This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.

/pdf/character-level-convolutional-networks-for-text-whh3tafudk.pdf

Character-level convolutional networks for text classification

The DBpedia community project extracts structured, multilingual knowledge from Wikipedia and makes it freely available on the Web using Semantic Web and Linked Data technologies. The project extracts knowledge from 111 different language editions of Wikipedia. The largest DBpedia knowledge base which is extracted from the English edition of Wikipedia consists of over 400 million facts that describe 3.7 million things. The DBpedia knowledge bases that are extracted from the other 110 Wikipedia editions together consist of 1.46 billion facts and describe 10 million additional things. The DBpedia project maps Wikipedia infoboxes from 27 different language editions to a single shared ontology consisting of 320 classes and 1,650 properties. The mappings are created via a world-wide crowd-sourcing effort and enable knowledge from the different Wikipedia editions to be combined. The project publishes releases of all DBpedia knowledge bases for download and provides SPARQL query access to 14 out of the 111 language editions via a global network of local DBpedia chapters. In addition to the regular releases, the project maintains a live knowledge base which is updated whenever a page in Wikipedia changes. DBpedia sets 27 million RDF links pointing into over 30 external data sources and thus enables data from these sources to be used together with DBpedia data. Several hundred data sets on the Web publish RDF links pointing to DBpedia themselves and make DBpedia one of the central interlinking hubs in the Linked Open Data (LOD) cloud. In this system report, we give an overview of the DBpedia community project, including its architecture, technical implementation, maintenance, internationalisation, usage statistics and applications.

/pdf/dbpedia-a-large-scale-multilingual-knowledge-base-extracted-2yfl0whyxn.pdf

DBpedia - A Large-scale, Multilingual Knowledge Base Extracted from Wikipedia

Character-level Convolutional Networks for Text Classification

Knowledge graph (KG) embedding is to embed components of a KG including entities and relations into continuous vector spaces, so as to simplify the manipulation while preserving the inherent structure of the KG. It can benefit a variety of downstream tasks such as KG completion and relation extraction, and hence has quickly gained massive attention. In this article, we provide a systematic review of existing techniques, including not only the state-of-the-arts but also those with latest trends. Particularly, we make the review based on the type of information used in the embedding task. Techniques that conduct embedding using only facts observed in the KG are first introduced. We describe the overall framework, specific model design, typical training procedures, as well as pros and cons of such techniques. After that, we discuss techniques that further incorporate additional information besides facts. We focus specifically on the use of entity types, relation paths, textual descriptions, and logical rules. Finally, we briefly introduce how KG embedding can be applied to and benefit a wide variety of downstream tasks such as KG completion, relation extraction, question answering, and so forth.

Knowledge Graph Embedding: A Survey of Approaches and Applications

In the recent years, different Web knowledge graphs, both free and commercial, have been created. While Google coined the term "Knowledge Graph" in 2012, there are also a few openly available knowledge graphs, with DBpedia, YAGO, and Freebase being among the most prominent ones. Those graphs are often constructed from semi-structured knowledge, such as Wikipedia, or harvested from the web with a combination of statistical and linguistic methods. The result are large-scale knowledge graphs that try to make a good trade-off between completeness and correctness. In order to further increase the utility of such knowledge graphs, various refinement methods have been proposed, which try to infer and add missing knowledge to the graph, or identify erroneous pieces of information. In this article, we provide a survey of such knowledge graph refinement approaches, with a dual look at both the methods being proposed as well as the evaluation methodologies used.

Knowledge graph refinement: A survey of approaches and evaluation methods

Triple stores are the backbone of increasingly many Data Web applications. It is thus evident that the performance of those stores is mission critical for individual projects as well as for data integration on the Data Web in general. Consequently, it is of central importance during the implementation of any of these applications to have a clear picture of the weaknesses and strengths of current triple store implementations. In this paper, we propose a generic SPARQL benchmark creation procedure, which we apply to the DBpedia knowledge base. Previous approaches often compared relational and triple stores and, thus, settled on measuring performance against a relational database which had been converted to RDF by using SQL-like queries. In contrast to those approaches, our benchmark is based on queries that were actually issued by humans and applications against existing RDF data not resembling a relational schema. Our generic procedure for benchmark creation is based on query-log mining, clustering and SPARQL feature analysis. We argue that a pure SPARQL benchmark is more useful to compare existing triple stores and provide results for the popular triple store implementations Virtuoso, Sesame, Jena-TDB, and BigOWLIM. The subsequent comparison of our results with other benchmark results indicates that the performance of triple stores is by far less homogeneous than suggested by previous benchmarks.

/pdf/dbpedia-sparql-benchmark-performance-assessment-with-real-39kdb3x2fj.pdf

DBpedia SPARQL benchmark: performance assessment with real queries on real data

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.

/pdf/user-driven-quality-evaluation-of-dbpedia-xoqyi5albp.pdf

User-driven quality evaluation of DBpedia

Purpose – DBpedia extracts structured information from Wikipedia, interlinks it with other knowledge bases and freely publishes the results on the web using Linked Data and SPARQL. However, the DBpedia release process is heavyweight and releases are sometimes based on several months old data. DBpedia‐Live solves this problem by providing a live synchronization method based on the update stream of Wikipedia. This paper seeks to address these issues.Design/methodology/approach – Wikipedia provides DBpedia with a continuous stream of updates, i.e. a stream of articles, which were recently updated. DBpedia‐Live processes that stream on the fly to obtain RDF data and stores the extracted data back to DBpedia. DBpedia‐Live publishes the newly added/deleted triples in files, in order to enable synchronization between the DBpedia endpoint and other DBpedia mirrors.Findings – During the realization of DBpedia‐Live the authors learned that it is crucial to process Wikipedia updates in a priority queue. Recently‐upd...

/pdf/dbpedia-and-the-live-extraction-of-structured-data-from-45nq7zs0xe.pdf

DBpedia and the live extraction of structured data from Wikipedia

One of the main tasks when creating and maintaining knowledge bases is to validate facts and provide sources for them in order to ensure correctness and traceability of the provided knowledge. So far, this task is often addressed by human curators in a three-step process: issuing appropriate keyword queries for the statement to check using standard search engines, retrieving potentially relevant documents and screening those documents for relevant content. The drawbacks of this process are manifold. Most importantly, it is very time-consuming as the experts have to carry out several search processes and must often read several documents. In this article, we present DeFacto (Deep Fact Validation) --- an algorithm for validating facts by finding trustworthy sources for it on the Web. DeFacto aims to provide an effective way of validating facts by supplying the user with relevant excerpts of webpages as well as useful additional information including a score for the confidence DeFacto has in the correctness of the input fact.

/pdf/defacto-deep-fact-validation-5emaww40o7.pdf

Mohamed Morsey

Papers

DBpedia - A Large-scale, Multilingual Knowledge Base Extracted from Wikipedia

DBpedia SPARQL benchmark: performance assessment with real queries on real data

User-driven quality evaluation of DBpedia

DBpedia and the live extraction of structured data from Wikipedia

DeFacto - deep fact validation