Filters








171 Hits in 2.0 sec

Multilingual schema matching for Wikipedia infoboxes

Thanh Nguyen, Viviane Moreira, Huong Nguyen, Hoa Nguyen, Juliana Freire
2011 Proceedings of the VLDB Endowment  
We also present a case study which demonstrates that the multilingual mappings we derive lead to substantial improvements in answer quality and coverage for structured queries over Wikipedia content.  ...  Recent research has taken advantage of Wikipedia's multilingualism as a resource for cross-language information retrieval and machine translation, as well as proposed techniques for enriching its cross-language  ...  We thank Gosse Bouma, Sabine Massmann and Erhard Rahm for sharing their software with us, and the reviewers for their constructive comments.  ... 
doi:10.14778/2078324.2078329 fatcat:eexeqy6rnbcx3lrczjewdzvaeq

Multilingual Schema Matching for Wikipedia Infoboxes [article]

Thanh Nguyen, Viviane Moreira, Huong Nguyen, Hoa Nguyen, Juliana Freire
2011 arXiv   pre-print
We also present a case study which demonstrates that the multilingual mappings we derive lead to substantial improvements in answer quality and coverage for structured queries over Wikipedia content.  ...  Recent research has taken advantage of Wikipedia's multilingualism as a resource for cross-language information retrieval and machine translation, as well as proposed techniques for enriching its cross-language  ...  We thank Gosse Bouma, Sabine Massmann and Erhard Rahm for sharing their software with us, and the reviewers for their constructive comments.  ... 
arXiv:1110.6651v1 fatcat:6fuogzmdvjdufhcfzzdlvixnme

A Self-Supervised Approach for Extraction of Attribute-Value Pairs from Wikipedia Articles [chapter]

Wladmir C. Brandão, Edleno S. Moura, Altigran S. Silva, Nivio Ziviani
2010 Lecture Notes in Computer Science  
In this paper we present a self-supervised approach for autonomously extract attributevalue pairs from Wikipedia articles.  ...  We apply our method to the Wikipedia automatic infobox generation problem and outperformed a method presented in the literature by 21.92% in precision, 26.86% in recall and 24.29% in F1.  ...  For each article, sentences are associated with attributes within the infobox schema of the article. The association is based on simple term matching.  ... 
doi:10.1007/978-3-642-16321-0_29 fatcat:dto5tftuandsdkybrvts5guvt4

Building a Large Scale Knowledge Base from Chinese Wiki Encyclopedia [chapter]

Zhichun Wang, Zhigang Wang, Juanzi Li, Jeff Z. Pan
2012 Lecture Notes in Computer Science  
In this paper, an upper-level ontology schema in Chinese is first learned based on the category system and Infobox information in Hudong.  ...  But in Chinese, due to the heavily imbalance in size (no more than one tenth) between English and Chinese in Wikipedia, there are few Chinese linked data are published and linked to DBpedia, which hinders  ...  Melo et.al [15] explored the multilingual nature of Wikipedia, and built a large multilingual entity taxonomy MENTA, which describes 5.4 million entities in various languages.  ... 
doi:10.1007/978-3-642-29923-0_6 fatcat:oja3gikpcvdird4s47t5234gmq

Cross-Lingual Infobox Alignment in Wikipedia Using Entity-Attribute Factor Graph [chapter]

Yan Zhang, Thomas Paradis, Lei Hou, Juanzi Li, Jing Zhang, Haitao Zheng
2017 Lecture Notes in Computer Science  
In this paper, we propose 8 effective features for cross lingual infobox attribute matching containing categories, templates, attribute labels and values.  ...  Our proposed approach finds 23,923 new infobox attribute mappings between English and Chinese Wikipedia, and 31,576 between English and French based on no more than six thousand existing matched infobox  ...  Ontology Schema Matching Ontology schema matching [14] is another related problem which mainly aims to get alignments of concepts and properties.  ... 
doi:10.1007/978-3-319-68288-4_44 fatcat:v2hx2qe7ujatbpjuituptfxcmu

Towards an Automatic Creation of Localized Versions of DBpedia [chapter]

Alessio Palmero Aprosio, Claudio Giuliano, Alberto Lavelli
2013 Lecture Notes in Computer Science  
Specifically, we mapped 45,978 Wikipedia infobox attributes to DBpedia properties in 14 different languages for which mappings were not yet available. The resource is made available in an open format.  ...  DBpedia is a large-scale knowledge base that exploits Wikipedia as primary data source. The extraction procedure requires to manually map Wikipedia infoboxes into the DBpedia ontology.  ...  Similarly, Shvaiko and Euzenat [15] present a new classification of schema-based matching techniques.  ... 
doi:10.1007/978-3-642-41335-3_31 fatcat:x3nj4tvozrevrpkidybpyn7ls4

Semantic Relationship Extraction and Ontology Building using Wikipedia: A Comprehensive Survey

Nora I. Al- Rajebah, Hend S. Al- Khalifa
2010 International Journal of Computer Applications  
Wikipedia is considered as one of the important knowledge sources that have been used to extract semantic relations due to its characteristics as a semi-structured knowledge source that would facilitate  ...  In this paper we will focus on the current state of this challenging field by discussing some of the recent studies about Wikipedia and semantic extraction and highlighting their main contributions and  ...  Al-Salman, for his valuable and thoughtful feedback.  ... 
doi:10.5120/1661-2236 fatcat:54cgxwxatnawdbtp2reynusqo4

Inside YAGO2s

Joanna Biega, Erdal Kuzey, Fabian M. Suchanek
2013 Proceedings of the 22nd International Conference on World Wide Web - WWW '13 Companion  
In this demo, users can see how more than 30 individual modules of YAGO work in parallel to extract facts, to check facts for their correctness, to deduce facts, and to merge facts from different sources  ...  Of particular interest are the themes that define the schema of YAGO, the extraction patterns for Wikipedia, and the themes that define the deductive rules of YAGO.  ...  For instance, the user can choose to run the Wikipedia extractor only on a specific Wikipedia page.  ... 
doi:10.1145/2487788.2487935 dblp:conf/www/BiegaKS13 fatcat:ujhseflfmnct3lr4422dbm2pmq

YAGO: A Multilingual Knowledge Base from Wikipedia, Wordnet, and Geonames [chapter]

Thomas Rebele, Fabian Suchanek, Johannes Hoffart, Joanna Biega, Erdal Kuzey, Gerhard Weikum
2016 Lecture Notes in Computer Science  
The project combines information from Wikipedias in 10 different languages into a coherent whole, thus giving the knowledge a multilingual dimension.  ...  YAGO is a large knowledge base that is built automatically from Wikipedia, WordNet and GeoNames.  ...  We provide infobox attributes of entities (72m), the infobox templates that an entity has on its Wikipedia page (5m), the infobox attributes per template (262k), Wikipedia-links between the entities (63m  ... 
doi:10.1007/978-3-319-46547-0_19 fatcat:hdmd4y5wavanrgngx27p2kw37u

Zhishi.me - Weaving Chinese Linking Open Data [chapter]

Xing Niu, Xinruo Sun, Haofen Wang, Shu Rong, Guilin Qi, Yong Yu
2011 Lecture Notes in Computer Science  
As a result, the CLOD has more than 5 million distinct entities and we simply link CLOD with the existing LOD based on the multilingual characteristic of Wikipedia.  ...  More precisely, we identify important structural features in three largest Chinese encyclopedia sites (i.e., Baidu Baike, Hudong Baike, and Chinese Wikipedia) for extraction and propose several data-level  ...  One is the practice of schema-level ontology matching, as Jain et al. [9] and Raimond et al. [14] did.  ... 
doi:10.1007/978-3-642-25093-4_14 fatcat:n56bkdt3qfevfkbryurn35ccqm

DBpedia – A large-scale, multilingual knowledge base extracted from Wikipedia

Jens Lehmann, Robert Isele, Max Jakob, Anja Jentzsch, Dimitris Kontokostas, Pablo N. Mendes, Sebastian Hellmann, Mohamed Morsey, Patrick van Kleef, Sören Auer, Christian Bizer
2015 Semantic Web Journal  
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 DBpedia community project extracts structured, multilingual knowledge from Wikipedia and makes it freely available on the Web using Semantic Web and Linked Data technologies.  ...  Raw Infobox Extraction The type of Wikipedia content that is most valuable for the DBpedia extraction are infoboxes.  ... 
doi:10.3233/sw-140134 fatcat:phpmzjhshvfajldnon7behaxva

The knowledge organization of DBpedia: a case study

Cristina Pattuelli, Sara Rubinow
2013 Journal of Documentation  
The flexibility of the RDF model allows for the mixing and matching of properties from different namespaces without the need for agreement on the adoption of a specific schema.  ...  The left box presents the wiki markup for the musical artist infobox template, which is displayed in the infobox (center) as viewed within the Wikipedia article for "Mary Lou Williams."  ... 
doi:10.1108/jd-07-2012-0084 fatcat:rrzgauiwg5dz5a4s6ga6agvi6i

Information arbitrage across multi-lingual Wikipedia

Eytan Adar, Michael Skinner, Daniel S. Weld
2009 Proceedings of the Second ACM International Conference on Web Search and Data Mining - WSDM '09  
Analyzing four large language domains (English, Spanish, French, and German), we present Ziggurat, an automated system for aligning Wikipedia infoboxes, creating new infoboxes as necessary, filling in  ...  The rapid globalization of Wikipedia is generating a parallel, multi-lingual corpus of unprecedented scale.  ...  Additional thanks to Ivan Beschastnikh, Travis Kriplean, Raphael Hoffman, Fei Wu and Mausam for their feedback, advice, and labeling.  ... 
doi:10.1145/1498759.1498813 dblp:conf/wsdm/AdarSW09 fatcat:qwzvovhp3bbhtacckdosa7txma

Populating a multilingual ontology of proper names from open sources

Agata Savary, Leszek Manicki, Małgorzata Baron
2013 Journal of Language Modelling  
Thus, mapping multilingual sets of instances (names) from Wikipedia and GeoNames on Prolexbase pivots corresponds to an instance-to-concept rather than a concept-to-concept matching.  ...  Note that this matching process is less reliable than matching Wikipedia entries with Prolexbase.  ... 
doi:10.15398/jlm.v1i2.63 fatcat:i4b6hdd2x5ftdcqkpsok52ntom

Charting DBpedia: Towards a Cartography of a Major Linked Dataset [chapter]

M. Cristina Pattuelli, Sara Rubinow
2012 Categories, Contexts and Relations in Knowledge Organization  
The flexibility of the RDF model allows for the mixing and matching of properties from different namespaces without the need for agreement on the adoption of a specific schema.  ...  DBpedia DBpedia is a multilingual and cross-domain RDF dataset created with the purpose of making Wikipedia information available as Linked Data.  ... 
doi:10.5771/9783956504402-75 fatcat:c7jbpk2yyngxva4szxnki2pfkq
« Previous Showing results 1 — 15 out of 171 results