 |
|
|
 |
|
|
|
|
Our Vision
Defining principle
Cataphora's success and very existence are based upon one defining principle. This arose from a conceptual breakthrough that was simply stated, yet proved to be radical in its practical effects. This idea was that, in order to truly understand a document, you have to know about the circumstances in which it arose. In other words, you have to understand its context.
Context within a document
In its simplest manifestation, the context of a word refers to the words surrounding it. This is a lesson we all learn when first we read. And this is the way in which the term is often used. For years, the term context search has been used to mean context within a document. In other words, it does not refer to the context in which a document appears, but rather it says something about the words that constitute the document.
This is not the whole story. The context of a document can't be described by the words within the document. Rather, this context depends on surrounding documents.
Technology improvements
Technologies to address "context" have been improving for years. At first, they were confined to identifying simple co-existence of words which had to be explicitly chosen by the searcher ("keywords"). A further step was to automate this process to some degree. One way to do this is to assume that documents that contain similar groups of words are in some sense "similar". This is sometimes called "concept search", since the idea is that these "similar" documents all address some common concept.
Context between documents
Yet similarity is not the same as significance. And we live and work in a world where short electronic communications such as instant messages and text messages are becoming more common – and more significant. In such a world, it becomes increasingly difficult for software to accurately group documents just on the basis of the words they contain. And, ultimately, the only effective way to understand communications is not by recognizing groups of words within documents, but by identifying the context between documents.
This is the vision being realized and enhanced by Cataphora's patented technology* – the first technology developed specifically to take advantage of the context between documents and to use that information to provide superior review and analysis tools for legal applications.
* United States Patent Number 7,143,091, granted November 28, 2006: Method and apparatus for sociological data mining.
|
|
|
