The role of natural language in the exploration of an information space

With the computer the flexibility in dealing with the form of written language (editing) and accessing language (retrieving) is extremely emphasized, but in the scientific area of natural language processing, the goal has been much more ambitious: to automatically understand and produce language. In particular, effort has been put in making possible to communicate with a computer, in order to get some desired information. The impact has been very minor, if we consider the way in which the society could change if computers could really take the burden of understanding human language and make information available to all people. It took quite a lot to the scientific community to understand that communicating with a computer through natural language may mean something different from the two basic language modalities we are used too. The so-called teletype approach has also persisted for some time. Only recently have we begun to understand the fact that a larger bandwidth of communication can be established between human and computer. Language can be integrated with images dynamically; the screen itself is not only an output medium but it can become the basis for direct manipulation of all objects involved in the communication. But the point is not only in the interface. Often the user does not know what information is available to him, or he may not have a clear idea of what he is searching for. His attitude may reflect the fact that a lot of flexible information is there