DBpedia 3.9 is up and going. Word came today from Christian Bizer and Christopher Sahnwaldt that the new release boasts an overall increase in the number of concepts in the English edition from 3.7 to 4 million things, thanks to being based on updated Wikipedia dumps from the spring of 2013.
Other numbers to impress:
Posts Tagged ‘YAGO’
A paper entitled “Recovering Semantics of Tables on the Web” was presented at the 37th Conference on Very Large Databases in Seattle, WA . The paper’s authors included 6 Google engineers along with professor Petros Venetis of Stanford University and Gengxin Miao of UC Santa Barbara. The paper summarizes an approach for recovering the semantics of tables with additional annotations other than what the author of a table has provided. The paper is of interest to developers working on the semantic web because it gives insight into how programmers can use semantic data (database of triples) and Open Information Extraction (OIE) to enhance unstructured data on the web. In addition they compare how a “maximum-likelihood” model, used to assign class labels to tables, compares to a “database of triples” approach. The authors show that their method for labeling tables is capable of labeling “an order of magnitude more tables on the web than is possible using Wikipedia/YAGO and many more than freebase.”
Eqentia added to its content discovery and knowledge management portal this week features to recommend additional content or people connections to end users and content curators. But it’s also been doing some other interesting work in the past couple of months on the back-end that draws on semantic technologies to help curators and content administrators of custom Eqentia-based knowledge portals with their taxonomies.
This is where YAGO (Yet Another Great Ontology), a semantic knowledge base some 2 million entities strong that extracts structured information from Wikipedia via DBpedia, comes into play. In essence, YAGO reveals Wikipedia to the Semantic Web, explains CEO William Mougayar.
YAGO gives Eqentia a list of companies and persons to to use for its auto-complete list. Once the user clicks what he wants from the auto complete list — say “Steve Jobs”– Eqentia takes “Steve_Jobs” (note the underscore) and builds a SPARQL query to DBpedia that extracts all related labels by which DBpedia knows “Steve Jobs.” As Eqentia explains it, the upshot is that Eqentia uses a local copy of YAGO to quickly search companies and persons to get a unique “key” that is shared by all 3 systems (YAGO, DBpedia and Wikipedia), and which is then used to query DBpedia for any related labels.