d'Aquin, Mathieu; Lopez, Vanessa and Motta, Enrico
PDF (Accepted Manuscript)
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
|Google Scholar:||Look up in Google Scholar|
This submission presents the application of two coupled systems to the Billion Triples Challenge. The first system (Watson) provides the infrastructure which allows the second one (PowerAqua) to pose natural language queries to the billion triple datasets. Watson is a gateway to the Semantic Web: it crawls and indexes semantic data online to provide a variety of access mechanisms for human users and applications.We show here how we indexed most of the datasets provided for the challenge, thus obtaining an infrastructure (comprising web services, API, web interface, etc.) which supports the exploration of these datasets and makes them available to any Watson-based application. PowerAqua is an open domain question answering system which allows users to pose natural language queries to large scale collections of heterogeneous semantic data. In this paper, we discuss the issues we faced in configuring
PowerAqua and Watson for the challenge and report on our results. The system composed of Watson and PowerAqua, and applied to the Billion Triples Challenge, is called FABilT.
|Item Type:||Conference Item|
|Copyright Holders:||2008 The Authors|
|Academic Unit/Department:||Knowledge Media Institute|
|Interdisciplinary Research Centre:||Centre for Research in Computing (CRC)|
|Depositing User:||Kay Dave|
|Date Deposited:||23 Nov 2010 09:11|
|Last Modified:||23 Feb 2016 21:28|
|Share this page:|
Download history for this item
These details should be considered as only a guide to the number of downloads performed manually. Algorithmic methods have been applied in an attempt to remove automated downloads from the displayed statistics but no guarantee can be made as to the accuracy of the figures.