Artificial Intelligence

Question Answering on Linked Open Data: Past, Present and Future

When:
Monday, April 09, 2018, 11:00am - 12:00pm PSTiCal
Where:
6th floor large conference room
This event is open to the public.
Type:
AI Seminar
Speaker:
Saeedeh Shekarpour, University of Dayton
Video:
https://bluejeans.com/s/sAh2_
Description:

Question Answering (QA) systems are becoming the inspiring model for the future of search engines. While, recently, datasets underlying QA systems have been promoted from unstructured datasets to structured datasets with semantically highly enriched metadata, question answering systems are still facing serious challenges and are therefore not meeting users’ expectations.  Especially, question answering over interlinked data sources is raising new challenges due to two inherent characteristics. First, different datasets employ heterogeneous schemas and each one may only contain a part of the answer to a certain question. Second, constructing a federated formal query across different datasets requires exploiting links between the different datasets on both the schema and instance levels. This talk will be conducted in the three following directions:

i.    SINA strategies for addressing the salient challenges of QA systems [1,2,3]

ii.    Re-engineering Question Answering Systems [4,5,6]

iii.    A look to the future

[1] Saeedeh Shekarpour, Axel-Cyrille Ngomo, Sören Auer: Question answering on interlinked data. WWW 2013

[2] Saeedeh Shekarpour, Edgard Marx, Axel-Cyrille Ngonga Ngomo, Sören Auer: SINA: Semantic interpretation of user queries for question answering on interlinked data. J. Web Sem. 2015

[3] Saeedeh Shekarpour, Edgards Marx, Sören Auer, and Amit Sheth. RQUERY: Rewriting Natural Language

[4] Queries on Knowledge Graphs to Alleviate the Vocabulary Mismatch Problem. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence AAAI-17

[5] Andreas Both, Dennis Diefenbach, Kuldeep Singh, Saeedeh Shekarpour, Didier Cherix, Christoph Lange: Qanary - A Methodology for Vocabulary-Driven Open Question Answering Systems. ESWC2016

[6] Why Reinvent the Wheel-Let's Build Question Answering Systems Together. Kuldeep Singh, Sethupat, A, Andreas Both, Saeedeh Shekarpour, Lytra, I, Usbeck, R, Vyas, A, Khikmatullaev, A, Punjani, D, Christoph Lange, Vidal, M-E, Jens Lehmann, Sören Auer. The Web Conference (WWW 2018)

[7] Kuldeep SinghAndreas BothDennis Diefenbach, Saeedeh Shekarpour:
Towards a Message-Driven Vocabulary for Promoting the Interoperability of Question Answering Systems. ICSC 2016: 386-389

Speaker ‘s Background

Saeedeh Shekarpour joined the University of Dayton as an assistant professor in 2018. She honorably accomplished her PhD research at the University of Bonn in Germany. Saeedeh also spent one year as a postdoctoral researcher in the EIS research group at the Bonn University and two years as a postdoctoral researcher at Knoesis research center. She is passionate to conduct advanced research in the following fields: (i) Question Answering, (ii) Linked Open Data, (iii) Ontology Development, (iv) Text and knowledge Analytics. She successfully published her research results in the most renowned conferences and journals of her field including World Wide Web, AAAI, Web Intelligence conference, Journal of Web Semantics, Semantic Web Journal.

« Return to Events