1 - Introduction

What is language and communication?
Why process natural language?

"Implementing a natural language understanding program requires that we represent large amounts of knowledge and reason effectively with it."
-- Luger and Stubblefield

In virtually every niche of our planet, there is some interaction.
Everywhere we see entities exchanging information in order to rearrange or to achieve a goal. Now, we want to focus on what is communicated and in which way - in terms of syntax and semantics - the information is actually transferred from A to B. Language is a "complex, structured system of signs (...) that enables humans to communicate".
We already know that communication is aimed at moving information from the sender to the hearer. Obviously, generating sensible utterances (that is: spoken or written strings or texts in any given language) poses no big problem to humans, and to a limited degree, machines can also tell us what we should know about their work.
But, how about extracting the information back from the message? Again, no problem for humans. Machines, on the other side, need some explicit guidance to understand what is told to them. Clearly, user interfaces to computers and other artifacts have improved notably in the last years, but still, it is difficult for certain user groups to have satisfactory access to the offered services. Thus, you need to implement some easier and more intuitive ways to provide this access - natural language, for example.

What's the Problem...

The main problem with natural language is perhaps its ambiguity. Take the following sentence for example: "Time flies like an arrow." Does it mean time flying or creatures known as "time flies" are like an arrow? The computer would need to be able to identify whether "flies" refers to a noun or a verb in order to understand the actual meaning of the sentence. In order for a system to deal with these kinds of ambiguity, it has to know a lot about the world and be able to use that knowledge to the intended effects. Current AI technology has not yet developed to the stage where such large quantity of knowledge could be handled efficiently and effectly. However, by restricting the scope of the language to that required to handle a limited task in a limited domain, performance systems capable of useful natural language communications can be achieved.