Preface While more and more semantic data is published on the Web, the question of how typical Web users can access this body of knowledge becomes of cru- cial importance. Therefore there is a growing amount of research on interaction paradigms that allow end users to profit from the expressive power of Semantic Web standards while at the same time hiding the complexity behind an intuitive and easy-to-use interface. These paradigms range from keyword search, faceted browsing and exploration to natural language question answering. Keyword-based semantic search (e.g. provided by Swoogle1 and Watson2 ) suffice for simple information lookup. However, keyword queries constitute an ambiguous and impoverished representation of an information need and do not fully exploit the expressive power of Semantic Web datamodels and query lan- guages. Explicit formal queries, on the other hand, allow the user to exploit the full power and expressiveness of the Semantic Web standards. But they require schema knowledge and query language expertise, thus are not suitable for naive users. Faceted browsing interfaces (e.g. Ontogator [16], mSpace [17], and BrowseRDF [14]), in contrast, do not require domain knowledge or exper- tise in Semantic Web languages, rather they allow users to navigate through the dataset and thereby explore its content. However, faceted browsing is often domain-dependent. Also, in case the user has a clear information need, it is te- dious to search for the answer manually, not knowing where exactly to look for it. Similarly, graph visulatization (e.g. IsaViz3 , [13]) provides an intuitive access to understanding semantic data, but often does not scale to large datasets and is not suitable for searching for an answer to a particular question. In order to precisely answer particular questions, a lot of research has been conducted on natural language interfaces (see for instance [4], [5, 6], [7], and [3]), which allow users to express arbitrarily complex information needs in an intuitive fashion. They combine progress in the areas of question answering from textual data [8] and natural language interfaces to databases [9]. The key challenges lie in trans- lating these information needs into a form such that they can be evaluated using standard Semantic Web query processing and inferencing techniques, as well as in scaling question answering approaches to Linked Data. Despite different goals and different kinds of interaction, the main challenge involved in interacting with Linked Data is the same for all approaches: dealing with a heterogeneous, distributed and very large set of highly interconnected data. The availability of such an amount of open and structured data has no precedents in computer science and approaches that can deal with the specific character of Linked Data are urgently needed. 1 http://swoogle.umbc.edu/ 2 http://kmi-web05.open.ac.uk/WatsonWUI/ 3 http://www.w3.org/2001/11/IsaViz/ III The Workshop Interacting with Linked Data (ILD) is the second in a series of workshops exploring approaches towards a powerful and intuitive interaction with Linked Data. While the first workshop4 focused on question answering, the scope of ILD 2012 is now broader, including other paradigms for interacting with Linked Data. The goal of ILD is to bring together research and expertise from different communities, including NLP, HCI, Semantic Web and Databases, and to encourage communication across interaction paradigms. To this end, we issued a call for papers on the following topics: – Question answering and natural language interfaces to Linked Data – HCI and Linked Data – Faceted browsing and exploration – New interaction metaphors for Linked Data – Multimodal interfaces to Linked Data – Disambiguation and inferencing across multiple sources and domains – Natural language generation – Discovery on the fly of relevant Linked Data sources – Efficiency and performance aspects – Dealing with data and schema heterogeneity – Summarization and aggregation – Providing justifications of answers and conveying trust – Personalization in accessing Linked Data – User feedback and interaction – Habitability and usability aspects We received 11 submissions; to each of them three reviewers were assigned. On the basis of their reviews, six full papers were accepted for presentations. In addition, three papers were included as demo presentations. Accompanying the workshop, we set up the second open challenge on Ques- tion Answering over Linked Data (QALD-2). It follows the first challenge (QALD- 1) in aiming at facilitating the comparison between different question answering approaches and systems, and at developing the datasets needed for a standard evaluation benchmark for semantic question answering systems that focus on the ability to solve open-ended real life problems over real-world datasets. As part of this challenge, two independent datasets have been provided: DBpedia 3.7 and an udpated RDF export of MusicBrainz – together with 100 training questions for each dataset, annotated with SPARQL queries and corresponding answers, and 100 test questions for DBpedia as well as 55 test questions for MusicBrainz. All questions were designed to represent information needs of different complex- ity that real end users would ask. The datasets as well as all training and test questions can be accessed from the workshop website: http://www.sc.cit-ec.uni-bielefeld.de/ild 4 1st Workshop on Question Answering Over Linked Data (QALD-1) at ESWC 2011: http://www.sc.cit-ec.uni-bielefeld.de/qald IV The main goal of the challenge was to get a picture of the strengths, capabili- ties and current shortcomings of question answering systems, as well as to gain insight into how question answering approaches can deal with the fact that the amount of RDF data available on the Web is huge and that this data is dis- tributed and heterogeneous with respect to the vocabularies and schemas used. Five question answering systems participated in the test phase of the challenge, all reporting on the DBpedia question set (where Alexandria used German trans- lations of the questions and extracted the answers from Freebase, thus suffering from data mismatches). The results of our online evaluation are given in Table 1. Alexandria, SemSeK, and QAKiS are described in papers in these proceedings; MHE was developed by Marek Ciglan5 at the Institute of Informatics at the Slovak Academy of Sciences. total answered right partially right precision recall f-measure SemSeK 100 80 32 7 0.44 0.48 0.46 Alexandria 100 25 5 10 0.43 0.46 0.45 MHE 100 97 30 12 0.36 0.4 0.38 QAKiS 100 35 11 4 0.39 0.37 0.38 Table 1. QALD-2 results on DBpedia With the ILD workshop and the accompanying open challenge we hope to establish a series of workshops that aim at coupling current research on interac- tion paradigms for accessing Linked Data with open challenges that benchmark question answering approaches and thereby evaluate their success in providing an easy and intuitive interface to the Semantic Web. May 2012 Christina Unger Philipp Cimiano Vanessa Lopez Enrico Motta Paul Buitelaar Richard Cyganiak (Organizing Committee ILD 2012) 5 http://ups.savba.sk/~marek/ V References 1. Kaufmann, E., Bernstein, A.: How Useful Are Natural Language Interfaces to the Semantic Web for Casual End-Users?. In: Proceedings of the Joint International and Asian Semantic Web Conference (ISWC/ASWC), pp. 281–294, 2007 2. Kaljurand, K.: ACE View – An Ontology and Rule Editor based on Controlled English. In: Proceedings of the International Semantic Web Conference (ISWC), Poster and Demo Proceedings, 2008 3. Cimiano, P., Haase, P., Heizmann, J., Mantel, M., Studer, R.: Towards portable natural language interfaces to knowledge bases – The case of the ORAKEL system. Data Knowl. Eng. 65:2, pp. 325–354, 2008 4. Bernstein, A., Kaufmann, E., Göhring, A., Kiefer, C.: Querying Ontologies: A Controlled English Interface for End-Users. In: Proceedings of the International Semantic Web Conference (ISWC), pp. 112–126, 2005 5. Lopez, V., Nikolov, A., Sabou, M., Uren, V., Motta, E., D’Aquin, M.: Scaling up Question-Answering to Linked Data. In: Proceedings of the 17th International Con- ference on Knowledge Management and Knowledge Engineering (EKAW), 2010 6. Lopez, V., Uren, V., Sabou, M., Motta, E.: Cross ontology query answering on the semantic web: an initial evaluation. In: Proceedings of International Conference on Knowledge Capture (K-CAP), pp. 17–24, 2009 7. Tran, T., Wang, H., Rudolph, S., Cimiano, P.: Top-k Exploration of Query Candi- dates for Efficient Keyword Search on Graph-Shaped (RDF) Data. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 405–416, 2009 8. Strzalkowsi, T., Harabagiu, S.: Advances in Open Domain Question Answering. Springer, 2006 9. Minock, M.: C-Phrase: A system for building robust natural language interfaces to databases. Data Knowl. Eng. 69:3, pp. 290–302, 2010 10. Damljanovic, D., Agatonovic, M., Cunningham, H.: Natural Language Interfaces to Ontologies: Combining Syntactic Analysis and Ontology-based Lookup through the User Interaction. In: Proceedings of the 7th Extended Semantic Web Conference (ESWC 2010), Heraklion, Greece, May 31-June 3, 2010, Springer Verlag, 2010 11. Lopez, V., Motta, E., Uren, V.: PowerAqua: Fishing the Semantic Web. In: Proceedings of the 3rd European Semantic Web Conference, Budva, Montenegro, 2006 12. Lopez, V., Sabou, M., Uren, V., Motta, E.: = Cross-Ontology Question Answering on the Semantic Web: an initial evaluation. In: Proceedings of the Knowledge Capture Conference 2009, California, 2009 13. Jacobson, K., Sandler, M.: Interacting With Linked Data About Music. In: Pro- ceedings of the WebSci’09: Society On-Line, 18-20 March 2009, Athens, Greece, 2009 14. Oren, E., Delbru, R., Decker, S.: Extending faceted navigation for RDF data. In: I. Cruz et al.: ISWC 2006. LNCS 4273, pp. 559–572, 2006 15. Hildebrand, M., van Ossenbruggen, J., Hardman, L.: /facet: A browser for hetero- geneous Semantic Web repositories. In: I. Cruz et al.: ISWC 2006. LNCS 4273, pp. 272–285, 2006 16. Hyvönen, E., Saarela, S., Viljanen, K.: Ontogator: Combining view- and ontology- based search with semantic browsing. In: Proc. of XML Finland, 2003 17. schraefel, m., Wilson, M., Russell, A., Smith, D. A.: mSpace: Improving information access to multimedia domains with multimodal exploratory search. Comm. of the ACM 49:4, 2006