With the rise of linked data, more and more semantically described information is being published online according to the principles and technologies of the Semantic Web (especially, RDF and SPARQL). The use of such standard technologies means that this data should be exploitable, integrable and reusable straight away. However, once a potentially interesting dataset has been discovered, significant efforts are currently required in order to understand its schema, its content, the way to query it and what it can answer. In this paper, we propose a method and a tool to automatically discover questions that can be answered by an RDF dataset. We use formal concept analysis to build a hierarchy of meaningful sets of entities from a dataset. These sets of entities represent answers, which common characteristics represent the clauses of the corresponding questions. This hierarchy can then be used as a querying interface, proposing questions of varying levels of granularity and specificity to the user. A major issue is however that thousands of questions can be included in this hierarchy. Based on an empirical analysis and using metrics inspired both from formal concept analysis and from ontology summarization, we devise an approach for identifying relevant questions to act as a starting point to the navigation in the question hierarchy.

@inproceedings{daquin2011extracting, author = {d'Aquin, Mathieu and Motta, Enrico}, title = {Extracting relevant questions to an RDF dataset using formal concept analysis}, booktitle = {Proceedings of the sixth international conference on Knowledge capture}, publisher = {ACM}, address = {New York, NY, USA}, year = {2011}, pages = {121--128}, url = {http://doi.acm.org/10.1145/1999676.1999698}, doi = {10.1145/1999676.1999698}, isbn = {978-1-4503-0396-5}, keywords = {rdf, concept, formal, semantic, analysis, fca, ontology, web}, abstract = {With the rise of linked data, more and more semantically described information is being published online according to the principles and technologies of the Semantic Web (especially, RDF and SPARQL). The use of such standard technologies means that this data should be exploitable, integrable and reusable straight away. However, once a potentially interesting dataset has been discovered, significant efforts are currently required in order to understand its schema, its content, the way to query it and what it can answer. In this paper, we propose a method and a tool to automatically discover questions that can be answered by an RDF dataset. We use formal concept analysis to build a hierarchy of meaningful sets of entities from a dataset. These sets of entities represent answers, which common characteristics represent the clauses of the corresponding questions. This hierarchy can then be used as a querying interface, proposing questions of varying levels of granularity and specificity to the user. A major issue is however that thousands of questions can be included in this hierarchy. Based on an empirical analysis and using metrics inspired both from formal concept analysis and from ontology summarization, we devise an approach for identifying relevant questions to act as a starting point to the navigation in the question hierarchy.} }

%0 = inproceedings %A = d'Aquin, Mathieu and Motta, Enrico %B = Proceedings of the sixth international conference on Knowledge capture %C = New York, NY, USA %D = 2011 %I = ACM %T = Extracting relevant questions to an RDF dataset using formal concept analysis %U = http://doi.acm.org/10.1145/1999676.1999698

Abstract. While the increasing popularity of folksonomies has lead to a vast quantity of tagged data, resource retrieval in folksonomies is limited by being agnostic to the meaning (i.e., semantics) of tags. Our goal is to automatically enrich folksonomy tags (and implicitly the related resources) with formal semantics by associating them to relevant concepts defined in online ontologies. We introduce FLOR, a method that performs automatic folksonomy enrichment by combining knowledge from WordNet and online available ontologies. Experimentally testing FLOR, we found that it correctly enriched 72 % of 250 Flickr photos. 1

@inproceedings{angeletou2008semantically, author = {Angeletou, Sofia and Sabou, Marta and Motta, Enrico}, title = {Semantically enriching folksonomies with FLOR}, booktitle = {Proceedings of the CISWeb Workshop, located at the 5th European Semantic Web Conference ESWC 2008}, year = {2008}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.2569}, keywords = {ol_web2.0, ontology_learning, semantic_enrichment}, abstract = {Abstract. While the increasing popularity of folksonomies has lead to a vast quantity of tagged data, resource retrieval in folksonomies is limited by being agnostic to the meaning (i.e., semantics) of tags. Our goal is to automatically enrich folksonomy tags (and implicitly the related resources) with formal semantics by associating them to relevant concepts defined in online ontologies. We introduce FLOR, a method that performs automatic folksonomy enrichment by combining knowledge from WordNet and online available ontologies. Experimentally testing FLOR, we found that it correctly enriched 72 % of 250 Flickr photos. 1} }

%0 = inproceedings %A = Angeletou, Sofia and Sabou, Marta and Motta, Enrico %B = Proceedings of the CISWeb Workshop, located at the 5th European Semantic Web Conference ESWC 2008 %D = 2008 %T = Semantically enriching folksonomies with FLOR %U = http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.2569

Abstract. While the increasing popularity of folksonomies has lead to a vast quantity of tagged data, resource retrieval in folksonomies is limited by being agnostic to the meaning (i.e., semantics) of tags. Our goal is to automatically enrich folksonomy tags (and implicitly the related resources) with formal semantics by associating them to relevant concepts defined in online ontologies. We introduce FLOR, a method that performs automatic folksonomy enrichment by combining knowledge from WordNet and online available ontologies. Experimentally testing FLOR, we found that it correctly enriched 72 % of 250 Flickr photos. 1

@inproceedings{Angeletou08semanticallyenriching, author = {Angeletou, Sofia and Sabou, Marta and Motta, Enrico}, title = {Semantically enriching folksonomies with FLOR}, booktitle = {In Proc of the 5th ESWC. workshop: Collective Intelligence & the Semantic Web}, year = {2008}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.2569}, keywords = {tagging, taggingsurvey, ontologies, semantic, folksonomy}, abstract = {Abstract. While the increasing popularity of folksonomies has lead to a vast quantity of tagged data, resource retrieval in folksonomies is limited by being agnostic to the meaning (i.e., semantics) of tags. Our goal is to automatically enrich folksonomy tags (and implicitly the related resources) with formal semantics by associating them to relevant concepts defined in online ontologies. We introduce FLOR, a method that performs automatic folksonomy enrichment by combining knowledge from WordNet and online available ontologies. Experimentally testing FLOR, we found that it correctly enriched 72 % of 250 Flickr photos. 1} }

%0 = inproceedings %A = Angeletou, Sofia and Sabou, Marta and Motta, Enrico %B = In Proc of the 5th ESWC. workshop: Collective Intelligence & the Semantic Web %D = 2008 %T = Semantically enriching folksonomies with FLOR %U = http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.2569

While tags in collaborative tagging systems serve primarily an indexing purpose, facilitating search and navigation of resources, the use of the same tags by more than one individual can yield a collective classification schema. We present an approach for making explicit the semantics behind the tag space in social tagging systems, so that this collaborative organization can emerge in the form of groups of concepts and partial ontologies. This is achieved by using a combination of shallow pre-processing strategies and statistical techniques together with knowledge provided by ontologies available on the semantic web. Preliminary results on the del.icio.us and Flickr tag sets show that the approach is very promising: it generates clusters with highly related tags corresponding to concepts in ontologies and meaningful relationships among subsets of these tags can be identified.

@inproceedings{specia2007integrating, author = {Specia, Lucia and Motta, Enrico}, title = {Integrating Folksonomies with the Semantic Web}, series = {Lecture Notes in Computer Science}, publisher = {Springer Berlin / Heidelberg}, year = {2007}, volume = {4519/2007}, pages = {624-639}, keywords = {ol_web2.0, methods_concepts, toread_dbe, toread, emergentsemantics_evidence}, abstract = {While tags in collaborative tagging systems serve primarily an indexing purpose, facilitating search and navigation of resources, the use of the same tags by more than one individual can yield a collective classification schema. We present an approach for making explicit the semantics behind the tag space in social tagging systems, so that this collaborative organization can emerge in the form of groups of concepts and partial ontologies. This is achieved by using a combination of shallow pre-processing strategies and statistical techniques together with knowledge provided by ontologies available on the semantic web. Preliminary results on the del.icio.us and Flickr tag sets show that the approach is very promising: it generates clusters with highly related tags corresponding to concepts in ontologies and meaningful relationships among subsets of these tags can be identified.} }

%0 = inproceedings %A = Specia, Lucia and Motta, Enrico %D = 2007 %I = Springer Berlin / Heidelberg %T = Integrating Folksonomies with the Semantic Web

While tags in collaborative tagging systems serve primarily an indexing purpose, facilitating search and navigation of resources, the use of the same tags by more than one individual can yield a collective classification schema. We present an approach for making explicit the semantics behind the tag space in social tagging systems, so that this collaborative organization can emerge in the form of groups of concepts and partial ontologies. This is achieved by using a combination of shallow pre-processing strategies and statistical techniques together with knowledge provided by ontologies available on the semantic web. Preliminary results on the del.icio.us and Flickr tag sets show that the approach is very promising: it generates clusters with highly related tags corresponding to concepts in ontologies and meaningful relationships among subsets of these tags can be identified.

@inbook{specia2007integrating, author = {Specia, Lucia and Motta, Enrico}, title = {Integrating Folksonomies with the Semantic Web}, series = {Lecture Notes in Computer Science}, publisher = {Springer Berlin / Heidelberg}, year = {2007}, volume = {4519/2007}, pages = {624-639}, keywords = {ol_web2.0, toread}, abstract = {While tags in collaborative tagging systems serve primarily an indexing purpose, facilitating search and navigation of resources, the use of the same tags by more than one individual can yield a collective classification schema. We present an approach for making explicit the semantics behind the tag space in social tagging systems, so that this collaborative organization can emerge in the form of groups of concepts and partial ontologies. This is achieved by using a combination of shallow pre-processing strategies and statistical techniques together with knowledge provided by ontologies available on the semantic web. Preliminary results on the del.icio.us and Flickr tag sets show that the approach is very promising: it generates clusters with highly related tags corresponding to concepts in ontologies and meaningful relationships among subsets of these tags can be identified.} }

%0 = inbook %A = Specia, Lucia and Motta, Enrico %D = 2007 %I = Springer Berlin / Heidelberg %T = Integrating Folksonomies with the Semantic Web

While tags in collaborative tagging systems serve primarily an indexing purpose, facilitating search and navigation of resources, the use of the same tags by more than one individual can yield a collective classification schema. We present an approach for making explicit the semantics behind the tag space in social tagging systems, so that this collaborative organization can emerge in the form of partial ontologies. This is achieved by using a combination of shallow pre-processing strategies and statistical techniques together with knowledge provided by ontologies available on the semantic web. Preliminary results on the Del.icio.us and Flickr tag sets showed that the approach is very promising: it generates clusters with highly related tags corresponding to concepts in ontologies, and meaningful relationships among subsets of these tags can be identified.

@inproceedings{ieKey, author = {Specia, Lucia and Motta, Enrico}, title = {Integrating Folksonomies with the Semantic Web}, editor = {Franconi, Enrico and Kifer, Michael and May, Wolfgang}, booktitle = {Proceedings of the European Semantic Web Conference (ESWC2007)}, series = {LNCS}, publisher = {Springer-Verlag}, address = {Berlin Heidelberg, Germany}, year = {2007}, volume = {4519}, pages = {624-639}, url = {http://www.eswc2007.org/pdf/eswc07-specia.pdf}, keywords = {2007, semantic, folksonomy, eswc, web}, abstract = {While tags in collaborative tagging systems serve primarily an indexing purpose, facilitating search and navigation of resources, the use of the same tags by more than one individual can yield a collective classification schema. We present an approach for making explicit the semantics behind the tag space in social tagging systems, so that this collaborative organization can emerge in the form of partial ontologies. This is achieved by using a combination of shallow pre-processing strategies and statistical techniques together with knowledge provided by ontologies available on the semantic web. Preliminary results on the Del.icio.us and Flickr tag sets showed that the approach is very promising: it generates clusters with highly related tags corresponding to concepts in ontologies, and meaningful relationships among subsets of these tags can be identified.} }

%0 = inproceedings %A = Specia, Lucia and Motta, Enrico %B = Proceedings of the European Semantic Web Conference (ESWC2007) %C = Berlin Heidelberg, Germany %D = 2007 %I = Springer-Verlag %T = Integrating Folksonomies with the Semantic Web %U = http://www.eswc2007.org/pdf/eswc07-specia.pdf

@inproceedings{DBLP:conf/esws/LeiSLZUM06, author = {Lei, Yuangui and Sabou, Marta and Lopez, Vanessa and Zhu, Jianhan and Uren, Victoria and Motta, Enrico}, title = {An Infrastructure for Acquiring High Quality Semantic Metadata.}, booktitle = {ESWC}, year = {2006}, pages = {230-244}, keywords = {european, proceedings, 2006, semantic, conference, learning, eswc, ontology, web} }

%0 = inproceedings %A = Lei, Yuangui and Sabou, Marta and Lopez, Vanessa and Zhu, Jianhan and Uren, Victoria and Motta, Enrico %B = ESWC %D = 2006 %T = An Infrastructure for Acquiring High Quality Semantic Metadata.

@inproceedings{DBLP:conf/esws/LopezMU06, author = {Lopez, Vanessa and Motta, Enrico and Uren, Victoria}, title = {PowerAqua: Fishing the Semantic Web.}, booktitle = {ESWC}, year = {2006}, pages = {393-410}, keywords = {searching, european, proceedings, 2006, semantic, conference, querying, eswc, and, web} }

%0 = inproceedings %A = Lopez, Vanessa and Motta, Enrico and Uren, Victoria %B = ESWC %D = 2006 %T = PowerAqua: Fishing the Semantic Web.