AKSW Blog

We are very pleased to report that 4 of our papers were accepted for presentation as full papers at ESWC 2016. These are

• Detecting Similar Linked Datasets Using Topic Modelling by Michael Röder, Axel-Cyrille Ngonga Ngomo, Ivan Ermilov and Andreas Both.
• The Lazy Traveling Salesman – Memory Management for Large-Scale Link Discovery by Axel-Cyrille Ngonga Ngomo and Mofeed Hassan.
• AskNow: A Framework for Natural Language Query Formalization in SPARQL by Mohnish Dubey, Sourish Dasgupta, Ankit Sharma, Konrad Höffner, Jens Lehmann
• Semantically Enhanced Quality Assurance in the JURION Business Use Case by Dimitris Kontokostas, Christian Mader, Christian Dirschl, Katja Eck, Michael Leuthold, Jens Lehmann, Sebastian Hellmann

In addition, we organised the first HOBBIT community meeting. Many thanks to all who participated. Get involved in the project by going here. Our survey pertaining to benchmarking is still open and we’d love to have your feedback on what you would want benchmarking Linked Data to look like.

We also presented  three research projects, i.e., HOBBIT, QAMEL and DIESEL during the EU networking sessions. Many thanks for the fruitful discussions and ideas.

Finally, we thank all the systems which participated to QALD-6 and OKE and made these challenges so interesting. Little perk: We are still to find a system to beat CETUS at the OKE challenge 🙂

FYI, a full list of accepted conference papers can be found here.

Workshops

In addition to the main conference, we were active during the workshops. Axel gave the keynote at the Profiles workshop (many thanks to the organizers for the invite). The following papers were accepted as full papers.

• DBtrends : Publishing and Benchmarking RDF Ranking Functions by Edgard Marx, Amrapali J. Zaveri, Mofeed Mohammed, Sandro Rautenberg, Jens Lehmann, Axel-Cyrille Ngonga Ngomo and Gong Cheng, SumPre2016 Workshop at ESWC 2016
  • http://dbtrends.aksw.org
• Towards Sustainable view-based Extract-Transform-Load (ETL) Fusion of Open Data by Kay Mueller, Claus Stadler, Ritesh Kumar Singh and Sebastian Hellmann, LDQ2016 [pdf]
• UPSP: Unique Predicate-based Source Selection for SPARQL Endpoint Federation by Ethem Cem Ozkan, Muhammad Saleem, Erdogan Dogdu and Axel-Cyrille Ngonga Ngomo  PROFILES Workshop at ESWC 2016 [pdf]
• Federated Query Processing: Challenges and Opportunities by Axel-Cyrille Ngonga Ngomo and Muhammad Saleem Keynote at PROFILES Workshop at ESWC 2016 [pdf]

Quo Vadis?

We are now looking forward to EDF 2016, where we will present HOBBIT as a poster as well as organise a post conference event (see http://project-hobbit.eu/edf2016). Thereafter, you can meet us at  ISWC 2016, where we will present two tutorials (Link Discovery and Federated SPARQL queries) and organise the BLINK [[http://project-hobbit.eu/events/blink-2016/]] workshop. Your submissions are welcome.

In the incoming colloquium, Mohamed Ahmed Sherif will present the paper “PARIS: Probabilistic Alignment of Relations, Instances, and Schema” from Suchanek et al., published in the proceedings of VLDB 2012 [PDF].

Abstract

One of the main challenges that the Semantic Web faces is the integration of a growing number of independently designed ontologies. In this work, we present PARIS, an approach for the automatic alignment of ontologies. PARIS aligns not only instances, but also relations and classes. Alignments at the instance level cross-fertilize with alignments at the schema level. Thereby, our system provides a truly holistic solution to the problem of ontology alignment. The heart of the approach is probabilistic, i.e., we measure degrees of matchings based on probability estimates. This allows PARIS to run without any parameter tuning. We demonstrate the efficiency of the algorithm and its precision through extensive experiments. In particular, we obtain a precision of around 90% in experiments with some of the world’s largest ontologies.

This event is part of a series of events about Semantic Web technology. Please see http://wiki.aksw.org/Colloquium for further information about previous and future events. As always, Bachelor and Master students are able to get points for attendance and there is complimentary coffee and cake after the session.

In the incoming colloquium, Mofeed Hassan will present the paper “Semi-supervised Instance Matching Using Boosted Classifiers” from Kejriwal et al., published in the proceedings of ESWC 2015 [PDF].

Abstract

Instance matching concerns identifying pairs of instances that refer to the same underlying entity. Current state-of-the-art instance matchers use machine learning methods. Supervised learning systems achieve good performance by training on significant amounts of manually labeled samples. To alleviate the labeling effort, this paper presents a minimally supervised instance matching approach that is able to deliver competitive performance using only 2% training data and little parameter tuning. As a first step, the classifier is trained in an ensemble setting using boosting. Iterative semi-supervised learning is used to improve the performance of the boosted classifier even further, by re-training it on the most confident samples labeled in the current iteration. Empirical evaluations on a suite of six publicly available benchmarks show that the proposed system outcompetes optimization-based minimally supervised approaches in 1-7 iterations. The system’s average F-Measure is shown to be within 2.5% of that of recent supervised systems that require more training samples for effective performance.

After that, Michael Röder will present his paper “Detecting Similar Linked Datasets Using Topic Modelling” that has been accepted by the upcoming ESWC 2016 [PDF].

Abstract

The Web of data is growing continuously with respect to both the size and number of the datasets published. Porting a dataset to five-star Linked Data however requires the publisher of this dataset to link it with the already available linked datasets. Given the size and growth of the Linked Data Cloud, the current mostly manual approach used for detecting relevant datasets for linking is obsolete. We study the use of topic modelling for dataset search experimentally and present TAPIOCA, a linked dataset search engine that provides data publishers with similar existing datasets automatically. Our search engine uses a novel approach for determining the topical similarity of datasets. This approach relies on probabilistic topic modelling to determine related datasets by relying solely on the metadata of datasets. We evaluate our approach on a manually created gold standard and with a user study. Our evaluation shows that our algorithm outperforms a set of comparable baseline algorithms including standard search engines significantly by 6% F1-score. Moreover, we show that it can be used on a large real world dataset with a comparable performance.

About the AKSW Colloquium

This event is part of a series of events about Semantic Web technology. Please see http://wiki.aksw.org/Colloquium for further information about previous and future events. As always, Bachelor and Master students are able to get points for attendance and there is complimentary coffee and cake after the session.