NATURAL LANGUAGE PROCESSING ISP610

OUTLINES

❑Overview of Natural Language Processing (NLP)

❑Application of NLP
❑Stages of NLP
 Language used for everyday communication

English Chinese Tamil Espanol Malay

WHAT IS
•Not artificial computer language ( python, c++) NATURAL
LANGUAGE?
•Also the language we use in short text messages (c u
2nite) or on tweets is also, by this definition natural
language.
 ❑Natural Language Processing (NLP) refers to AI method of
communicating with an intelligent system using a natural
language such as English.
❑It is a process of teaching computers:
ohow to understand words mean
ohow to generate human language by understanding how sentences are
constructed
❑Natural Language evolves:
INTRODUCTION oNew words get added - google, selfie
oOld words lose popularity - thou

TO NLP oMeanings of words change -Learn (words such as learn in Old English used
to mean teach)
oLanguage rules change - position of verb
Non-standard English / language.
Segmentation issues
Idioms

PROBLEM IN NLP
Machine Translation
• Translation System
• Google Translate
• Yahoo! Babel Fish
Database Access

Information Retrieval
APPLICATION
• Selecting from a set of documents the ones that
are relevant to a query
OF NLP
• Gmail
• Search Engine
Text Categorization
• Sorting text into fixed topic categories
APPLICATION OF NLP
❑Search Engine
oGoogle, Bing, Yahoo, Ask

❑Extracting data from text

oConverting unstructured text into structure data

❑Spoken language control systems

oNatural Language Assistant (Apple’s Siri)
oQuestion-answering systems, where natural
language is used to query a database (for
example, a query system to a personnel
database)

❑Spelling and grammar checkers

oGrammarly
EXAMPLE S OF NLP USAGE
 Phonetics, Phonology
• How word are pronounce in terms of sequences of sounds

Morphological Analysis
• Individual words are analyzed into their components and non word
tokens such as punctuation are separated from the words.
Syntactic Analysis
• Linear sequences of words are transformed into structures that show

STAGES OF NLP how the words relate to each other.

Semantic Analysis
• The structures created by the syntactic analyzer are assigned
meanings.
Discourse integration
• The meaning of an individual sentence may depend on the sentences
that precede it and may influence the meanings of the sentences that
follow it.
Pragmatic Analysis
• The structure representing what was said is reinterpreted to
determine what was actually meant
 Pronunciation of different
speakers.

Deals with physical building

blocks of language sound system.

Pace of Speech.
PHONETICS
Example:

• I ate eight cake, different 'k' sounds in

'kite', 'coat',
• That band is banned.
• She sells seashells by the seashore.
 Processing of a speech.

Organization of speech sound within

language.

PHONOLOGY Example:
• Bank (finance) v/s. Bank (River).
• They got engaged on March 7th. / The
students were very engaged in the
presentation.
• Her favorite fruit to eat is a date. / Joe took
Alexandria out on a date.
MORPHOLOGICAL ANALYSIS
❑Morphology is the structure of words.
❑Many morphemes are very helpful for analyzing unfamiliar words.
Morphemes can be divided into prefixes, suffixes, and roots/bases.
❑Prefixes are morphemes that attach to the front of a root/base word.
❑Suffixes are morphemes that attach to the end of a root/base word,
or to other suffixes.
❑Roots/Base/Stem words are morphemes that form the base of a word,
and usually carry its meaning.
❑Generally, base words are free morphemes, that can stand by
themselves (e.g. cycle as in bicycle/cyclist, and form as in
transform/formation).
❑Whereas root words are bound morphemes that cannot stand by
themselves (e.g. -ject as in subject/reject, and -vovle as in
evolve/revolve).
SYNTHETIC
ANALYSIS
❑It is concerned with the construction
of sentences.
❑Indicates how the words are
related to each other.
❑Syntax tree is assigned by a
grammar and a lexicon.
LEXICAL ANALYSIS

Obtaining the properties of word.

Example: 'dog' then you can easily bring an image of dog and
its properties like 4 leg, carnivore and animate. These
properties is also matching with another animals like Lion.
 Concerned with the meaning of language and how to
combine words into meaningful phrases and sentences.
The first step in any semantic processing is to look up
SEMANTIC the individual word in the dictionary and extract their
meaning.
ANALYSIS Example:
 The sentence "you have a colorless green ...." would reject as
semantically because colorless and green makes no sense.
DISCOURSE INTEGRATION
The meaning of Individual sentence is depending on previous sentence.
It deals with how the immediately preceding sentence can affect the interpretation of
the next sentence.
Examples:
 Bill had a red balloon.
 John wanted it.
PRAGMATIC ANALYSIS
It deals with using and understanding sentences in different situations and how
the interpretation of the sentence is affected.
Understanding the text and dialogues.
It derives Knowledge from external common-sense information.
Examples:
Do you know what time it is?
oIt does not mean the speaker asking you the time!!!
oWe should understand what to do?
AMBIGUITY IN NLP
Ambiguity can be referred as the ability of having more than one meaning or being understood in more than one way.
Natural languages are ambiguous, so computers are not able to understand language the way people do.
Natural Language Processing (NLP) is concerned with the development of computational models of aspects of human language
processing.
Ambiguity can occur at various levels of NLP. Ambiguity could be Lexical, Syntactic, Semantic, Pragmatic etc.
If an expression (word/phrase/sentence) has more than one interpretation, we can refer it as ambiguous.
Example:
Consider the sentence, “The chicken is ready to eat.”
The interpretations in the above phrase can be, “The chicken(bird) is ready to be fed” or
“The chicken (food) is ready to be eaten.”
Consider another sentence, “There was not a single man at the party.”
The interpretations in this case can be “Lack of bachelors at the party” or
“Lack of men altogether”