| Publications Page
|
![[Previous Page]](/icons/button-back.gif)
![[Table of Contents]](/icons/button-contents.gif)
Section 4.1: Syntactic Analysis
Section 4.2: Semantic Analysis
Section 4.3: Conceptual Dependency
Section 4.4: Expert Systems
Section 4.5: Connected Word Recognition Using
Keywords
Chapter 4
Natural Language Understanding
Natural Language is the language that we use to communicate with other
people, that also can be used as an interface between humans and
machines. Using natural language a user should be able to ask questions
and give commands to computers in a natural way. The computer needs to
understand the questions and commands to answer or perform them. But
what is understanding? The operational definition of understanding is
when a system performs the actions that the user asks. In this
definition it is assumed that the actions chosen by the computer were
the right ones.
Sometimes the system does not respond to every input, it is possible
that it is modifying its internal structures and until some conditions
happen it performs something that is noticeable externally. "To
understand something is to transform it from one representation into
another, where the second representation has been chosen to correspond
to a set of available actions that could be performed and where the
mapping has been designed so that for each event, an appropriate action
will be performed," Rich [16] explains.
The process of understanding natural language can be decomposed into a
number of steps:
- Input Signal - Either speech or text coming from a keyboard. This
input signal is transformed into basic units (words) for the next steps.
- Syntactic Analysis - In this step the input words are tested to
find if they are grouped according to grammatical rules, meaning that
they form grammatically correct sentences.
- Semantic Analysis - In this step the meaning of each word and
sentence is assigned. This one is the most complicated of the three
steps, and unless dealing with a very simple problem domain, it
requires a big knowledge data base about the topic being discussed.
In this chapter we focus our attention on Syntactic and Semantic Analysis.