Abstract. Over the last decades, several billion Web pages have been made available on the Web. The ongoing transition from the current Web of unstructured data to the Web of Data yet requires scalable and accurate approaches for the extraction of structured data in RDF (Resource Description Framework) from these websites. One of the key steps towards extracting RDF from text is the disambiguation of named entities. While several approaches aim to tackle this problem, they still achieve poor accuracy. We address this drawback by presenting AGDIS-TIS, a novel knowledge-base-agnostic approach for named entity disambiguation. Our approach combines the Hypertext-Induced Topic Search (HITS) algorithm with label expansion strategies and string similarity measures. Based on this combination, AGDISTIS can efficiently detect the correct URIs for a given set of named entities within an input text. We evaluate our approach on eight different datasets against state-of-theart named entity disambiguation frameworks. Our results indicate that we outperform the state-of-the-art approach by up to 29% F-measure.

Abstract. Semantic Question Answering (SQA) removes two major access requirements to the Semantic Web: the mastery of a formal query language like SPARQL and knowledge of a specific vocabulary. Because of the complexity of natural language, SQA presents difficult challenges and many research opportunities. Instead of a shared effort, however, many essential components are redeveloped, which is an inefficient use of researcher's time and resources. This survey analyzes 62 different SQA systems, which are systematically and manually selected using predefined inclusion and exclusion criteria, leading to 72 selected publications out of 1960 candidates. We identify common challenges, structure solutions, and provide recommendations for future systems. This work is based on publications from the end of 2010 to July 2015 and is also compared to older but similar surveys.

No abstract

Hyper-relational knowledge graphs (KGs) (e.g., Wikidata) enable associating additional key-value pairs along with the main triple to disambiguate, or restrict the validity of a fact. In this work, we propose a message passing based graph encoder -STARE capable of modeling such hyper-relational KGs. Unlike existing approaches, STARE can encode an arbitrary number of additional information (qualifiers) along with the main triple while keeping the semantic roles of qualifiers and triples intact. We also demonstrate that existing benchmarks for evaluating link prediction (LP) performance on hyper-relational KGs suffer from fundamental flaws and thus develop a new Wikidata-based dataset -WD50K. Our experiments demonstrate that STARE based LP model outperforms existing approaches across multiple benchmarks. We also confirm that leveraging qualifiers is vital for link prediction with gains up to 25 MRR points compared to triple-based representations.

No abstract

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%.

Billions of facts pertaining to a multitude of domains are now availableon the Web as RDF data. However, accessing this data is stilla difficult endeavour for non-expert users. In order to melioratethe access to this data, approaches imposing minimal hurdles totheir users are required. Although many question answering systemsover Linked Data have being proposed, retrieving the desireddata is still significantly challenging. In addition, developing andevaluating question answering systems remains a very complex task.To overcome these obstacles, we present a modular and extensibleopen-source question answering framework. We demonstratehow the framework can be used by integrating two state-of-the-artquestion answering systems. As a result our evaluation shows thatoverall better results can be achieved by the use of combinationrather than individual stand-alone versions

The necessity of making the Semantic Web more accessible for lay users, alongside the uptake of interactive systems and smart assistants for the Web, have spawned a new generation of RDF-based question answering systems. However, fair evaluation of these systems remains a challenge due to the different type of answers that they provide. Hence, repeating current published experiments or even benchmarking on the same datasets remains a complex and time-consuming task. We present a novel online benchmarking platform for question answering (QA) that relies on the FAIR principles to support the fine-grained evaluation of question answering systems. We detail how the platform addresses the fair benchmarking platform of question answering systems through the rewriting of URIs and URLs. In addition, we implement different evaluation metrics, measures, datasets and pre-implemented systems as well as methods to work with novel formats for interactive and non-interactive benchmarking of question answering systems. Our analysis of current frameworks shows that most of the current frameworks are tailored towards particular datasets and challenges but do not provide generic models. In addition, while most frameworks perform well in the annotation of entities and properties, the generation of SPARQL queries from annotated text remains a challenge.