Lorenz Bühmann

Template-based question answering over RDF data

As an increasing amount of RDF data is published as Linked Data, intuitive ways of accessing this data become more and more important. Question answering approaches have been proposed as a good compromise between intuitiveness and expressivity. Most question answering systems translate questions into triples which are matched against the RDF data to retrieve an answer, typically relying on some similarity metric. However, in many cases, triples do not represent a faithful representation of the semantic structure of the natural language question, with the result that more expressive queries can not be answered. To circumvent this problem, we present a novel approach that relies on a parse of the question to produce a SPARQL template that directly mirrors the internal structure of the question. This template is then instantiated using statistical entity identification and predicate detection. We show that this approach is competitive and discuss cases of questions that can be answered with our approach but not with competing approaches.

User-driven quality evaluation of DBpedia

Linked Open Data (LOD) comprises of an unprecedented volume of structured datasets on the Web. However, these datasets are of varying quality ranging from extensively curated datasets to crowdsourced and even extracted data of relatively low quality. We present a methodology for assessing the quality of linked data resources, which comprises of a manual and a semi-automatic process. The first phase includes the detection of common quality problems and their representation in a quality problem taxonomy. In the manual process, the second phase comprises of the evaluation of a large number of individual resources, according to the quality problem taxonomy via crowdsourcing. This process is accompanied by a tool wherein a user assesses an individual resource and evaluates each fact for correctness. The semi-automatic process involves the generation and verification of schema axioms. We report the results obtained by applying this methodology to DBpedia. We identified 17 data quality problem types and 58 users assessed a total of 521 resources. Overall, 11.93% of the evaluated DBpedia triples were identified to have some quality issues. Applying the semi-automatic component yielded a total of 222,982 triples that have a high probability to be incorrect. In particular, we found that problems such as object values being incorrectly extracted, irrelevant extraction of information and broken links were the most recurring quality problems. With this study, we not only aim to assess the quality of this sample of DBpedia resources but also adopt an agile methodology to improve the quality in future versions by regularly providing feedback to the DBpedia maintainers.

Class expression learning for ontology engineering

Abstract: While the number of knowledge bases in the Semantic Web increases, the maintenance and creation of ontology schemata still remain a challenge. In particular creating class expressions constitutes one of the more demanding aspects of ontology engineering. In this article we describe how to adapt a semi-automatic method for learning OWL class expressions to the ontology engineering use case. Specifically, we describe how to extend an existing learning algorithm for the class learning problem. We perform rigorous performance optimization of the underlying algorithms for providing instant suggestions to the user. We also present two plugins, which use the algorithm, for the popular Protege and OntoWiki ontology editors and provide a preliminary evaluation on real ontologies.

Managing the life-cycle of linked data with the LOD2 stack

The LOD2 Stack is an integrated distribution of aligned tools which support the whole life cycle of Linked Data from extraction, authoring/creation via enrichment, interlinking, fusing to maintenance. The LOD2 Stack comprises new and substantially extended existing tools from the LOD2 project partners and third parties. The stack is designed to be versatile; for all functionality we define clear interfaces, which enable the plugging in of alternative third-party implementations. The architecture of the LOD2 Stack is based on three pillars: ( 1 ) Software integration and deployment using the Debian packaging system. ( 2 ) Use of a central SPARQL endpoint and standardized vocabularies for knowledge base access and integration between the different tools of the LOD2 Stack. ( 3 ) Integration of the LOD2 Stack user interfaces based on REST enabled Web Applications. These three pillars comprise the methodological and technological framework for integrating the very heterogeneous LOD2 Stack components into a consistent framework. In this article we describe these pillars in more detail and give an overview of the individual LOD2 Stack components. The article also includes a description of a real-world usage scenario in the publishing domain.

AutoSPARQL: let users query your knowledge base

An advantage of Semantic Web standards like RDF and OWL is their flexibility in modifying the structure of a knowledge base. To turn this flexibility into a practical advantage, it is of high importance to have tools and methods, which offer similar flexibility in exploring information in a knowledge base. This is closely related to the ability to easily formulate queries over those knowledge bases. We explain benefits and drawbacks of existing techniques in achieving this goal and then present the QTL algorithm, which fills a gap in research and practice. It uses supervised machine learning and allows users to ask queries without knowing the schema of the underlying knowledge base beforehand and without expertise in the SPARQL query language. We then present the AutoSPARQL user interface, which implements an active learning approach on top of QTL. Finally, we evaluate the approach based on a benchmark data set for question answering over Linked Data.

ORE - a tool for repairing and enriching knowledge bases

While the number and size of Semantic Web knowledge bases increases, their maintenance and quality assurance are still difficult. In this article, we present ORE, a tool for repairing and enriching OWL ontologies. State-of the-art methods in ontology debugging and supervised machine learning form the basis of ORE and are adapted or extended so as to work well in practice. ORE supports the detection of a variety of ontology modelling problems and guides the user through the process of resolving them. Furthermore, the tool allows to extend an ontology through (semi-)automatic supervised learning. A wizardlike process helps the user to resolve potential issues after axioms are added.

Sorry, i don't speak SPARQL: translating SPARQL queries into natural language

Over the past years, Semantic Web and Linked Data technologies have reached the backend of a considerable number of applications. Consequently, large amounts of RDF data are constantly being made available across the planet. While experts can easily gather information from this wealth of data by using the W3C standard query language SPARQL, most lay users lack the expertise necessary to proficiently interact with these applications. Consequently, non-expert users usually have to rely on forms, query builders, question answering or keyword search tools to access RDF data. However, these tools have so far been unable to explicate the queries they generate to lay users, making it difficult for these users to i) assess the correctness of the query generated out of their input, and ii) to adapt their queries or iii) to choose in an informed manner between possible interpretations of their input. This paper addresses this drawback by presenting SPARQL2NL, a generic approach that allows verbalizing SPARQL queries, i.e., converting them into natural language. Our framework can be integrated into applications where lay users are required to understand SPARQL or to generate SPARQL queries in a direct (forms, query builders) or an indirect (keyword search, question answering) manner. We evaluate our approach on the DBpedia question set provided by QALD-2 within a survey setting with both SPARQL experts and lay users. The results of the 115 filled surveys show that SPARQL2NL can generate complete and easily understandable natural language descriptions. In addition, our results suggest that even SPARQL experts can process the natural language representation of SPARQL queries computed by our approach more efficiently than the corresponding SPARQL queries. Moreover, non-experts are enabled to reliably understand the content of SPARQL queries.

Universal OWL axiom enrichment for large knowledge bases

The Semantic Web has seen a rise in the availability and usage of knowledge bases over the past years, in particular in the Linked Open Data initiative. Despite this growth, there is still a lack of knowledge bases that consist of high quality schema information and instance data adhering to this schema. Several knowledge bases only consist of schema information, while others are, to a large extent, a mere collection of facts without a clear structure. The combination of rich schema and instance data would allow powerful reasoning, consistency checking, and improved querying possibilities as well as provide more generic ways to interact with the underlying data. In this article, we present a light-weight method to enrich knowledge bases accessible via SPARQL endpoints with almost all types of OWL 2 axioms. This allows to semi-automatically create schemata, which we evaluate and discuss using DBpedia.

Real-Time RDF Extraction from Unstructured Data Streams

The vision behind the Web of Data is to extend the current document-oriented Web with machine-readable facts and structured data, thus creating a representation of general knowledge. However, most of the Web of Data is limited to being a large compendium of encyclopedic knowledge describing entities. A huge challenge, the timely and massive extraction of RDF facts from unstructured data, has remained open so far. The availability of such knowledge on the Web of Data would provide significant benefits to manifold applications including news retrieval, sentiment analysis and business intelligence. In this paper, we address the problem of the actuality of the Web of Data by presenting an approach that allows extracting RDF triples from unstructured data streams. We employ statistical methods in combination with deduplication, disambiguation and unsupervised as well as supervised machine learning techniques to create a knowledge base that reflects the content of the input streams. We evaluate a sample of the RDF we generate against a large corpus of news streams and show that we achieve a precision of more than 85%.

Pattern Based Knowledge Base Enrichment

Although an increasing number of RDF knowledge bases are published, many of those consist primarily of instance data and lack sophisticated schemata. Having such schemata allows more powerful querying, consistency checking and debugging as well as improved inference. One of the reasons why schemata are still rare is the effort required to create them. In this article, we propose a semi-automatic schemata construction approach addressing this problem: First, the frequency of axiom patterns in existing knowledge bases is discovered. Afterwards, those patterns are converted to SPARQL based pattern detection algorithms, which allow to enrich knowledge base schemata. We argue that we present the first scalable knowledge base enrichment approach based on real schema usage patterns. The approach is evaluated on a large set of knowledge bases with a quantitative and qualitative result analysis.