Archive for the ‘Update’ Category

On Monday October 18th and Tuesday October 19th, TextWise will be launching an enhanced Categorization Service on the SemanticHacker API. This update adds the following improvements:

* The Categorization API call now uses our latest 2010 semantic dictionary, incorporating new terminology from across the Web and TextWise’s latest technology enhancements (An updated listing of available semantic dictionaries and their suggested use cases is available here:
http://textwise.com/api_docs/api/configuration_ids.xhtml). Please note that at this time our other API services will remain using their respective dictionaries.

* More granularity in the category scheme, along with the removal of noisy ‘Regional’ categories

* We now have both ‘long’ category labels and equivalent ‘short’
labels available for use in your application. An example of the new-style category call result:

—-OLD CATEGORY
—-Top/Arts/Music/Styles/Bands_and_Artists

—-NEW CATEGORY:
—-LONG LABEL SHORT LABEL
—-Arts/Music/Bands_and_Artists Music/Bands_and_Artists

We have a complete mapping of the old category style to the new categories available on our API documentation site, linked here:

http://textwise.com/api_docs/api/configuration_ids.xhtml

We’ve also made other enhancements to the 4.3 API, in an ongoing effort to provide the best possible semantic API services to our users.

HOW THIS MIGHT AFFECT YOU:

* By default, the Categorization API call will use the new 2010 semantic dictionary. THIS IS THE ONLY SUPPORTED CONFIGURATION. While it is possible to specify a different, older dictionary as part of your category query, the results are not guaranteed to be accurate, due to the extensive reworking of the Categorization API. You will NOT be able to replicate the previous category query results simply by specifying an older dictionary.

* We will be phasing in the new version of the API during the day on Monday, October 18th. We don’t anticipate any downtime during this process. The update will be complete and fully implemented for all users by Tuesday morning, October 19th.

Thanks for your continued use and support of the TextWise SemanticHacker API! If you have any questions please ask away in our forum, or send an email to support@textwise.com.

TextWise is pleased to release an updated version of our WordPress plugin which now supports WordPress version 2.9.2. After a few rigorous rounds of development and testing, then more development and testing, the plugin is now available for you to enjoy on your blogs. We’ve worked hard to maintain compatibility with all WordPress versions from 2.9.2 back to 2.6.1. We have our eye on WordPress and know that they’re releasing version 3.0 soon, as well. So we’ll be working to ensure our plugin works with that, too.

If you’re currently a user of our plugin, thanks for using it and giving us great feedback to make it even better. If you aren’t using the plugin…why not? Head on over to http://wordpress.org/extend/plugins/textwise/ and download it to enhance your WordPress blog with relevant media, tags, links, and more! Enjoy!

We’ve been updating the WordPress plugin to work with the newest version of WordPress (currently 2.8.4), and it’s now available for download from the WordPress Plugin Directory.  This new release restores functionality affected by changes in WordPress 2.8, and is still compatible with previous versions down to 2.6.1.  In addition to restoring the plugin’s original functionality, we enhanced the Content Link Suggestions operation.  In the past, this feature used a direct title link to Wikipedia, which could result in a non-existent entry.  Now we use an article search, which returns the best match Wikipedia can find.

We’re adding a new configuration (dictionary) to our service offering: the 2009 ODP L1 (Configuration ID = odp_2009_l1_1.6k). This new configuration utilizes an up-to-date ODP dataset. 

Note the following information about our existing configurations:

  1. The 2007 ODP L1 (odp_2007_l1_1.7k) will remain available in the service. While we think you will like the 2009 ODP configuration and we encourage you to give it a try, you can certainly continue using the 2007 ODP L1.
  2. The ODP 20K configuration (Configuration ID = odp_2006_l2_20k) will be removed from the service effective immediately. We’ve listened to your feedback and are confident the new 2009 ODP configuration will meet your needs.
  3. Semantic signatures are dependent on the configuration they were generated with. If you’re utilizing signatures you’ve stored, you’ll need to either continue with the same configuration, or regenerate the signatures with the new configuration and use the new signatures instead.
     

For additional information on the available configurations, see the Service Configuration page in the API Documentation. If you have any questions or concerns, please contact us or notify us via the Forum. We will try our best to help you resolve any issues you may encounter.

On December 31, 2008, TextWise released an exciting update to their core API services. As we communicated at that time, our original API service was scheduled to be decommissioned.  As of May 27, 2009, calls to the original API service will fail unless changes to your application code and API URL are made.

WHAT’S NEW WITH THE API?

New API calls for:

  • Matching signatures to content indexes (Wikipedia, our News and Blog collection, Amazon products, YouTube videos and Photos)
  • Concept tags derived from Semantic Signatures
  • Text categorization

Usage reporting – see exactly how much you have used per the API license agreement

HOW THIS UPGRADE IMPACTS YOU:

To prepare you for this migration, we have put together a Migration Guide (http://www.semantichacker.com/support/migration-guide) that will take you through the minimal requirements needed to keep your application running. The new API is already available, so you can modify and test your application or even enhance it using the exciting new API calls available to you now.

Again, the current API will be permanently decommissioned on May 27, 2009.

    If you have any questions or concerns regarding this process, please contact us or on the Forum. We will try our best to help you resolve any issues you may encounter within 24 hours.

A reminder that the SemanticHacker Innovators’ Challenge ends Wednesday @ 11:59pm EST. Or…

10:59pm CST

9:59pm MST

8:59pm PST

Best of luck to those of you who have entered or will be entering by the deadline!

The SemanticHacker Innovators’ Challenge is scheduled to end on June 18, 2008 at 11:59pm EST. That’s just 14 days from today.

We want to know though – has it been enough time? A Forum topic has been set up for responses here: http://talk.semantichacker.com/javabb/viewtopic.jbb?t=32 or feel free to comment to this blog post.

If we get enough response we may consider a time extension!

Good luck to those of you who have entered already.

The new Semantic Hacker match server exploits the fact that Semantic Signatures® are mathematically related. The original example tools we provided have a “similarity” function. This produces a “score” of how closely related two signatures are.  Often times when writing applications a large set of documents is in hand, and one wishes to find the most closely related documents to some other document. This is exactly how the Wikipedia extension (and the front page demonstration) work.  We used the API to generate a signature for every single Wikipedia page. All 2 million of them. Then, we took those signatures and added them to a match server. Once that’s all done we can get the most closely related Wikipedia articles to any document.

The concept of the match server is the same as using the similarity tool and then sorting by which ones had the highest score.  That’s tedious work and error prone code. We’re providing the match server to speed up application development of ideas that require it.
The match server is also very very fast. It can sift through all those 2 million Wikipedia pages and grab the top matches in less then 10 milliseconds.