In Pingar’s case, its API will allow a company’s existing software programs to work with Pingar’s advanced data analysis and search technology to manage the company’s unstructured electronic data. Unstructured data can include: documents, webpages, emails, news or any kind of text. Companies will be able to review massive amounts of data with the touch of a button, rather than having the staff do these tasks by hand – saving valuable time.

From March 8. Pingar’s API will be available free to software developers for a limited development period to enable developers to work with Pingar’s tools to build specific solutions for their clients.

With Pingar’s API companies can utilise:

• Rapid Discovery – a tool that can be added to existing search engines for rapid query refinement and results assessment.
• Entity Extraction – a suite of cutting-edge tools that turn documents into useful lists of entities including people’s names, telephone numbers, credit card numbers and organisations.
• Content Analysis – provides precision key-word extraction and on-click document summarization and sanitation.

Pingar API tools will help companies make better sense of the data they own and deliver smarter, time-saving search and data analysis.

You can find all the information at http://www.pingar.com

• Twitter hashtags,
• user IDs, and
• arbitrary URIs.

by a simple yet powerful syntax. For example, users can easily state that two hashtags mean the same:

#muenchen = #munich

The Hypertwitter application can extract and interpret such special tweets (Twitter messages) for two purposes, namely:

1. To expand your queries / search in Twitter (e.g. turn a query for tweets containing #muenchen into those also containing #munich), and
2. to create an RDF graph of all such statements for usage in other Web applications.

Now, given the millions of Twitter users, this could naturally lead to chaos, so there are two a simple yet effective ways to control which subset of statements should be considered:

1. Just use your own tweets.
2. Create a new public or private Twitter list that contains all users whose tweets you want us to consider. We call the list used for HyperTwitter the “trust list”.

In the simplest form, you will just trust your own statements, so you would use your Twitter ID without a list.

You can find all the information at http://semantictwitter.appspot.com/.

On the last 4th of February, IBM patented a way to improve traditional free-text tagging with semantic capabilities basically to improve the exploitation of those annotations/tags. If you are interested on the patent, you can find it just here.

Regarding this free-text tagging vs. more semantic tagging techniques, we should not forget the existence of an specification on these same matters called CommonTag. Of course, the IBM’s patent is more focused on the automatic generation/extraction of the semantics behind free-text tagging (tag clouds) than to directly tag resources semantically. ]]> http://blog.insemtives.eu/2010/02/ibms-patent-about-tagging-and-the-semantic-web/feed/ 0 http://blog.insemtives.eu/2009/10/report-by-alta-plana-titled-text-analytics-2009-user-perspectives-on-solutions-and-providers-avialable/ http://blog.insemtives.eu/2009/10/report-by-alta-plana-titled-text-analytics-2009-user-perspectives-on-solutions-and-providers-avialable/#comments Tue, 06 Oct 2009 11:02:28 +0000 gtorodelvalle http://blog.insemtives.eu/?p=124 You can get it at: http://altaplana.com/TA2009