Natural Language Processing

Dr. Hiteshwar Kumar Azad

Email ID: [email protected]
SCOPE
 Assessment Methods

Assessment Max. Weightage

type Marks
Quiz 1 10 10
Assignment 1 10 10
Assignment 2 10 10
CAT – I 50 15
CAT – II 50 15
FAT 100 40

Dr. H. K. Azad
Natural Language Processing
• Syllabus–Textbooks

1/24/2024 NLP 3
Motivation for NLP

• Understand language analysis & generation

• Communication
• Language is a window to the mind
• Data is in linguistic form
• Data can be in Structured (table form), Semi
structured (XML form), Unstructured (sentence
form).

4
1/24/2024 5
Introduction to Natural Language Processing
(NLP)
• NLP is the intersection of Linguistic Science, Computer
Science and Artificial Intelligence.
• It deals with the processing and understanding of human
languages by computer.
• The process of computer analysis of input provided in
a human language (natural language), and conversion
of this input into a useful form of representation.
• The field of NLP is primarily concerned with getting
computers to perform useful and interesting tasks
with human languages.
• The field of NLP is secondarily concerned with helping
us come to a better understanding of human
language.
1/24/2024 6
 Introduction to Natural Language Processing
(NLP)
• A natural language is a human spoken language, such as
English Arabic, French, … etc.
• One of the aims of Artificial Intelligence (AI) is to build
machines that can "understand" commands in natural
language, written or spoken.

• A computer that can do this requires very powerful hardware

and sophisticated software.
• At the present time, this is at the early stages of development.

1/24/2024 NLP 7
 Introduction to Natural Language Processing
(NLP)
• It is not an easy task to teach a person or computer a natural
language.
• The main problems are syntax (the rules governing the way in
which words are arranged), and understanding context to
determine the meaning of a word.

• To interpret even simple phrases requires a vast amount of

knowledge.
• The basic goal of Natural language Processing is to enable a
person to communicate with a computer in a language that
they use in their everyday life.

1/24/2024 NLP 8
 Introduction to Natural Language Processing (NLP)

• Natural language are those that we use for communicating with

each other, eg. Arabic, English, French, Japanese, etc.
• Natural language are expressive and easy for us to use.

• Computer languages are those that we use for controlling the

operations of a computer, eg. Prolog, C, C++, C#, Java,
Python,…, etc.
• Computer languages are easy for a computer to understand,
but they are not expressive.

1/24/2024 NLP 9
1/24/2024 10
1/24/2024 11
1/24/2024 12
1/24/2024 13
1/24/2024 14
 Applications for Natural Language Processing : Summary

• Machine Translation
• Fact Extraction.
• Information Retrieval / Search Engines:
• Retrieval, Categorization, Filtering, Summarization
• Question Answering Systems
• Speech Recognition & Spoken Language Understanding
• Intelligent Tutoring Systems
• Database Query Interfaces

1/24/2024 NLP 15
 Major NLP Accomplishments

• Chomsky (1957) Syntactic Structures

• Weizenbaum (1966), ELIZA
• Woods (1967), Procedural semantics
• Thorne et al. and Woods (1968-70), ATNs
• Winograd (1970), Shrdlu
• Colby, Weber & Hilf, 1971; Colby, 1975,PARRY
• Wilks (1972), Preference semantics
• Woods et al. (1972), LSNLIS / Lunar
• Charniak (1972), Frames and demons
• Wilks (1973), Stanford machine translation project
• Montague (1973) IL semantics (Montague Grammar) in PTQ
• Grosz (1977), Focus in task-oriented dialogues
1/24/2024 NLP 16
 Major NLP Accomplishments

• Marcus (1977), Deterministic parsing

• Cohen, Phil (1979), Planning speech acts
• Allen (1980), Understanding speech acts
• McDonald (1980), MUMBLE
• Heim/Kamp (1981) Discourse Representation Theory
• McKeown (1982), TEXT
• Appelt (1982), KAMP (Integration of Functional Grammar with
Discourse Plans)
• Shieber (1984) Non context freeness of NL syntax proven
• Pollack (1986), Plan inference
• Mann & Thompson (1987), Rhetorical Structure Theory

1/24/2024 NLP 17
NLP Terminology

1/24/2024 18
 Processing Stages in NLP System

• Phonological Analysis
• Morphological or Lexical Analysis

• Syntactic Analysis

• Semantic Analysis
• Pragmatic Analysis

1/24/2024 NLP 19
Processing Stages in NLP System
(1) Phonological Analysis
• Phonetics: deals with the physical building blocks of a language
sound system.
Ex. sounds of ‘k’, ‘t’ and ‘e’ in ‘kite’
• Phonology: organization of speech sounds within a language.
Ex. (1) different ‘k’ sounds in ‘kite’ vs ‘coat’
(2) different ‘t’ and ‘p’ sounds in ‘top’ vs ‘pot’

1/24/2024 NLP 20
Five Processing Stages in NLP System

(2) Morphological or Lexical Analysis

• Morphology is the structure of words. Morphological analysis is a method
for investigating and structuring the possible relationships within a
complex problem.

• It is concerned with inflection. (i.e The various forms of the same basic
word. eg. run-ran, dog-dogs, etc)

• It is also concerned with derivation of new words from existing ones, eg.
lighthouse (formed from light & house).

• In NLP, words are also known as lexicon items and a set of words form a
lexicon.

1/24/2024 NLP 21
 Processing Stages in NLP System
(2) Morphological Analysis

• Any NL analysis system needs a lexicon {a module that tells what words
there are and what properties they have}.

• Simplest model is a full form dictionary that lists every word explicitly.

• Simply expanding the dictionary fails to take advantages of the regularities.

• No dictionary contains all the words, one is likely to encounter in real input.

• Languages with highly productive morphology (e.g. Finnish, where a verb

can have many thousands of forms.)

• Noun combination.

1/24/2024 NLP 22
 Processing Stages in NLP System

(3)Syntactic Analysis
• Syntactic analysis is concerned with the construction of sentences.

• It involves analysing the meaning of words and phrases to understand the purpose of a
sentence or paragraph.

• Syntactic structure indicates how the words are related to each other.

• Syntax tree is assigned by a grammar and a lexicon. Lexicon indicates syntactic category of
words.

• Grammar (typically Context Free Grammer) specifies legitimate concatenations of

constituents.

1/24/2024 NLP 23
 Processing Stages in NLP System
(4)Semantic Analysis
• Semantic analysis is concerned with the meaning of the languages.

• This stage uses the meanings of the word to extend and perhaps disambiguate the result
returned by the syntactic parse.

• The first step in any semantic processing system is to look up the individual words in a
dictionary (or lexicon) and extract their meanings. Unfortunately, many words have
several meanings, for example, the word ‘diamond’ might have the following set of
meanings:
(1) a geometrical shape with four equal sides.
(2) a baseball field
(3) an extremely hard and valuable gemstone
• To select the correct meaning for the word ‘diamond’ in the sentence John saw Susan's
diamond shining across the room.

1/24/2024 NLP 24
 Processing Stages in NLP System
(4)Semantic Analysis

• It is necessary to know that neither geometrical shapes nor baseball fields shimmer,
whereas gemstones do (process of elimination).

• The process of determining the correct meaning of an individual word is call word
sense disambiguation or lexical disambiguation.

• It is done by associating, with each word in the lexicon, information about the
contexts in which each of the word’s senses may appear.

• Each of the words in a sentence can serve as part of the context in

which the meanings of the other words must be determined.

1/24/2024 NLP 25
 Processing Stages in NLP System
(5)Pragmatic Analysis
• Pragmatic analysis focuses on the effects of context on meaning.
• An important analysis for understanding texts and dialogues.
• There are many important relationships that may hold between phrases and
parts of their discourse context, as outlined below.

Identical entities. Consider :

• Bill had a red balloon.
• John wanted it.
• The word ‘it’ should be identified as referring to the red balloon. References
such as this are call anaphoric or anaphora.

1/24/2024 NLP 26
 Thanks

1/24/2024 27