The International Semantic Web Conference is the pre-eminent international forum for the Semantic Web / Linked Data Community. The ISWC 2017 will take place October 21-25 in Vienna, Austria and will bring together researchers, practitioners and industry specialists to discuss, advance and shape the future of semantic technologies.
The DIESEL consortium has a strong presence at ISWC and proudly presents and co-organizes the NLIWoD3 workshop and supports the 8th QALD challenge on question answering. The DIESEL consortium will also give several talks for its accepted research contributions.
The 3rd International Workshop on Natural Language Interfaces for Web of Data (NLIWoD)
The NLIWoD workshop will take place on Sunday morning at ISWC this year. There are two main obstacles to making the billions of already available RDF triples accessible to common Web users: (1) the need to learn the query language SPARQL, and (2) the need to know the schemas underlying the datasets. Approaches to ease access to the Web of Data include graphical query interfaces, agent-based systems, and natural language interfaces. Amongst them, natural language interfaces are receiving growing interest due to their highly expressive power and low cost for educational purposes. Recent progress in speech recognition technologies (e.g., Siri and Google Voice) also demonstrate the usefulness of a natural language interface. The goal of this workshop is to bring together experts on the use of natural-language interfaces (NLI) for accessing the Web of Data. Come and join us! The NLIWoD3 accepted papers are published by CEUR ( http://ceur-ws.org/Vol-1932/).
8th Question Answering over Linked Data challenge
The NLIWoD 3 workshop hosts the 8th QALD challenge and participants of the workshop are cordially invited to participate with their tools. Users can display the capabilities of their systems using the provided online benchmarking platform GERBIL QA on a novel test dataset comprising 45 new questions as well as their SPARQL representation. Check out the results in our second session at the NLIWoD workshop!
We are proud to support the 8th QALD challenge and 3rd NLIWoD workshop and look forward to meeting you and your ideas at ISWC 2017.
Furthermore, the DIESEL partner metaphacts will have two presentations at the poster and demo session at this year’s ISWC:
- Alexa, Ask Wikidata! Voice interaction with knowledge graphs using Amazon Alexa – October 23, 6:30 pm – in this demo, attendees will learn how metaphacts uses Amazon Alexa technologies to build a Semantic Web application able to answer factual questions using the Wikidata knowledge graph.
- Ephedra: SPARQL federation over RDF data and services – October 23, 6:30 pm – this demo will focus on Ephedra, a federated SPARQL query processing engine targeted at processing hybrid queries, which was developed as part of the metaphactory platform.
In addition to metaphacts’ support as Gold sponsor and presenter, Peter Haase (CEO of metaphacts) is acting as Chair of the Industry Track, which will present the state of adoption of semantic technologies in industrial applications.
University of Leipzig’s research submissions
- Distributed Semantic Analytics using the SANSA Stack – October 23, Lehár 4, 11:00 – A major research challenge is to perform scalable analysis of large-scale knowledge graphs to facilitate applications like link prediction, knowledge base completion and reasoning. This software framework paper describes the ongoing Semantic Analytics Stack (SANSA) project, which supports expressive and scalable semantic analytics by providing functionality for distributed computing on RDF data.
- Iguana : A Generic Framework for Benchmarking the Read-Write Performance of Triple Stores – October 25, Lehár 1-3, 15:30 – The performance of triples stores is crucial for applications which rely on RDF data. We propose a novel SPARQL benchmark execution framework called IGUANA. Our framework complements benchmarks by providing an execution environment which can measure the performance of triple stores during data loading, data updates as well as under different loads.
- Question Answering Over Linked Data: What is Difficult to Answer? What Affects the F scores? – October 22, NLIWoD workshop – We present a fine-grained analysis of the Question Answering over Linked Data (QALD-6) challenge. We divide the QALD-6 questions into 8 main categories and compare state-of-the-art question answering (QA) systems over Linked Data against the individual categories.