Page 149 - DCAP506_ARTIFICIAL_INTELLIGENCE

Unit 11: Natural Language Processing

4. Discourse Integration: The meaning of an individual sentences may rely on the sentences Notes
that head it and may affect the meanings of the sentence (may rely on the sentences that
come first) that chase it.
5. Pragmatic Analysis: The structure displaying what was said is reinterpreted to verify that
what was in fact meant.

Example: The sentence “Do you know what time it is?” should be deduced as a request
to be informed the time.
These steps are discussed in detail as below.

11.2.1 Morphological Analysis

As a problem structuring and problem solving technique, morphological analysis was designed
for multi-dimensional, non-quantifiable problems where causal modeling and simulation do
not function well or at all. Zwicky developed this approach to address seemingly non-reducible
complexity. Using the technique of Cross Consistency Assessment (CCA) (Ritchey, 2002), the
system however does allow for reduction, not by reducing the number of variables involved,
but by reducing the number of possible solutions through the elimination of the illogical
solution combinations in a grid box. From Wikipedia, the free encyclopedia.

What is “Morphological Analyzer” and How it Related to Search Engines?

A morphological analyzer is a program for analyzing the morphology of an input word, the
analyzer including a recognition engine, identifying suffixes and finding a stem within the input
word algorithms. Morphological analyzers are using lexicon/thesaurus, keep/stop lists, and
indexing engines for their process. Google using morphological analysis across all its products.

Example: Broad Match: This is the default option. If you include general keyword or
keyword phrases – such as tennis shoes – in your keyword list, your ads will appear when a
user’s query contains tennis and shoes, in any order, and possibly along with other terms. Your
ads will also automatically show for expanded matches, including plurals and relevant variations.
Because broad matches are sometimes less targeted than exact or phrase matches, you should
create keyword phrases containing at least two descriptive words each.

11.2.2 Syntactic Processing

This level concentrates on scrutinizing the words in a sentence so as to reveal the grammatical
arrangement of the sentence. This needs both a grammar and a parser. The output of this level
of processing is a (perhaps delinearized) demonstration of the sentence that discloses the structural
dependency relationships among the words. There are numerous grammars that can be utilized,
and which will, in turn, impact the choice of a parser. Not all NLP applications require a full
parse of sentences, thus the remaining challenges in parsing of prepositional phrase attachment
and conjunction scoping no longer stymie those applications for which phrasal and clausal
dependencies are adequate.

!
Caution Syntax transmits meaning in most languages since order and dependency
contribute to meaning.

LOVELY PROFESSIONAL UNIVERSITY 143