Skip to main content

Home/ Semantic Search Engines/ Group items tagged interest

Rss Feed Group items tagged

Filter: All | Bookmarks | Topics Simple Middle
Janos Haits

Discovery Hub Beta - 0 views

semreco.inria.fr/beta

discovery hub beta wikipedia web3.0 web 3.0 semantic semantic web semanticweb semweb search searchengine search engine reference research

shared by Janos Haits on 04 Jan 13 - No Cached
  • Janos Haits on 04 Jan 13
     
    Discovery hub is an exploratory search engine which helps you to discover things you might like or be interested in. It widens your cultural and knowledge horizons by revealing and explaining unattended information. Based on Wikipedia data, Discovery Hub is cross-domain and works on numerous topics including music, cinema, literature but also politics, automobile and much more. It allows performing queries in an innovative way and helps you to navigate rich results. As a hub, it proposes redirections to others platforms to make you benefit from your discoveries (Youtube, Deezer and more).
Janos Haits

CTRL-Follow - 0 views

www.ctrl-search.com/Follow

search semantic web3.0 semantic web reference search engine semanticweb searchengine research

shared by Janos Haits on 23 Jul 12 - No Cached
  • Janos Haits on 23 Jul 12
     
    Our leading semantic engine, CTRL, tracks your subject of interest by fetching relevant news from the top news sources online saving you time by delivering only relevant articles (summary and original link) straight to your email.
Janos Haits

CTSAsearch - 0 views

research.icts.uiowa.edu/polyglot

research science collaboration networking network semantic search web3.0 Semantic Web search engine searchengine semanticweb semantic_web

shared by Janos Haits on 11 Feb 18 - No Cached
  • Janos Haits on 11 Feb 18
     
    "CTSAsearch is a federated search engine using Linked Open Data published by members of the CTSA Consortium and other interested parties. To try it out, use the form below or click on the "CTSA Search" entry in the menu on the left to see a ranked list of matching investigators. Check the "Display Map" box or click on the "CTSA Map" entry in the menu to visualize coauthorship amongst the matching investigators."
Seçkin Anıl Ünlü

Semantic Search: The Myth and Reality - ReadWriteWeb - 0 views

www.readwriteweb.com/...earch_the_myth_and_reality.php

semantic search readwriteweb web web3.0 comparison

shared by Seçkin Anıl Ünlü on 02 Nov 08 - Cached
  • Any technology that stands a chance to dethrone Google is of great interest to all of us, particularly one that takes advantage of long-awaited and much-hyped semantic technologies. But no matter how much progress has been made, most of us are still underwhelmed by the results. In head-to-head comparisons with Google, the results have not come out much different.
  • We all know that semantic technologies are powerful, but how and why?
  • The mistake is that semantic search engines present us with Google-like search box and allow us to enter free form queries. So we type the things that we are used to asking - primitive queries.
  • ...11 more annotations...
  • The situation is made more difficult by the fact that right now there is only a thin range of problems where semantic search can clearly do better. This range is complex queries involving inferencing and reasoning over a complex data set.
  • Sadly, natural language processing gives little advantage when it comes to this category of problems.
  • Before looking at the problems that are perfect for semantic search, lets look at the hardest problems. These are computationally challenging problems that really have nothing to do with understanding semantics.
  • There are fundamental limits to what we can compute, and a class of problems that have an exponential number of possible solutions is not going to be magically solved because we represent data as RDF.
  • The good news is that there is a set of problems that are great for semantic search. These are the problems we have been solving so wonderfully with relational database.
  • At its most structured extreme we find Freebase - the semantic database of everything. Freebase is accessible via free text search, but more importantly via MQL (Metaweb Query Language).
  • Companies like Hakia and Powerset are probably working the hardest. These companies are trying to simultaneously build Freebase-like structures on the fly and then do natural language queries on top of them. The difference is that Hakia is using (likely similar) technology to query over the entire web, while Powerset has (probably shrewdly) chosen to restrict the search to Wikipedia.
  • Here is the problem - the natural language interface has nothing to do with the underlying data representation.
  • Fundamentally, Hakia, Powerset, and Freebase are databases. Fundamentally, all of them have some kind of Natural Language Processing that translates the question into a canonical query over the database.
  • Having a simplistic search interface hurts Powerset and Hakia, and to a lesser extent Freebase, which is not positioning itself as generic search.
  • Instead, the expectation should really be to solve the problems that can not be solved by Google today.
1 - 5 of 5
Showing 20▼ items per page