The management of information (Knowledge Management, broadly speaking) has its own myths and legends and I think it will be interesting to discuss them in a new category of posts dedicated to what is just a myth and what is actually feasible.

I hope I will be able to write in a way that will be both clear and involving, but I can’t guarantee a regular publishing schedule (every now and then I also have to work), so I appreciate the patience of my readers.

The comprehension of a text performed by a linguistic analysis engine is only a simulation of some aspects of human comprehension, therefore the automatic process and the human process cannot be considered equivalent.  No one knows yet how human comprehension really works (and it seems we are still far from knowing it), therefore we are not able to reproduce it with a software, even in absence of other obstacles.

When I started to think about COGITO^® and automatic comprehension of texts, I selected some aspects of the wider process of human comprehension. Then, with the agreement of engineers, programmers, mathematicians and linguists, I focused on the following:

• analysis of the context and the structure in order to perform the most accurate  disambiguation of the meaning of words having more than one meaning. Identifying the right meaning of words is fundamental to “understanding” the subject of the text;
• analysis of the logical structure of the sentences in order to identify the most relevant elements in the document;
• algorithms to identify the expressive structures that, when recognized, can infer important information from the content.

“I think there is a world market for about five computers.” 

This quote is famous: it’s from 1943 and these are the words of Thomas J. Watson, founder and first chairman of IBM. 

As we all well know, things turned out differently (fortunately for IBM too), and today it is difficult to imagine our life without a computer (or better yet, “computers”: often in addition to the one we use in the office we have one at home full of pictures and a laptop, so we’re ok also when we travel.)

The reasons why we use the computer are many and varied, as are our jobs and interests. Regardless, whether it’s for professional needs or hobbies, when we must deal with knowledge we all tend to share the same negative experience: not being able to manage it.

I’m not speaking about only the business world here, where the problem is crucial for strategic and economic reasons, but also in our everyday life.

How many times do we launch an Internet search without getting any results?

How much time do we waste checking sources only to realize that they contain useless information?

Sometimes we realize that the criteria we have used to organize the files of our computer are ineffective, so we decide to rearrange everything: we merge folders, move files, change names, etc. Then after a few weeks we start to miss our old desktop. Often frantic searches to find a specific email message lead to nowhere.

We follow clues, try to remember, put the pieces together… we type some words and hit “search”; but nothing; the email message was actually about this and that, yet we can’t find it; it was old so maybe it’s in the bin; thank heaven we never empty the bin… ; Tom sent it, so for sure we moved it to the folder with his name, maybe he also sent a copy to Bob…

At least, we can write to Bob, our last and only hope to put an end to this.

If our computers could only be a little smarter (if not intelligent), it wouldn’t be so difficult for us to get the knowledge we need.

We have already solved the basic problem, the diffusion of knowledge, but now it’s time to ask for more: we need a way to use knowledge without too much effort.

Trying to give concrete answers to the many problems related to the management of knowledge through computers is my work; trying to discuss them matter-of-factly, looking at my experience in the development of linguistic technology, semantics and for natural language processing and unstructured knowledge from all angles, as well as talking about products, other technologies, challenges, innovation and future is the goal of this blog.