Archive for the ‘News’ Category

« Older Entries

TextWise Launches One-Click Findability on the Salesforce App Exchange

12 Jul 2011

The TextWise One-Click Findability application is now available on the Salesforce App Exchange.  If you manage a contact center and/or customer self-service using Salesforce then try this app. Our patented semantic technology uses queries of any length and complexity and directly matches the query to relevant information with one click.  One-Click Findability provides automatic matching of customer queries/cases to the most relevant information in Knowledge, Solutions and/or other information repositories.

Reduce the cost of running your call center with One-Click Findability:

  • Save time and resources
  • Generate consistently-relevant answers to
customer queries in one-click matching
  • Reduce the amount of time agents spend
on calls looking for answers
  • Expedite call deflection through self-service
  • Remove the guesswork from keyword searches
  • Eliminate repetitive key word query
attempts to find answers in your
knowledge repositories.

One-Click Findability provides a host of valuable features: Self-service and/or agented access; Support of all verticals; Federated and/or faceted result sets from multiple repositories; Incorporation of external web content.

Visit textwise.com and click on the One-Click Findability link to learn more.

 

 

Comments Off Posted in General, News, Semantic Signatures by Mary McKenna Read More »

Language, Thought, and Action

3 Mar 2011

The February issue of Scientific American had an article on the latest thinking about the Whorfian Hypothesis, which states that language strongly influences how humans think. This was a hot idea about sixty years ago, but eventually fell out of academic favor because of the lack of hard empirical evidence. Now that evidence is starting to show up, which has some implications for computational semantics.

The standard view on language and meaning has recently emphasized universality. This is to say that the understanding of language is hardwired in our heads, and so any competent human should qualify as an expert in the algorithmic delineation of meaning. The Whorfian hypothesis throws us a curve here in that we now have to consider language along with culture in our models of thought. A single well-crafted taxonomy or other semantic construct will not fit all.

We see something of this problem on the Worldwide Web. As Jimmy Wales noted this past week, the content of the Web, and Wikipedia in particular, is largely created by twenty- and thirty-something males and so is dominated by their interests. A set of semantic categories derived from the Web in general will certainly be insufficient for understanding text on finance or on medicine and may be challenged even when dealing with the pages frequented by twenty- and thirty-something females.

This does not mean that a given semantic scheme is invalid. Each scheme, however, is limited by the vocabulary it covers and in the kinds of distinctions that that it makes. That should be good news for those of us who make their living in computational semantics.

Tags: , , , , ,

Comments Off Posted in General, News, Opinion, Science, semantics by Clinton Mah Read More »

IBM’s Watson — It’s Elementary, My Dear Holmes

17 Feb 2011

Watson, IBM’s Jeopardy computer, is showing everyone that its 900-pound gorilla of trivia and is likely to beat its human opponents. Watson could still do something stupid, but its formidable performance says much about the effectiveness of current natural language processing technology and computation resources.

Although Watson has a knowledge base of millions of documents gleaned from the Web, its weakness is that it really does not understand any of this data. It is just an extremely smart entity extraction system; Watson uses the terms of a Jeopardy clue as a selecting a particular entity as an answer, which of course then has to be phrased as a question. It has to figure what kind of entity to look for and what kind of context that entity would be found in.

In a sense, this is a simple kind of semantic search because it involves scanning its entire knowledge base of documents and scoring contexts statistically. The entities of the right kind in the highest-scoring contexts are then the prime candidates for an answer; and Watson can use their statistics to derive a level of confidence that a given candidate is the right answer. This basically relies heavily on brute computational power.

As can be seen in the Jeopardy competition, brute power can be quite effective. In most of the straightforward questions that one might expect that Google would do well on, Watson can simply outsearch its opponents. It can grab enough right answers in this way to make up for its frequent wrong answers on more subtle questions requiring a deeper understanding. This is as much gamesmanship as it is intelligence.

Now imagine how overwhelming Watson could be if it actually developed some understanding and made far fewer wrong answers. The first step in this direction is in fact quite easy: develop a large set of semantic categories corresponding to how humans understand language. Indexing a knowledge base by such predefined categories would have the immediate effect of simplifying the search process so that documents do not always have to be analyzed at the lowest linguistic level. That should allow the searches to be broader, much like allowing a chess computer to analyze more moves ahead.

We of course are in the business of semantic dictionaries, which provide a quick way of assigning semantic categories to text documents. Hey, Watson. If you are listening, give us a call.

Tags: , , , , , , , , , ,

Comments Off Posted in News, Science, Semantic Search, semantics by Clinton Mah Read More »

Language, Thought, and Reality

19 Oct 2010

Back in the 60′s and 70′s of the last century, the Whorfian hypothesis was a hot subject on college campuses. This was the idea that one’s native language, its syntax and semantics, strongly shaped one’s worldview. For example, Eskimos speaking Inuit supposedly had thirty different words for snow and so had a more complex relationship with their environment than someone speaking English with only one word for snow.

The problem of course is that skiers can make plenty of distinctions about kinds of snow even in English. Despite Whorfian hypothesis being theoretically attractive, it did not square in the end with our actual experience with language. That pretty much took the steam out of the Whorfian hypothesis, but now in the 21st Century, empirical support has been accumulating for a weaker version of it. This was the subject of an article in New York Times Magazine (http://nyti.ms/boqzs5).

The weak Whorfian hypothesis rejects the idea that language establishes an absolute limit on thinking. Thus we can learn about distinctions in types of snow if we really need them. The structure of a language, however, definitely can bias our thinking; and this could have consequences in practical matters like the ranking of retrieved documents. The choice of a particular semantic framework like RDF may therefore affect the performance of an information system in unexpected ways.

So far, experimental results on language and thought have focused on highly specific biases in areas of language like giving spatial directions, assigning gender to nouns, and dividing the spectrum into colors. It seems plausible, though, that this should generalize to the overall semantic problem of dividing up meaning into some kind of compact space. There is more than one way to skin a cat here, and there are probably advantages and disadvantages in each possibility.

A dogmatist might be tempted to argue here that RDF with certain standard taxonomies is the right way and everything else is wrong, but that is probably overreaching. We are not yet savvy enough about semantics to carve tablets in stone about its implementation. At present, one can say only whether a given scheme is optimal in some formal sense; but if it makes no obvious sense to people, then something more comprehendable might be better in the long run even if it is less than optimal.

The weak Whorfian hypothesis forces us to be more honest. If each semantic scheme introduces its own biases, then we need to experiment to see how different approaches work out for a given target application. Given that humans operate with more than one linguistic framework, we should not be so quick to assume than machines can do better at semantics with just a single framework.

Tags: , , , , ,

Comments Off Posted in General, News, Opinion, Science, semantics by Clinton Mah Read More »

Important Notice: Categorization API Service Update Coming

15 Oct 2010

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.

Comments Off Posted in News, Update by Rebecca Povio Read More »

TextWise to Present CRM Use Cases for the SemanticHacker API at The Content Analytics Conference

30 Sep 2010

We’re excited that in just a few weeks our own Anthony Vito will be presenting at Smart Content: The Content Analytics Conference on October 19th. The session, ‘The Value of Semantic Discovery in CRM,’ will use a Salesforce application that highlights the ability for customer service agents to quickly find answers to customer questions in a more efficient, effective manner. Will you be there?

The conference will be held at the Executive Conference Center in New York, explores business challenges, technologies, and solutions in Content Analytics, the world where Content Management & Publishing, Search, and Analytics intersect. The conference is about digital transformation, about enhancing the business value of information, both enterprise content and social media.

You can always follow details on Twitter through @textwise.

Comments Off Posted in News by Rebecca Povio Read More »

A surprising – artistic – use of semantics!

24 Sep 2010

We have a lot of ideas and thoughts about the best fit for our SemanticHacker API. And until today we believed we came up with nearly everything… this one particular use escaped our imagination. The Powerhouse Museum of Science and Design in Sydney Australia has an exhibit called Artefact H10515. The exhibit is powered by an application called Thingalyzer – Thingalzyer uses the TextWise SemanticHacker API as one of the APIs in which to “feed” the project data. From their site:

Thingalyzer is a web application designed to collate, associate and explore everyone’s favourite things. It was designed to interoperate with Artefact H10515, an interactive sculpture at the Powerhouse Museum but it can also operate entirely independently and may also be used to create future art projects.

I found this time lapse video and it looks like quite a bit of work went into it.

If you’re interested to learn what Artefact H10515 consumed on a particular day, they have a calendar in which you can select a date to see the menu.

Our congratulations go out to artist Craig Walsh on this innovative use of semantics!

Comments Off Posted in News by Rebecca Povio Read More »

Attention! TextWise WordPress Plugin for 3.0 Tweak Needed

17 Jun 2010

For those of you using WordPress and the TextWise WordPress plugin, the long anticipated version 3.0 of WordPress has been released.  We’ve been testing our plugin using release candidate versions to get a head start on fixing issues, and we’re working to get a new release of the plugin out that’s compatible with WordPress 3.0. However, we know that our current plugin WILL work with 3.0 with one very minor tweak, which you can do yourself to continue using it until we release the fully functional replacement. WordPress 3.0 contains a change that breaks our Tag functionality. All you have to do to make all of the functionality of the plugin, minus Tags, work again is the following:

1. Log into your Admin Dashboard
2. Click on Settings
3. Click on TextWise
4. Remove the check in the checkbox next to Tags in the “Select TextWise Content Suggestions” section
5. Click on Save Changes at the bottom of the page

That’s it! You will still be able to add tags manually. We’ll have the replacement plugin out to you as soon as possible. And by all means, if you discover an issue, please let us know!

Tags: , , ,

Comments Off Posted in News, qa by Jay Baker Read More »

2010 Semantic Technology Conference

7 May 2010

The 2010 Semantic Technology Conference will take place from June 21 – 25 in San Francisco.

This year our Executive Director of Science, Wen Ruan, will be on the ‘Semantic Social Networking’ panel along with Amit P. Sheth, Professor & Director of Kno.e.sis, Wright State University and Jamie Taylor who oversees data operations at Metaweb Technologies.

This panel will present some approaches and tools that combine semantics with social network data, visualization of relationships, measurement and interactions, and user-generated content analysis. For more on the topics being covered, go to the schedule. The session is scheduled on June 24th from 4:45pm – 5:45pm PST.

Watch a video of last year’s panel that Wen hosted: “Semantic Search: Beyond RDF”

Hope to see you there!

Tags:

Comments Off Posted in News by Rebecca Povio Read More »

TextWise WordPress Plugin 1.0.4 Released!

10 Mar 2010

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!

Comments Off Posted in News, Update by Jay Baker Read More »

« Older Entries