Presentation 18.11.2008

Search Engine Thirth Generation

From: Baraika,
1 hour ago

Search Engine Thirth Generation

View SlideShare presentation or Upload your own. (tags: language natural)

my opinion about the natural language search engines

SlideShare Link

True Knowledge - let see

What is that ?

Is new search engine which should help to find easily knowledges contented on web. The goal as they say should be providing consumers with instant answers to complex questions, with a single click.True Knowledge structures data in a way that enables computers to work and think like humans do. Its ambitions are to be a search engine-like consumer site which can answer questions, be used to add knowledge and also be used just like a conventional search engine. The whole True Knowledge would be presented during 2008. Nowadays work True Knowledge as beta version and for access is necessary registration. In other case you are not alowed to see whats going on at all.

How it works?

Technically the system use the knowledge stored in format which it could understand and after decoding the question it´s able to find and code the answer back in natural language. Because the majority of people is nowadays used to write query in short keyword version is also part of this system possibility to use this clasical style of searching, when the system is able to look for two or three keywords and show results or show the short conclusion on the top of the side.

Difference between normal search engine even between natural language search engine is that True Knowledge enables you also to add yor own knowledges. The difference between wiki is that the format of knowledges is in the format understandable for sysetm, not in the natural language as an wiki article, user is forced to add knowledge in forprepared blank. Nowadays is possible to add all real kinds of information, from some reason is not possible to add knowledge about fantastics things as mystical animals and others. The quality of facts is secured by assessing, which is not described in accesible information.But actually this could be the most interesting point of this platform. Because they actually make absolutely new database of knowledges, which probably should be way to assess the content, but on my opinion it´s really huge goal nowadays in competition of web environment...
But if they really would be able to make assessed knowledge database with some relevant garant or institution in background, then it would be really important search tool.

Conclusion
Nowadays is available beta version. And its really hard to get some information from that, because it usually doesnt have answer and ask you for adding information. Which means that there is really a lot of work to fill the database and link it throught.
As a conclusion I could say that it has potential at least the structure of the searching with the use of natural language and the answer which is formulated in natural language as much as its possible.

Powerset - small miracle

What´s that?
Powerset is one of the modern search engines which tries to facilitates the retrieval in Internet as much as is possible. This search engine arose in San Francisco in 2005 and was founded by Foundation Capital, Founders Fund, Paperboy Ventures and other investors. In 2008 was Powerset acquired by Microsoft.
The whole engine is applied on Wikipedia and Freebase that means that the among of information is limited by among of information consist in these databases. This product was launched in May 2008, thus that means that it´s really young, but in my opinion very succesful.

How does it work?
The basic think, which brough me to this search engine is the use of natural language. It is possible to add query in short version, as we are used from classic search engines, as topic or key keyword. But then is here possibility to add normal question in natural language as for example "How many people were evacuated from new orleans during hurricane katrina?" or "How old is Barack Obama?".
System is able to decomposite this natural language structure on necessary keywords containing the meaning of the query and then use traditional fulltext search method. The result is not just the list of the articles in Wikipedia which consist the answer, but also the clear answer on question in the heading, if its possible. Which means if he hasn´t differently information.
Powerset than provides further searching in articles. Is able to extract thetable of contents which is helpful for further searching. Offers two different views on article and also the link to the original article.
The system is always improving. There are such small details as possibility to highlighte the important parts of text and send it to someone else, which means that he get the same text with the same marks in the text. Simply but very worthwile.

Conclusion
Powerset is one of my favourite search engines. You know how I am exacting...
The point is not in the use of natural language, although I was surprised how well it works. The main point and advantige of this search engine is in his sophisticated structure. Its easy, well aranged and with cosy design. It offers tools as table of contents which really helps and make faster the searching.
I am really curious how it will grow on.

Project - consideration

As I said in last artical, my topic for the final essay are searchengines and specially focus on natural language search engines.

First and second generation of search engines
Technologies should help people to make things easily and faster. After the first generation of search engines which were quite complicated and was quit necessary to have a help of the thirth side (librarian or information specialist), because of using special forced language. It was necessary to know how ... Came the second generation of search engines, which was based on the boolean logic and used graphic userfirendly interface. Thats actually search engine which we know from nowadays. I dont think that its necessary to give here an example, because everyone knows them, Google or Yahoo. They are for sure not the only but they are the biggest and the most famous. Nowadays could users quit easily use this kind of interface and most of users are able to work with boolean logic. That means use the basic operators as AND, OR, NOT and keywords. With combination of fulltext search which nowadays promote common search engines.

My own opinion is, that this is good way how to search information. That actually the process of thinking and searching for information is based on simple definitions of keywords and their combinations. Our brain is used to work with these basic forms, always when we create a sentence or other speech, we have to use at least two different ranges: vocabularies and grammar. How we use it depends on our language skills or communication skills. Actually the way of searching information reflect the way of thinking, but it is not process in brain, but the final proces of creating sentence takes place directly in the search engine. The interface of search engines makes this process easier. In the better search engines you could use for exmple suggestions, to see how other people use this or that keyword in which combination, which could help you to create exactly the query.
Conclusion for this is that this way of searching information is used at the begun of thinking and helps to create the right query or sentence directly in the process.

Thirth generation ... ?
Nowadays is very trendy and big tendency to develop new engines based on natural language searching. The idea is that user writes question in the natural language ( mostly in english) and the system decodes the keywords from this sentence and go throught the webpages and use these keywords to find the answer. Problem is that the decoding of the sentence could be quit defficult, because of the basic charakter of natural language which is asymetry. That means that there are different ways how to express the same thing. Then after is the system usually confused and doesnt give the right answer or any answer at all.

If we look at this problematic, we could see that the that here exist two ways of coding and decoding of information. First is in our brain when we have to think out how to create proper sentence which would be system able to answer, then the system decode this sentence back on the basic fundaments and find the answer. During the first coding process of making a sentence
in the brain we have to work just with our knowledges, because the search engines usually cant offer any suggestions. Well in this point I think is the searching much more exhausting than when you could use the clusters or other supports of common search engines.

What say libraries of it?
The use of natural language maybe could help them get older users, because they would feel more comfortable to use the natural language then to use the traditional boolean logic. It could remind more the traditional communication with the librarian. And contrary to the boolean logic search engines the system would speak as a normal human. But is that enought?

More interesting would be implementation of sth. like Trueknowledge which is search engine, which use the natural language, but uses its own knowledge database with the basic in Wikipedia database. I will speak about this engine more later...
Or the system Powerset which helps to scan and make abstract from the webpages and ofer briefly information about the article. Nowadays is oriented just on the Wikipedia articles, but the plan is to extend the focus. This is really nice engine ... and contrary to the others it works quit well ... I also will speak about it in special articel ...

Conclusion
This was just theoretical concideration about the use of natural language in search engines. Just a small theory...

Project

The main project of our course should be something like essay or what ever which should be somehow connected with library 2.0. It will be quit hard for me, but we will see... you know that I am obsessed with searching engines so its no surprise that I will make my essay on such topic. I thought about focus on natural language searching, which is quit trendy today. I actually don´t believe that its so valuable and necessary, because nowadays are people quit used to use boolean logic and so on. And even if I don´t think about HOW to make such kind of search engine, than I always have the question about WHY... But we will see maybe I will change my view ...
Some of them. I would speak about them more but for the begun you could make your own opinion ... :

• true knowledge
• Powerset
• Lexxe
• Start
  

How trendy are Christmas?

Blogpulse is webservice which could measure frekquence or popularity of different discussed topics on blogs. The searching is based on fulltext. That means that it show all texts which mention the searched word, but without any context and any evaluation. The nice example are Christmas. My hypothesis was that there will be nothing interesting about this topic at least during the summer months. I suppossed that there will be slowly increase during september, because Christmas time is comming. But as you can see in the graf, there was rapidly increase of this topic in blog´s articles during the end of June. It was very surprising for me...
After deeper scan of these blog´s articles I found out, that someone created and sent kind of enquiry regarding to books. A lot of people rewrote the list of books and added marks about quality and readability ect. and presented it on their blogs.
And how could it influence the Christmas topic? Easily ... the first book in the list was Christmas Carol of Charles Dickens.

Conclusion
This kind of service is interesting, but actually it doesn´t tell us anything important about context, which is most important. Blogpulse is not the only service which you can use for such measuring. The similar service offer Google Trends. With small difference and that is that they are measure the popularity of keywords used in google search engine.

BlinkList

What´s that ?
BlinkList is one of the web applications which could help you to save your favourite webpages directly on web. You can than access from everywhere to your own blinklist webpage which will content all your bookmarks and favourite webpages. This service is similar to del.icio.us. Nowadays has this application more than 30,000 users. And it´s completely free.

How does it work?
As a guest you can search the public saved links according the tags whose are presented in the tag cloud at the homepage of this application. You can see who and how taged this or that webpage. And look directly on it.
If you want to use this application, you have to make your own profile, which is really easy and contents just necessarily information as name and email. But you have possibility to use a field for description if you want to.
The "blinking" is based on principle of tagging. Everyone could add his own tag for his favourite webpage. All public tags are than given in one tag cloud which is used for searching. Your own tags are desplayed on your profile and you could use it and classify as you wish. BlinkList offer you also possibility to display your tag cloud on your webpages or blog. This cloud is directly connected to your profile at BlinkList. It could help you, if you want to show somehow your interests on your blog.
In the list of links you could see how many people blinked the webpage and what kind of tags they used. This list could be also private and in that case it serves just to you.

Conclusion
Nice way how to make your bookmarks well-arranged. You can have them always when you are connected to web. They offer just simple search tool but I don´t think that in this kind of application is necessary to have advance tools for searching. It should serve primary for you to make a bookmark. And your tag cloud will be well-arranged because you will do it, as you want.

Resources: www.blinklist.com

Ning

What´s that?
Ning was founded in 2004. As its creators say...
they wanted to see what happen if everyone would have
possibility to create his own social network on the Internet.
The result is over 230,000 social networks nowadays. Topics which connect people in different social networks are really miscellaneous. It starts somewhere around cooking, exchange tips for everything, then continues with networks for fans of celebrities or what ever and ends with career or job networks. The scale of topics is really huge.

How does it work?
You can browse through different networks and look in these public ones without any registration. But if you would like somehow participate in some concrete group or create your own network, you have to sign up and create your own profile. The look of the profile or network depends on you. You could use quite a lot different looks and if you are not satisfied with the offer, you always can use your own CSS code. (That i find really progressive.)
The structure of profile is similar to profiles at Facebook. You could add information about your private life as broad as you wish.

The network has possibilty to add different aplications as for example pictures, discussions, videos and others. The webpage of the network is on the Ning platform and the creating, changing or repairing is really easy. I could compare it to a little bit more sophisticated blog. It offers possibility to export data from other aplications like Flickr. There is also possibility to present your network as a group on Facebook, what could help you to wider your community.

I know that I am obsesed with the subject searching, but the search tool in Ning is worse than in SlideShare (viz SlideShare). You could browse in most popular networks or use really simple search tool and use the keywords. There is no sign of any classification and you even can´t choos the category that your network belongs to. There is just something like keywords of your network, but they works more like tags than anything else.

Conclusion
Interesting, how from an experiment could grow up an gigant network like Ning. This aplication is interesting idea and I think that it´s mainly dedicated to people they are looking for entertainment. I can´t imagine how should I find some serious network in the torrent of recipes and Harry Potters fans.

Resource: www.ning.com

SlideShare

What´s that?
SlideShare is world largest community for sharing presentations in the www environment. It contains powerpoint or pdf presentation about different topics. The company is based in USA in California and her biggest investor is Venrock .

How does it work?
It´s possible to go throught webpage, browse, searche, watch slideshows or send them per email. That all you can do from the post of guest, which does not call for registration.
If you really would like to use this "service" with all its odds, you have to sign you up. It´s for free and it enables you to download or upload slideshows from/on the webside, leave comments for whole presentation or for each separate slide (what I find interesting and helpful) and much more...

SlideShare offers traditional simple tool for searching which is based on keywords, you can sort it by relevance or other different classifications. Then you can use the metod of tagging or search according to groups or events.

Groups and events connect slideshows with the same or similar topic, place, time or what ever... and create that kind of subcultur. These subculturs are not just about the slideshows, but in particular about people. Each user could be member of group what ever he wants and share by this way his/her experiences with that topic.

One of the interesting offers is Widget. When you use this package, you could publish presentation from the SlideShare on your own webpages or blog as an inner part of your webpages. Not as appendix or as a link on special webpages. The presentation is simply implemented in your webpages and you can browse through it without the loss of context from your own webpages.

Conclusion
SlideShare looks like really serious webpage, whose goal is not primary to entertain people, but really help and connect them with the relevant information. If I would have possibility to influence the development of this webpage, I would focus on search tools. I miss search tool with focus on subject content.
But I am sure that I could find there a lot of helpful information even with the basic search tool.

Resources: www.slideshare.net