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

Linked Open Data (LOD) comprises an unprecedented volume of structured data on the Web. However, these datasets are of varying quality ranging from extensively curated datasets to crowdsourced or extracted data of often relatively low quality. We present a methodology for test-driven quality assessment of Linked Data, which is inspired by test-driven software development. We argue that vocabularies, ontologies and knowledge bases should be accompanied by a number of test cases, which help to ensure a basic level of quality. We present a methodology for assessing the quality of linked data resources, based on a formalization of bad smells and data quality problems. Our formalization employs SPARQL query templates, which are instantiated into concrete quality test case queries. Based on an extensive survey, we compile a comprehensive library of data quality test case patterns. We perform automatic test case instantiation based on schema constraints or semi-automatically enriched schemata and allow the user to generate specific test case instantiations that are applicable to a schema or dataset. We provide an extensive evaluation of five LOD datasets, manual test case instantiation for five schemas and automatic test case instantiations for all available schemata registered with Linked Open Vocabularies (LOV). One of the main advantages of our approach is that domain specific semantics can be encoded in the data quality test cases, thus being able to discover data quality problems beyond conventional quality heuristics.

/pdf/test-driven-evaluation-of-linked-data-quality-43bbrnqnvi.pdf

Test-driven evaluation of linked data quality

In this paper we look into the use of crowdsourcing as a means to handle Linked Data quality problems that are challenging to be solved automatically. We analyzed the most common errors encountered in Linked Data sources and classified them according to the extent to which they are likely to be amenable to a specific form of crowdsourcing. Based on this analysis, we implemented a quality assessment methodology for Linked Data that leverages the wisdom of the crowds in different ways: (i) a contest targeting an expert crowd of researchers and Linked Data enthusiasts; complemented by (ii) paid microtasks published on Amazon Mechanical Turk.We empirically evaluated how this methodology could efficiently spot quality issues in DBpedia. We also investigated how the contributions of the two types of crowds could be optimally integrated into Linked Data curation processes. The results show that the two styles of crowdsourcing are complementary and that crowdsourcing-enabled quality assessment is a promising and affordable way to enhance the quality of Linked Data.

/pdf/crowdsourcing-linked-data-quality-assessment-39mtbfx4dv.pdf

Crowdsourcing Linked Data Quality Assessment

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

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. In this paper we focus on the manual process where the first phase includes the detection of common quality problems and their representation in a quality problem taxonomy. 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 implemented by the tool TripleCheckMate wherein a user assesses an individual resource and evaluates each fact for correctness. This paper focuses on describing the methodology, quality taxonomy and the tools’ system architecture, user perspective and extensibility.

/pdf/triplecheckmate-a-tool-for-crowdsourcing-the-quality-2owllnan4j.pdf

Dimitris Kontokostas

Papers

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

Test-driven evaluation of linked data quality

Crowdsourcing Linked Data Quality Assessment

User-driven quality evaluation of DBpedia

TripleCheckMate: A Tool for Crowdsourcing the Quality Assessment of Linked Data