Amazon Web Services published almost one terabyte of knowledge, databases of different sorts are now available and accessible. Among them we can find US Bureau of Transportation Statistics, DBPedia Knowledge Base, Freebase Data Dump, Wikipedia Extraction and NCBI Genbank. This cloud of information can be processed with ease by creating EBS volume, basing it on the snapshot ID of the data, attaching created volume to a running EC2 instance in the same disk space and adding mount point and mount the EBS volume on the instance. Downloading these inconceivable dataset is not necessary any longer.

This can be found to be the milestone in starting the web cloud computing space. The main use for these cloud will be availing these information for bots, that will process them and support humans with their structured knowledge.

-mw

Have you ever had this problem that while searching you did not reach satisfying results and you did not know what other words you could use to get more precise results? It  is quite often problem I guess. One of the possible solutions is using different kinds of vocabularies, like synonyms. However there are some tools that you can use with pleasure to inspire yourself while working on specific query.

First one is Thinkmap Visual Thesaurus, created in cooperation with EU. It is a multilingual tool (english, german, duth, italian, spanish and french, although english version is most developed) that enables user to see the hierarchy of words related to searched term. User gets map of related words, brenches, synonyms, definitions and subcategories. It was developed as a language learning tool - that is why except for map of words user gets also a lot of grammatical information, but thanks to its innovativeness and usability of knowledge user can expand his or her knowledge about query that is currently conducted. There is just one drawback of Visual Thesaurus - it is a paid service, without paying user can go only with few queries.

Second tool is a Visuword application, developed by Princeton students and researchers. Main idea is simmilar, but… Visuwords presents the map of associations with complete information on the matter of various associations - by arrows in different colours user can lear if the result means for example: word A “is a member of” word B, A “causes” B etc. In visuwords results are also presented in form of thinkmap, after putting cursor on specific node of net of words user get additional information on this word.

Such tools are useful on stage of planning the query before you really start searching. It helps to organize knowledge for analyzing the data you have already gathered, get fresh ideas by expanding the view on particular topic - there can always exist some aspects you did not take into account.

-mw

True Knowledge released new version of its product, you can try freshly improved features and smoothed inequalities. True knowledge as answer search engine aspire to analyse query semantically and serve its users a ready answer.  At the moment TK can connect facts and objects from database of almost 120,000,000 facts and 5,000,000 things. These amount of data is impressive. But is it enough to give precise answers for all questions that users might like to ask?

Probably it not enough, as long as human’s creativeness is not limited and world still goes round. More important thing is how efficient TK is in analysing queries. It deals quite well with precisely formulated queries like “date of birth of William Shakespeare” but it has problems with “when william shakespeare was born?”. It looks like this is a sort of a law that using semantical search engines users have to use plain equivalent elipsises. However TK sometimes struggles with more complicated questions, the mechanism of narrowing the search or giving the engine some hints on how to interpret your query, it does good work.

If you found answer, you’ve just got from TK, not satisfactory or not true you can take ‘disagree’ option and add knowledge that is more relevant in your opinion. While adding the knowledge TK ask series of questions that avail it to precise how interpret that knowledge - see the screen shot below:

TK has enourmous potential to become one of most accurate answer search engines. Service structure is already well developed, at the moment its owners should face the need of gathering varied gruop of users eager to contribute by expanding databases of knowledge. Bigger amount of data ready to be analysed should eliminate problems with queries interpretation.

To learn more watch True Knowledge video demo below:

-mw

So-called semantic web industry is growing bigger every day. Although it still has not been defined what exactly semantic web mean, there is no week we do not get another semantic tool. It seems like the word semantic became a mantra. Although it is still hard to identify the web services that in fact are semantic. Many of them just have names based on the term. Before we check few quite new semantic tools let’s try to find an answer to the question why do we need semantic text analysis.

In my opinion the reason for starting whole this semantic affair was the need for improvement of queries understanging by search engines and the quality of search results. These two needs are mutually dependent and conditional. That is why the term semantic search - the most exciting combo - has not been embodied yet. Right now people are on the stage of developing automatic semantic analyses of text that would enable both: indexing of huge amounts of semantically analysed text and semantical analyses of queries, formulated as questions. There already exist several services that try to deal with such an analysis.

SemantalyzR is a service that enables getting the page’s content filtered and presented in form of tags, divided in categories such as: names, industry terms, countries, organizations and facilities etc. Unfortunately the engine is not precise enough. For example for DelveInto.Info most of the tags were drawed from the tag cloud, in addition fewof tags were not even separeted from each other, although that in fact they are two separete tags.

SemantalyzR gives also possibility to delve into specific tags to get a set of informations from different services such as twitter, flickr, wikipedia and dooblet. User gets the small compilation of previously analysed sites, where the specific tag was detected. The most interesting thing about that links-list is the fact it contains questions and answers from Yahoo Answers, regarding the searched term.

OpenCalais this tool offers two kinds of services, first is a text converter from simple text to .rdf coded file. It can be useful while making our webpage visible for semantic search engines. The other part of OpenCalais is a plug-in, that installed in our browser (currently only IE and FF available), can underline nouns in the content of currently browsed page with different colours, depending on which category the word was asosciated with. Similar solution was implemented in Mashlogic plugin, I wrote about. OpenCalais also enables to search the term with the most popular search engines, that are displayed in context menu, visible after setting the cursor on underlined term.

Interesting but unfortunately not available for the public tool is one developed by Cortex Intelligence, company specializing in Text Mining for the use of Competetive Intelligence. We can just watch a demo presentation. Its basis is the anlalyses of simple grammar functions and relations between the verbs and other sentence parts. Execpt for quick analyses of actions described in text without the need of reading the text we can also get text sorted to categories such as: date, companies or geographical names. This project is probably most advanced due to its grammar analyses. In fact it seems most semantic among all mentioned above (at least it is possible to make such a statemant basing on its demo).

-mw