Page 161 - DCAP506_ARTIFICIAL_INTELLIGENCE

Unit 11: Natural Language Processing

Notes
Example: To put a particular example, let us take the ungrammatical string * teached in
an English text. None of the spell checkers we have attempted recommended the correct form
taught. In a corresponding way, if a foreigner inserts into a Spanish text such strings as * muestrar
or * disponido, the Spanish spellcheckers we have attempted did not provide the forms mostrar
and dispuesto as probable corrections.

Self Assessment

Fill in the blanks:

12. The goal of .............................. is the detection and rectification of typographic and
orthographic faults in the text at the level of word incidence measured out of its perspective.
13. Some people do not recognize the correct spelling of some words, particularly in a foreign
language. Such errors are known as .............................. .
14. The amount of linguistic information required for spell checkers is much superior than for
.............................. .
15. Initially, a spell checker simply detects the strings that are not accurate words in a specified
.............................. language.

11.4 Summary

 Natural language processing is a field of computer science concerned with the interactions
between computers and human (natural) languages.
 The goal of the Natural Language Processing (NLP) group is to design and build software
that will analyze, understand, and generate languages that humans use naturally, so that
eventually you will be able to address your computer as though you were addressing
another person.
 In Syntactic Analysis, Linear sequences of words are malformed into structures that
illustrate how the words associate to each other.
 Syntactic Processing 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 development of object-oriented software starts from requirements expressed
commonly as Use Cases.
 The term discourse includes both spoken and written forms, as well as both monologue
and dialogue, i.e. “discourse” is taken to be the most super ordinate term.
 Coherence might be defined as implicit relations between different parts of the discourse.
Coherence is closely connected to the concept of cohesion, which means explicit markers
of relations between different parts of the discourse.

 The goal of spell checking is the detection and rectification of typographic and orthographic
faults in the text at the level of word incidence measured out of its perspective.

11.5 Keywords

Discourse: The term discourse includes both spoken and written forms, as well as both monologue
and dialogue, i.e. “discourse” is taken to be the most super ordinate term.

LOVELY PROFESSIONAL UNIVERSITY 155