) systems by proposing a self-wiring approach that enables reuse of existing web-based QA modules, using Web Ontology Language descriptions and data-driven composition to reduce development time.
Question answering (QA) has been the subject of a resurgence over the past years. The said resurgence has led to a multitude of question answering (QA) systems being developed both by companies and research facilities. While a few components of QA systems get reused across implementations, most systems do not leverage the full potential of component reuse. Hence, the development of QA systems is currently still a tedious and time-consuming process. We address the challenge of accelerating the creation of novel or tailored QA systems by presenting a concept for a self-wiring approach to composing QA systems. Our approach will allow the reuse of existing, web-based QA systems or modules while developing new QA platforms. To this end, it will rely on QA modules being described using the Web Ontology Language. Based on these descriptions, our approach will be able to automatically compose QA systems using a data-driven approach automatically.