Posts Tagged ‘DBpedia’

Studio Ousia Envisions A World Of Semantic Augmented Reality

Image courtesy: Flickr/by Filter Forge

Image courtesy: Flickr/by Filter Forge

Ikuya Yamada, co-founder and CTO of Studio Ousia, the company behind Linkify – the technology to automatically extract certain keywords and add intelligent hyperlinks to them to accelerate mobile search – recently sat down with The Semantic Web Blog to discuss the company’s work, including its vision of Semantic AR (augmented reality).

The Semantic Web Blog: You spoke at last year’s SEEDS Conference on the subject of linking things and information and the vision of Semantic AR, which includes the idea of delivering additional information to users before they even launch a search for it. Explain your technology’s relation to that vision of finding and delivering the information users need while they are consuming content – even just looking at a word.

Yamada: The main focus of our technology is extracting accurately only a small amount of interesting keywords from text [around people, places, or things]. …We also develop a content matching system that matches those keywords with other content on the web – like a singer [keyword] with a song or a location [keyword] with a map. By combining keyword extraction and the content matching engine, we can augment text using information on the web.

Read more

The Web Is 25 — And The Semantic Web Has Been An Important Part Of It

web25NOTE: This post was updated at 5:40pm ET.

Today the Web celebrates its 25th birthday, and we celebrate the Semantic Web’s role in that milestone. And what a milestone it is: As of this month, the Indexed Web contains at least 2.31 billion pages, according to WorldWideWebSize.  

The Semantic Web Blog reached out to the World Wide Web Consortium’s current and former semantic leads to get their perspective on the roads The Semantic Web has traveled and the value it has so far brought to the Web’s table: Phil Archer, W3C Data Activity Lead coordinating work on the Semantic Web and related technologies; Ivan Herman, who last year transitioned roles at the W3C from Semantic Activity Lead to Digital Publishing Activity Lead; and Eric Miller, co-founder and president of Zepheira and the leader of the Semantic Web Initiative at the W3C until 2007.

While The Semantic Web came to the attention of the wider public in 2001, with the publication in The Scientific American of The Semantic Web by Tim Berners-Lee, James Hendler and Ora Lassila, Archer points out that “one could argue that the Semantic Web is 25 years old,” too. He cites Berners-Lee’s March 1989 paper, Information Management: A Proposal, that includes a diagram that shows relationships that are immediately recognizable as triples. “That’s how Tim envisaged it from Day 1,” Archer says.

Read more

Dandelion’s New Bloom: A Family Of Semantic Text Analysis APIs

rsz_dandyDandelion, the service from SpazioDati whose goal is to delivering linked and enriched data for apps, has just recently introduced a new suite of products related to semantic text analysis.

Its dataTXT family of semantic text analysis APIs includes dataTXT-NEX, a named entity recognition API that links entities in the input sentence with Wikipedia and DBpedia and, in turn, with the Linked Open Data cloud and dataTXT-SIM, an experimental semantic similarity API that computes the semantic distance between two short sentences. TXT-CL (now in beta) is a categorization service that classifies short sentences into user-defined categories, says SpazioDati.CEO Michele Barbera.

“The advantage of the dataTXT family compared to existing text analysis’ tools is that dataTXT relies neither on machine learning nor NLP techniques,” says Barbera. “Rather it relies entirely on the topology of our underlying knowledge graph to analyze the text.” Dandelion’s knowledge graph merges together several Open Community Data sources (such as DBpedia) and private data collected and curated by SpazioDati. It’s still in private beta and not yet publicly accessible, though plans are to gradually open up portions of the graph in the future via the service’s upcoming Datagem APIs, “so that developers will be able to access the same underlying structured data by linking their own content with dataTXT APIs or by directly querying the graph with the Datagem APIs; both of them will return the same resource identifiers,” Barbera says. (See the Semantic Web Blog’s initial coverage of Dandelion here, including additional discussion of its knowledge graph.)

Read more

Music Discovery Service seevl.fm Launches

screen shot of seevl.fm search: Lou ReedThis week marked the public launch of seevl.fm.

SemanticWeb.com has tracked seevl’s development through various incarnations, including a YouTube plugin and as a service for users of Deezer (available as a Deezer app). This week’s development, however, sees the service emerge as a stand-alone, cross-browser, cross-platform, mobile-ready service; a service that is free and allows for unlimited search and discovery. So, what can one do with seevl?

Following the death of Lou Reed this week, I (not surprisingly) saw mentions of the artist skyrocket across my social networks. People were sharing memories and seeking information — album and song titles, lyrics, biographies, who influenced Reed, who Reed influenced, and a lot of people simply wanted to listen to Reed’s music.  A quick look at the seevl.fm listing for Lou Reed shows a wealth of information including a music player pre-populated with some of the artist’s greatest hits.

Read more

Picture This: Muséophile Leads Art Lovers To Art Works

rsz_museophilepixWhere in Paris might you find an exhibit featuring the artist Charles Le Brun?

If you didn’t know to check into the Musée du Louvre, Muséophile can help. Just plug in an artist or movement, and city, and see what comes to the fore. The service, still in beta, comes courtesy of Sémanticpédia, a platform for collaboration between France’s Ministry of Culture and Communication; INRIA, the country’s public institution of scientific and technological research;   and Wikimedia France, whose aim is to perform research and development applied to corpus or collaborative cultural projects, using data extracted from Wikimedia projects.

Currently, data from French DBpedia is available for Sémanticpédia projects to leverage, and Muséophile is the first effort of the collaboration to do so. In fact, an overall effort by the government of France to boost the representation of French cultural resources on the web, which should aid in Muséophile’s continued development, is underway: Those within the Ministry of Culture and Communication with expertise in various content bases related to French culture are being charged to contribute their knowledge to the still youthful French DBpedia, which constitutes an extraction of structured information from the French Wikipedia. That will lead to a single reference system that they also can rely on to collaborate, and exchange and integrate data.

Read more

DBpedia 3.9 Hits The Runway


rsz_dbnew3DBpedia 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:

Read more

Startup TextRazor Features Enhanced Language Support In Open Semantic Analysis And Text Mining API

Comprehensive support for semantic analysis across 20 languages (up from ten) is one of the latest additions to TextRazor’s customizable, open semantic analysis and text mining API, to satisfy what the startup says is increasing demand for sophisticated semantic tools that go beyond English.

The company’s technology has been in public beta for just a few months. It differs from other multilingual natural language processing solutions, says founder Toby Crayston, in that it strongly leverages linked data sources like DBpedia and the semantic web to disambiguate, normalize and filter extracted metadata with better accuracy, so that end users can build powerful multilingual classifiers regardless of the language of their documents.

Read more

Yandex Co-Founder, CTO Ilya Segalovich Dies

Photo of Ilya SegalovichYandex, the leading Internet search service in Russia, has lost its co-Founder and Chief Technology Officer, Ilya Segalovich. Segalovich, the company reports, had been diagnosed with a treatable form of cancer and was responding well to treatment before unexpectedly succumbing to complications. DBpedia already has accounted for the news, as has Freebase.

Yandex’ portfolio of search technologies include everything from its method of machine learning, dubbed Matriksnet, to its Spectrum query statistics that analyzes a 5 billion query search log to find ‘objects’ in queries, categorize them in 60 categories, and map each query into one of possible ‘user intents’ according to a category of the object. It also, of course, signed on to support schema.org a couple of years back to leverage webmasters’ use of the structured data markup in its search results.

Read more

Art Lovers Will See There’s More To Love With Linked Data

The team behind the data integration tool Karma this week presented at LODLAM (Linked Open Data in Libraries, Archives & Museums), illustrating how to map museum data to the Europeana Data Model (EDM) or CIDOC CRM (Conceptual Reference Model). This came on the heels of its earning the best-in-use paper award at ESWC2013 for its publication about connecting Smithsonian American Art Museum (SAAM) data to the LOD cloud.

The work of Craig KnoblockPedro SzekelyJose Luis AmbiteShubham GuptaMaria MusleaMohsen Taheriyan, and Bo Wu at the Information Sciences InstituteUniversity of Southern California, Karma lets users integrate data from a variety of data sources (hierarchical and dynamic ones too) — databases, spreadsheets, delimited text files, XML, JSON, KML and Web APIs — by modeling it according to an ontology of their choice. A graphical user interface automates much of the process. Once the model is complete, users can publish the integrated data as RDF or store it in a database.

The Smithsonian project builds on the group’s work on Karma for mapping structured sources to RDF. For the Smithsonian project (whose announcement we covered here), Karma converted more than 40,000 of the museum’s holdings, stored in more than 100 tables in a SQL Server Database, to LOD, leveraging EDM, the metamodel used in the Europeana project to represent data from Europe’s cultural heritage institutions.

Read more

Self Medicating? Stay Safe With Semantic Tech’s Help

It’s pretty common these days for people to hit the web in search of medication advice to deal with symptoms they’re experiencing.  The trouble is, most people don’t approach the process in a truly safe manner.

Semantic technology can help rectify the situation. In fact, it’s already doing so in France, where Olivier Curé, an associate professor in computer science at the University of Paris-Est in France, created a web application based on the book by pharmacology expert and educator Jean-Paul Giroud Médicaments sans ordonnance: Les bons et les mauvais!, of which he is a co-author with Catherine Cupillard. The app is made available to their consumers via three big insurance companies there, in order to help the companies save costs on reimbursing them for buying drugs that won’t actually help their condition, or direct them to the appropriate drugs at pharmacies with which the insurers may have relationships to supply them at lower costs. An iPhone version of the app was just released to accompany the web version.

Read more

NEXT PAGE >>