Posts Tagged ‘Semantic search’
A few words on the soft revolution that might happen on the search giant…
The Google blog announces, at last, the release of some developments (known as Google Graph) that were studied by the R&D of Mountain View for years.
“The Knowledge Graph enables you to search for things, people or places that Google knows about—landmarks, celebrities, cities, sports teams, buildings, geographical features, movies, celestial objects, works of art and more—and instantly get information that’s relevant to your query. This is a critical first step towards building the next generation of search, which taps into the collective intelligence of the web and understands the world a bit more like people do. (…)
1. Find the right thing
Language can be ambiguous—do you mean Taj Mahal the monument, or Taj Mahal the musician? Now Google understands the difference, and can narrow your search results just to the one you mean—just click on one of the links to see that particular slice of results:
2. Get the best summary
With the Knowledge Graph, Google can better understand your query, so we can summarize relevant content around that topic, including key facts you’re likely to need for that particular thing. For example, if you’re looking for Marie Curie, you’ll see when she was born and died, but you’ll also get details on her education and scientific discoveries:
3. Go deeper and broader
Finally, the part that’s the most fun of all—the Knowledge Graph can help you make some unexpected discoveries. You might learn a new fact or new connection that prompts a whole new line of inquiry.
We’ve always believed that the perfect search engine should understand exactly what you mean and give you back exactly what you want. And we can now sometimes help answer your next question before you’ve asked it, because the facts we show are informed by what other people have searched for.
We’ve begun to gradually roll out this view of the Knowledge Graph to U.S. English users. It’s also going to be available on smartphones and tablets…
Singhal, Amit. Introducing the Knowledge Graph: things, not strings. Google Blog, 16th of May 2012. Available from: http://googleblog.blogspot.fr/2012/05/introducing-knowledge-graph-things-not.html [Accessed 30th of May 2012]
UTOPIA is a disruptive science article reader which integrates some sexy technos such as Altmetric, a comment editor, an integrated semantic search, an interactive figure browser…
The Utopia Documents PDF reader, developped by Lost Island Labs Ltd (LIL) has, in collaboration with Academic Concept Knowledge Ltd. (AQnowledge), seeks to bridge – while online – the ‘linkability gap’ between HTML and PDF, …
It allows readers to experience dynamically enriched scientific articles. The tool is publisher-independent and is providing ‘article-of-the-future-like‘ enrichment for any modern PDF.
The tool is free.
* Based on :
S. Pettifer, P. McDermott, J. Marsh, D. Thorne A. Villeger and T.K. Attwood Ceci n’est pas un hamburger: modelling and representing the scholarly article. Learned Publishing, 24:3, July 2011.
After Elsevier, Thomson, Springer, Karger, etc., TEMIS has signed a licence to improve the search experience in the American Sociaty of Microbiology’s journals platform.
“To serve its 40,000 members better, ASM is completely revamping its online content offering, and aggregating at a new site all of its authoritative content, including ASM’s journal titles dating back to 1916, a rapidly expanding image library, 240 book titles, its news magazine Microbe, and eventually abstracts of meetings and educational publications.
The organization’s main goal is to enhance access, search, navigation and knowledge discovery at a deeper level of detail–articles, chapters, collections by topic, podcasts and webinars. ASM has identified TEMIS as the best content enrichment solution provider for the scientific publishing community and licensed its platform Luxid® for Content Enrichment and its Biological Entity Relationships Skill Cartridge”.
Press release: http://www.temis.com/index.php?id=99&selt=14&lg=en
The NLM works on a new interface for PubMed, including latest advances of semantic search (NLP and connected graphs).
“Semantic MEDLINE is a prototype Web application that summarizes MEDLINE citations returned by a PubMed search. Natural language processing is used to analyze salient content in titles and abstracts. This information is then presented in a graph that has links to the MEDLINE text processed.
Currently, the results from 35 PubMed searches (including a variety of disorders and drugs) are available to be processed. The 500 most recent citations (from the date of the search) are available for further processing by Semantic MEDLINE”.
The prototype can be tested at:
See also this article:
Rindflesch, T.C., Kilicoglu, H., Fiszman, M., Rosemblat, G., Shin, D. Semantic MEDLINE: An advanced information management application for biomedicine. Information Services and Use, Volume 31, Issue 1-2, 2011, Pages 15-21
An impressive study research, sponsored by the Publishing Research Consortium: includes interviews of key-people from Pfizer, the CERN, Mendeley, the British Library, from TEMIS, Elsevier, Springer, Nature, Wiley, etc.
Journal Article Mining: a research study into Practices, Policies, Plans …..and Promises Eefke Smit and Maurits van der Graaf. PRC June 2011 153pp. This is a study commissioned by PRC which offers the first comprehensive look at what publishers and others are doing, and plan to do, in both data and text mining of the scholarly, mainly journal, literature. Lots of fascinating detail from a number of viewpoints – from 29 interviews and 190 detailed responses to a survey
SpringerLink will be soon enriched by semantic technologies, thanks to a collaboration betwwen Springer and TEMIS.
“At the core of this partnership, TEMIS’s flagship Luxid® Content Enrichment Platform leverages a sophisticated combination of linguistic and statistical methods to calculate semantic relatedness among the millions of publications accessible on SpringerLink.
This enables the automatic recommendation for each available article or book chapter of a selection of highly-relevant, semantically-related documents, without requiring specific editorial efforts”.
Press Release, TEMIS, May 19, 2011
TEMIS and Semantico have announced a strategic partnership.
The powerful text mining technology developed by TEMIS automates the semantic enrichment of unstructured content, dramatically improving its findability and discoverability by search engines and end-users.
In online publications, the resulting richer metadata can be used to:
- Help search engines return more relevant results
- Feed search facets to enable efficient drill-down in search results
- Recommend related or similar documents and knowledge
‘More and more publishers are seeing the benefits of semantic content enrichment to boost the value of their content and help market it in innovative ways,’ said Daniel Mayer, Product Marketing Manager, TEMIS