I haven’t had a chance to test-drive Twine, which is Radar Networks’ still-unreleased “Revolutionary Semantic Web Application,” but I’ve read Tim O’Reilly’s writeup based on a demo he saw, and I’ve been meaning to amplify something that appeared in a comment there. Jeffrey Carr wrote:
I really don’t see anything unique in what Twine has released so far. ClearForest, for example, has offered a Firefox add-on that does the same entity extraction for any web page that your Twine screenshot illustrates, and they had that available several months ago.
Like Tim O’Reilly I’ll reserve judgment on Twine until I’ve tried it myself, and seen it operate at scale. I did, however, recently try the Firefox extension that Jeffrey Carr mentions. It’s called Gnosis, from ClearForest, a company recently acquired by Reuters.
Here’s a picture of Gnosis summarizing Tim’s posting:
Gnosis finds and highlights entities — that is, companies, people, products, and industry terms. Here’s an expanded view of the industry terms, products, and technologies it extracted:
I’d love to see this kind of entity extraction turn into a commodity service that we can wire into our existing email, blogging, social networking, and social bookmarking systems. Being able to easily express, in all those contexts, that twine refers to the company, or the product, not the strong kind of string, would be a huge win.
October 26, 2007 at 9:51 am
> I’d love to see this kind of entity extraction turn into a commodity
>service that we can wire into our existing email, blogging, social
> networking, and social bookmarking systems.
You will see that a lot of this is already covered by Jiglu.com, which plugs staight into blogs
October 30, 2007 at 11:42 pm
[...] Jon Udell in a post commenting on Tim O’Reilly’s review of Twine talks about entity extraction and a firefox plugin called Gnosis. I had heard about Gnosis before, but only looked at it askance. However, Jon’s post made me take a second look, and all I can say is WOW. Take a look at the screenshot below. It shows the features that Gnosis extracted from my blog post on pharma futurology. The interesting thing is not the actual results, but the concept. If you could do the Freebase thing, and add additional information which gets stored in a dictionary somewhere, you have that much power available to you. Just as a note, for more complex pages, Gnosis is not always accurate, but the potential is obvious. You can also perform additional queries based on the extracted features. There will come a time when the options available will be that much more powerful. Adaptive Blue’s BlueOrganizer also takes a similar approach, recognizing books, websites, etc. Click for larger image [...]
November 1, 2007 at 7:09 pm
[...] Jon Udell in a post commenting on Tim O’Reilly’s review of Twine talks about entity extraction and a firefox plugin called Gnosis. I had heard about Gnosis before, but only looked at it askance. However, Jon’s post made me take a second look, and all I can say is WOW. Take a look at the screenshot below [PMR: omitted here]. It shows the features that Gnosis extracted from my blog post on pharma futurology. The interesting thing is not the actual results, but the concept. If you could do the Freebase thing, and add additional information which gets stored in a dictionary somewhere, you have that much power available to you. PMR: And OSCAR does pretty much the same for chemistry. Maybe the way forward is a mashup of domain-specific engines in a single framework. I’d certainly like to see the context added. There is so much experimentation to be done – and like all experiments we have to expect failures as well as successes. But the cost of each is getting less. [...]
May 1, 2009 at 10:25 am
At Orchestr8, we’ve been bringing Entity Extraction and other text mining capabilities “into the cloud”. Developers can utilize our REST api or SDKs to integrate natural language processing capabilities into their apps.
AlchemyAPI supports 6+ spoken languages (English, French, ..), extraction of dozens of entity types, disambiguation support, text classification, etc.
Other worthwhile Entity Extraction solutions include those from BasisTech and Teragram.