The field of QA is so vast that the list of different QA systems can go long. Many QA systems based on specific domains have been developed. While many of these systems achieved significant performance for special use cases, a shortage was observed in all of them. We figured out that the existing QA systems suffer from the following drawbacks: (1) potential of reusing its components is very weak, (2) extension of the components is problematic, and (3) interoperability between the employed components are not systematically defined. Therefore, there is a need for a descriptive approach that defines a conceptual view of QA systems. This approach must cover all the needs of current QA systems and be abstracted from implementation details. Moreover, it must be open such that it can be used in future QA systems. The generalized approach for architecture or ontology of a QA system and semantic search must focus to bring all state-of-the-art advancements of QA under a single umbrella. We envisioned that a generalized vocabulary for QA will be an abstraction level on top of all the existing QA approaches and will provide interoperability and exchangeability between them. This generalized vocabulary can be further used to integrate different components and web services within a QA system. For this, we have developed a message driven vocabulary to promote interoperability of Question answering Systems. This paper got accepted in ICSC 2016. This is now acting as a foundation step for further research to promote reusability of QA components in our current work. Furthermore, a vocabulary driven methodology for integrating heterogeneous QA components named Qanary has been developed. The work had been published in ESWC 2016. This work is extended to create the Qanary ecosystem with independent QA components integrated in Qanary architecture. The paper describing the ecosystem is now under review in ICWE 2017.

While integrating components in Qanary ecosystem, it has been observed that user need to put lot of manual work to create a QA pipeline. To solve this problem, QAestro, an ontology based approach for orchestrating QA components has been developed and work is now submitted to ICWE 2017.

Publications

Question Answering on Linked Data: Challenges and Future Directions. Saeedeh Shekarpour, Denis Lukovnikov, Ashwini Jaya Kumar, Kemele Endris, Kuldeep Singh, Harsh Thakkar, Christoph Lange. Q4APS at WWW 2016: 693-698 URL PDF

Qanary - the Fast Track to Creating a Question Answering System with Linked Data Technology. Kuldeep Singh, Andreas Both, Dennis Diefenbach, Saedeeh Shekarpour, Didier Cherix, Christoph Lange. ESWC (Satellite Events) 2016: 183-188 URL PDF

Towards a Message-Driven Vocabulary for Promoting the Interoperability of Question Answering Systems. Kuldeep Singh, Andreas Both, Dennis Diefenbach, Saeedeh Shekarpour. IEEE ICSC 2016: 386-389 URL PDF

Qanary - A Methodology for Vocabulary-driven Open Question Answering Systems. Andreas Both, Dennis Diefenbach, Kuldeep Singh, Saedeeh Shekarpour, Didier Cherix, Christoph Lange. ESWC 2016: 625-641 URL PDF

QAestro–semantic-based composition of question answering pipelines. Kuldeep Singh, Ionna Lytra, Maria Esther-Vidal, Dharmen Punjani, Harsh Thakkar, Christoph Lange, Sören Auer. DEXA 2017: 19-34 URL PDF

The Qanary Ecosystem: getting new insights by composing Question Answering pipelines. Dennis Diefenbach, Kuldeep Singh, Andreas Both, Didier Cherix, Christoph Lange,Sören Auer. ICWE 2017: 171-189 URL PDF

Rapid Engineering of QA Systems Using the Light-Weight Qanary Architecture. Andreas Both, Kuldeep Singh, Dennis Diefenbach, Ioanna Lytra. ICWE 2017: 544-548 URL PDF