diff --git a/aksw.bib b/aksw.bib index d5c8c43..a08d3a9 100644 --- a/aksw.bib +++ b/aksw.bib @@ -12325,4 +12325,74 @@ @InProceedings{stadler2023-kgcw-challenge url = {https://ceur-ws.org/Vol-3471/paper12.pdf}, } +@InProceedings{stadler2022-lsq-framework, + author = {Claus Stadler and Muhammad Saleem and Axel-Cyrille Ngonga Ngomo}, + booktitle = {6th Workshop on Storing, Querying and Benchmarking Knowledge Graphs @ ISWC 2022}, + title = {{LSQ} Framework: The {LSQ} Framework for {SPARQL} Query Log Processing}, + year = {2022}, + series = {{CEUR} Workshop Proceedings}, + volume = {3279}, + abstract = {The Linked SPARQL Queries (LSQ) datasets contain real-world SPARQL queries collected from the query logs of the publicly available SPARQL endpoints. In LSQ, each SPARQL query is represented as RDF with various structural and data-driven features attached. In this paper, we present the LSQ Java framework for creating rich knowledge graphs from SPARQL query logs. The framework is able to RDFize SPARQL query logs, which are available in different formats, in a scalable way. Furthermore, the framework offers a set of static and dynamic enrichers. Static enrichers derive information from the queries, such as their number of basic graph patterns and projected variables or even a full SPIN model. Dynamic enrichment involves additional resources. For instance, the benchmark enricher executes queries against a SPARQL endpoint and collects query execution times and result set sizes. This framework has already been used to convert query logs of 27 public SPARQL endpoints, representing 43.95 million executions of 11.56 million unique SPARQL queries. The LSQ queries have been used in many use cases such as benchmarking based on real-world SPARQL queries, SPARQL adoption, caching, query optimization, useability analysis, and meta-querying. Realization of LSQ required devising novel software components to (a) improve scalability of RDF data processing with the Apache Spark Big Data framework and (b) ease operations of complex RDF data models such as controlled skolemization. Following the spirit of OpenSource software development and the "don’t repeat yourself" (DRY) paradigm, the work on the LSQ framework also resulted in contributions to Apache Jena in order to make these improvements readily available outside of the LSQ context.}, + keywords = {group_aksw es sys:relevantFor:infai stadler saleem ngonga dice}, + url = {https://ceur-ws.org/Vol-3279/paper4.pdf}, +} + +@InProceedings{graux2020-minds, + author = {Graux, Damien and Sejdiu, Gezim and Stadler, Claus and Napolitano, Giulio and Lehmann, Jens}, + booktitle = {Semantic Systems. In the Era of Knowledge Graphs}, + title = {MINDS: A Translator to Embed Mathematical Expressions Inside SPARQL Queries}, + year = {2020}, + address = {Cham}, + editor = {Blomqvist, Eva and Groth, Paul and de Boer, Victor and Pellegrini, Tassilo and Alam, Mehwish and K{\"a}fer, Tobias and Kieseberg, Peter and Kirrane, Sabrina and Mero{\~{n}}o-Pe{\~{n}}uela, Albert and Pandit, Harshvardhan J.}, + pages = {104--117}, + publisher = {Springer International Publishing}, + abstract = {The recent deployments of semantic web tools and the expansion of available linked datasets have given users the opportunity of building increasingly complex applications. These emerging use cases often require queries containing mathematical formulas such as euclidean distances or unit conversions. Currently, the latest SPARQL standard (version 1.1) only embeds basic math operators. Thus, to address this shortcoming, some popular SPARQL evaluators provide built-in tools to cover specific needs; however, such tools are not standard yet. To offer users a more generic solution, we propose and share MINDS, a translator of mathematical expressions into SPARQL-compliant bindings which can be understood by any evaluator. MINDS thereby facilitates the query design whenever mathematical computations are needed in a SPARQL query.}, + isbn = {978-3-030-59833-4}, + keywords = {mole group_aksw sys:relevantFor:infai stadler lehmann graux}, + url = {https://svn.aksw.org/papers/2020/semantics_minds/public.pdf}, +} + +@InBook{Ibanez2023-qrowd, + author = {Ib{\'a}{\~{n}}ez, Luis-Daniel and Maddalena, Eddy and Gomer, Richard and Simperl, Elena and Zeni, Mattia and Bignotti, Enrico and Chenu-Abente, Ronald and Giunchiglia, Fausto and Westphal, Patrick and Stadler, Claus and Dziwis, Gordian and Lehmann, Jens and Yumusak, Semih and Voigt, Martin and Sanguino, Maria-Angeles and Villaz{\'a}n, Javier and Ruiz, Ricardo and Pariente-Lobo, Tomas}, + editor = {Singh, Pradeep Kumar and Paprzycki, Marcin and Essaaidi, Mohamad and Rahimi, Shahram}, + pages = {285--321}, + publisher = {Springer International Publishing}, + title = {QROWD---A Platform for Integrating Citizens in Smart City Data Analytics}, + year = {2023}, + address = {Cham}, + isbn = {978-3-031-08815-5}, + abstract = {Optimizing mobility services is one of the greatest challenges Smart Cities face in their efforts to improve residents' wellbeing and reduce {\$}{\$}{\backslash}text {\{}CO{\}}{\_}{\{}2{\}}{\$}{\$}emissions. The advent of IoT has created unparalleled opportunities to collect large amounts of data about how people use transportation. This data could be used to ascertain the quality and reach of the services offered and to inform future policy---provided cities have the capabilities to process, curate, integrate and analyse the data effectively. At the same time, to be truly `Smart', cities need to ensure that the data-driven decisions they make reflect the needs of their citizens, create feedback loops, and widen participation. In this chapter, we introduce QROWD, a data integration and analytics platform that seamlessly integrates multiple data sources alongside human, social and computational intelligence to build hybrid, automated data-centric workflows. By doing so, QROWD applications can take advantage of the best of both worlds: the accuracy and scale of machine computation, and the skills, knowledge and expertise of people. We present the architecture and main components of the platform, as well as its usage to realise two mobility use cases: estimating the modal split, which refers to trips people take that involve more than one type of transport, and urban auditing.}, + booktitle = {Sustainable Smart Cities: Theoretical Foundations and Practical Considerations}, + doi = {10.1007/978-3-031-08815-5_16}, + keywords = {sys:relevantFor:infai mole westphal stadler dziwis lehmann}, + url = {https://svn.aksw.org/papers/2022/SSC_qrowd/public.pdf}, +} + +@InProceedings{wenige2021open, + author = {Lisa Wenige and Claus Stadler and Michael Martin and Richard Figura and Robert Sauter and Christopher W. Frank}, + title = {Open Data and the Status Quo -- A Fine-Grained Evaluation Framework for Open Data Quality and an Analysis of Open Data portals in Germany}, + year = {2021}, + archiveprefix = {arXiv}, + eprint = {2106.09590}, + keywords = {group_aksw sys:relevantFor:infai wenige stadler martin es}, + primaryclass = {cs.IR}, + url = {https://arxiv.org/pdf/2106.09590.pdf}, +} + +@Article{stadler2022-lsq20, + author = {Stadler, Claus and Saleem, Muhammad and Mehmood, Qaiser and Buil-Aranda, Carlos and Dumontier, Michel and Hogan, Aidan and Ngonga Ngomo, Axel-Cyrille}, + journal = {Semantic Web}, + title = {{LSQ} 2.0: A linked dataset of {SPARQL} query logs}, + year = {2022}, + issn = {1570-0844}, + month = nov, + pages = {1--23}, + abstract = {We present the Linked SPARQL Queries (LSQ) dataset, which currently describes 43.95 million executions of 11.56 million unique SPARQL queries extracted from the logs of 27 different endpoints. The LSQ dataset provides RDF descriptions of each such query, which are indexed in a public LSQ endpoint, allowing interested parties to find queries with the characteristics they require. We begin by describing the use cases envisaged for the LSQ dataset, which include applications for research on common features of queries, for building custom benchmarks, and for designing user interfaces. We then discuss how LSQ has been used in practice since the release of four initial SPARQL logs in 2015. We discuss the model and vocabulary that we use to represent these queries in RDF. We then provide a brief overview of the 27 endpoints from which we extracted queries in terms of the domain to which they pertain and the data they contain. We provide statistics on the queries included from each log, including the number of query executions, unique queries, as well as distributions of queries for a variety of selected characteristics. We finally discuss how the LSQ dataset is hosted and how it can be accessed and leveraged by interested parties for their use cases.}, + doi = {10.3233/SW-223015}, + editor = {Cudré-Mauroux, Philippe}, + keywords = {group_aksw sys:relevantFor:infai stadler saleem ngonga es dice}, + publisher = {IOS Press}, + url = {https://www.semantic-web-journal.net/system/files/swj3015.pdf}, +} + @Comment{jabref-meta: databaseType:bibtex;}