infoarch

Wow! I've written some posts about the new Semantic Web wave and here's another surfer: eeggi ! ReadWriteWeb has a nice summary on this new search engine . Eeggi is not live yet. There are demo's on the site. It looks a lot like Powerset , but (from the demo) it seems to be a little smarter. For one it also supports multi-lingual search. Looking forward to the 'live' version of eeggi! By the way: did you also see the demo video's of Searchme ?

I'll continue and round up my posts on "The New Semantic Web wave" . In this post I'll comment on Alex Iskold's posts about the Semantic Web on Read/WriteWeb . The first post is titled "Semantic Web: Difficulties with the Classic Approach" and the second "Top-Down: A New Approach to the Semantic Web" . First of all: Alex, thanks for the insightful posts and the historical overview of the development of the semantic web. Secondly, to my readers, please read Alex's full posts. Summarizing them for you would withhold you of a good overview. They're long posts, but well worth the read. Now to my comments. I really liked the pragmatic approach ("simple semantics") to the long quest for the Semantic Web (refer to figure). I agree with your "new approach" too. Along with the examples you give, I find that Twine and Powerset are applying this new approach, right? They're doing "simple semantics", not waiting ...

Some time ago I was invited to use Powerset , a new natural language search tool! I'll share my experiences with you. The user-interface is wonderful! It’s clear, not clogged, lets you type in comments without moving away from the pa ge, etc. Here are two screenshots to give you an idea. When you start using Powerset you get to watch a couple of short video’s on how Powerset works, how you can use it, what the limitations of this version are, etc. Insightful, good expectation management. (By the way, why not let all be able to see those video's, while they're waiting for invites?) To give you a taste of how Powerset’s natural language search works they’ve created a set of queries to illustrate the power of their semantic index. The reference applications are limited to ‘speech’ (quotes), ‘business’ and ‘arts’. There's an application called Powermouse, which gives us a glimpse into Powerset’s natural language index and lets us see how it extracts struc...

Interesting interview with Nova Spivack , founder of Radar Networks , on Twine , by the Downloadsquad . Twine is about sharing, finding and organizing personal information in one place in a new way. This app addresses information overload most knowledge workers experience. ( Yes, there's money to be made here! , as Phil Windley says.) Spivack says Twine is the next step in knowledge management and communities of practice. All your personal information is tied together in one place. It's something in between Google and Facebook . Using natural language processing they can find places, people and things in your information. You can search in your Twine network for relatedness. The search is based on a user-driven crawler. Later on they will support importing all your information. Money will (possibly) be made using ads. They are slowly letting people use Twine (I'm still waiting…). Twine is about "knowledge networking" as opposed to "social networkin...

Anyway, let’s get back to the new apps. I collected all kinds of information on these tools. Lots of insightful articles have been written on them too. Here’s an overview of the posts: About Twine : Really short video about Twine. Presentation on the Semantic Web and Twine. Techcrunch review of Twine. RoughType review of Twine. O’Reilly Review of Twine. ReadWriteWeb review of Twine. About Powerset : Not too much posts about them lately. Wrote about them before here and here (and pointed to other posts on them). I’ll be posting again about Powerset soon! About TrueKnowledge : ReadWriteWeb review of TrueKnowledge Also check out this panel discussion on the Semantic Web at the Web 2.0 summit titled ‘The Semantic Edge’ with demo’s (although you can’t see them…) of Radar Networks (Twine), Powerset and Metaweb (Freebase). Metaweb kicks of with a demo of Freebase . It’s about opening up the silo’s of data. And creating interconnections between...

There’s (been) a lot of buzz about new Semantic Web and natural language tools the last couple of months (sometimes called 'web 3.0' ...). News about Radar Network’s Twine , Metaweb’s Freebase , TrueKnowledge and Powerset . (I got my invite to Powerset the other day!) This is very interesting. And I’m really curious whether these new apps will take us further than all the Semantic Web and natural language processing promises that were made in the nineties. Then semantic search was promoted and question answering, automatic summarization, etc. Semantic Web, language and speech technology was also hyped by companies like Lernout and Hauspie . After L&H came crashing down it seemed that natural language and speech technology turned quiet, was licking it’s wounds and looking for new approaches. With this in mind I was surprised by the fact that there are several companies attempting to address this market again. And practically at the same time. I’m always curious how ...

Some time ago I posted about an article in TR on Powerset . Mark Johnson from Powerset left a comment and pointed me to a blog post about their first demo . Data Strateg y says: It was basically a PowerPoint with some live demonstration of a few queries where Powerset got much better results than Google. (No surprises there.) Note that all the demos throughout the evening were only searching over Wikipedia. And: The interesting part of the night was the demo station where they allow people to compare search results between Powerset and Google. The queries were limited to the form of “What did ___ say?” and people were welcomed to fill in the blank with famous names. And: After each query, the user was encouraged to vote using one of the three buttons underneath the search box. He could vote that 1) Powerset results were better, 2) Google results were better, or 3) It’s a tie, and the buttons kept track of the counts. In almost all cases, the results were either a tie or Powerset ha...

TR published an article titled: "Building a Better Search Engine" . There's a lot of buzz going on around "beating Google search". Wikia is one of the names that's often mentioned. Powerset is too. (The TR article also mentions Avatar by IBM .) The TR article is disappointing due to the fact that nothing new is mentioned. All the issues in natural language technology (which is part of my educational background) and search mentioned are old (and very difficult). And progress is slow. Up until now, we haven't seen a convincing demo by, for instance , Powerset. They say on their blog they will be demo-ing soon. I know my post sounds cynical, but the fact that I write about this topic is because I really hope search will be improved by companies at Powerset, IBM, etc. Or by older Dutch companies as Irion and Collexis .