Pragmatics

The easiest way to view the task of pragmatics is as determining an action given the semantics of a request or sentence.

As you might guess, since finding the semantics of a sentence is extremely difficult, determining the pragmatics is even harder.

There is as much amibiguity in this area of NLP as any other, if not more. For example, consider the following question posed to a computer:

• "Do you have the time?"

A syntactically correct answer to this question could be "Yes" although this is clearly not pragmatically correct as the answer required is the actual time.

Conclusions

To enable a computer to perform NLP "properly" it must be given enough world knowledge (it must know everything about everything), or else it must be given the ability to learn. Much current research is centered around giving computers the ability to learn this world knowledge and therefore help make the semantic and pragmatic stages of NLP more feasible.

Creating a full blown dialogue agent is a very hard task, but that shouldn't deter any budding NLP programmers. There is a lot that can be acheived by limiting the domain of knowledge and the vocabularly used, and there are many uses for speech and natural language aware applications

Remember you can visit the Message Store to discuss this essay. Comments are always welcome!. There are already replies in the thread, why not join in?