Chapter Five

NLP(Natural Language
Processing)
 2

What is Language????

Way of Communication
Speaker Listener

9 December
2024
 3

 Natural language processing is the set of methods

for making human language accessible to
computers.
 Natural language processing is the field at the
intersection of Computer science (Artificial
intelligence) and linguistics.

9 December
Artificial Intelligence by Rahman Ali, Lect: QACC,UOP 2024
 4
Example: Conversational

Agent
Conversational agents contain:
 Speech recognition
 Language analysis
 Dialogue processing
 Information retrieval
 Text to speech

9 December
2024
 5
Natural Language Processing
vs Computational Linguistics

 In linguistics, language is the object of study

Computational methods may be brought to bear, just as
in scientific disciplines like computational biology and
computational astronomy, but they play only a supporting
role In contrast, natural language processing is focused on
the design and analysis of computational algorithms and
representations for processing natural human language
The goal of natural language processing is to provide new
computational capabilities around human language: for
example, extracting information from texts, translating
between languages, answering questions, holding a
conversation, taking instructions

9 December
2024
 Difference between Formal
6

and Natural Languages

 Natural languages are the languages that people speak,

such as English, Spanish, and French. They were not
designed by people and they evolved naturally. The
grammar of a natural language is incredibly complex and
discovered through empirical investigation
 Formal languages are languages that are designed by
people for specific applications. For example, the notation
that mathematicians use is a formal language that is
particularly good at denoting relationships among
numbers and symbols. Chemists use a formal language to
represent the chemical structure of molecules.
Java is an example of formal language, an artificial language and the
grammar of an artificial language (like Java) is incredibly simple. We don’t
discover the grammar of an artificial language, we stipulate it — we define it
however we want.

9 December
2024
 Difference between Formal
7

and Natural Languages

Although formal and natural languages have many features in
common — tokens, structure, syntax, and semantics — there are many
differences:
Ambiguity: Natural languages are full of ambiguity, which people deal
with by using contextual clues and other information. Formal languages
are designed to be nearly or completely unambiguous, which means
that any statement has exactly one meaning, regardless of context.
Redundancy: In order to make up for ambiguity and reduce
misunderstandings, natural languages employ lots of redundancy. As a
result, they are often verbose. Formal languages are less redundant and
more concise.
Literalness: Formal languages mean exactly what they say. On the
other hand, natural languages are full of idiom and metaphor.
 Difference Between Natural 8

Language and Computer

Language

 Natural Language >Computer language

 Ambiguous Non-ambiguous
 Context Sensitive Context free
 Informal Formal
 Descriptive Prescriptive
 Unstructured Structured
 Uncontrolled Controlled

9 December
2024
 9

Types of languages

 Natural languages
 Also called:
 Informal language
 Unstructured language
 Non-regular language

 Computer languages
 Also called:
 Formal language
 Structured language
 Regular language

9 December
2024
Ways of Communication b/w
10

Users and Computers

 To Know the language of computer

 Infancy

 To Know a third language

 Youth
 High-level languages

 To communicate through a human

natural language
 Maturity
 (HCI)
 Fifth generation languages

9 December
2024
 11

Natural Language Processing

 Natural language processing (NLP)

is a subfield of artificial intelligence
and computational linguistics. It
studies the problems of automated
generation and understanding of
natural human languages
OR
 Getting computers to understand and
communicate in everyday language is
known as natural language processing.
9 December
2024
 12

Computational Linguistics

 Computational linguistics is an interdisciplinary field

dealing with the statistical and/or rule-based
modeling of natural language from a
computational perspective.

9 December
2024
 13

Major Areas of NLP

 Natural Language Understanding (NLU)

 Natural Language Generation (NLG)
NLP

NLU NLG

9 December
2024
Natural Language
14

Understanding (NLU)

 Natural-language-understanding
systems convert samples of human
language into more formal
representations that are easier for
computer programs to manipulate.
 Natural-language understanding is sometimes
referred to as an AI-complete problem,
because natural-language recognition seems
to require extensive knowledge about the
outside world and the ability to manipulate it.

9 December
2024
Natural Language Generation
15

(NLG)

 Natural-language-generation
systems convert information from
computer databases into normal-
sounding human language.

9 December
2024
 16

Why NLP Hard?

9 December
2024
A tiny Sample of NLP
17

Applications
 18

NLP in Industry
 19

Chatbot:
 20

Applications of NLP….

 Automatic summarization
 Information extraction
 Information retrieval
 Machine translation
 Named entity recognition
 Natural language understanding
 Natural language generation
 Optical Character Recognition
 Question answering
 Speech Processing
 Spoken dialogue system
 Text simplification
 Automatic summarization
21

 Subfield of machine learning and data mining

 process of shortening a text document with software, in order to create a
summary with the major points of the original document.
 find a subset of data which contains the "information" of the entire set.
 Possible for documents, image collections and videos.
 two general approaches: extraction and abstraction.
 Automatic summarization:
22

Types

 Extractive methods work by selecting a subset of existing words, phrases, or

sentences in the original text to form the summary.
 Abstractive methods build an internal semantic representation and then use
natural language generation techniques to create a summary that is closer
to what a human might express. Such a summary might include verbal
innovations.
 extractive methods are appropriate for image collection and video
summarization.
 23

Information extraction

 the task of automatically extracting structured information from unstructured

and/or semi-structured machine-readable documents.
 Recent activities in multimedia document processing like automatic
annotation and content extraction out of images/audio/video could be seen
as information extraction.
 24

Information Extraction
 25

Information Extraction
 26

Information retrieval (IR)

 the activity of obtaining information resources relevant to

an information need from a collection of information
resources.
 Information retrieval is the science of searching for
information in a document, searching for documents
themselves, and also searching for metadata that
describe data, and for databases of texts, images or
sounds.
 Automated information retrieval systems are used to
reduce what has been called information overload.
 Web search engines are the most visible IR applications.
 Other IR systems Solr, Lucene, Elastic Search.
 27

Machine translation

 sometimes referred to by the abbreviation MT is a

sub-field of computational linguistics that
investigates the use of software to translate text or
speech from one language to another.
 28

MT Approaches
 29

Taken from Stanford Online lecture on

Natural Language Processing with Deep
Learning
 Named-entity recognition
30

(NER)

 also known as entity identification, entity chunking and entity

extraction
 subtask of information extraction that seeks to locate and
classify named entities in text into pre-defined categories such
as the names of persons, organizations, locations, expressions of
times, quantities, monetary values, percentages, etc.
 Most research on NER systems has been structured as taking an
unannotated block of text, such as:
Jim bought 300 shares of Acme Corp. in 2006.
 And producing an annotated block of text that highlights the
names of entities:
 [Jim]Person bought 300 shares of [Acme Corp.]Organization in
[2006]Time.
Named-entity recognition
31

(NER)
 32

Optical Character Recognition

 a system that provides a full alphanumeric

recognition of printed or handwritten characters at
electronic speed by simply scanning the form.
 33

An OCR System
 34

QUESTION AND ANSWERING

 Type of information retrieval.

 Given a collection of documents, the system should be able
to retrieve answers to questions posed in natural language.
 Find the answer to a question in a large collection of
documents.
 The main aim of QA is to present the user with a short
answer to a question rather than a list of possibly relevant
documents.
 As it become more and more difficult to find answers on the
WWW using standard search engines, question answering
technology will become increasingly important. 9 December
2024
 35

Speech Recognition

 is the process of converting an acoustic signal, captured by a

microphone or a telephone, to a set of words.
 The recognised words can be used as an input to next system, as for
applications such as commands & control, data entry, and document
preparation. They can also serve as the input to further linguistic
processing in order to achieve speech understanding.
 36

Spoken Dialogue System

 is an automated system that engages in a dialogue with a human user using

spoken language as the medium of interaction.
 1)Task-oriented: involves the use of dialogues to accomplish a task, e.g.
making a hotel booking, or planning a family holiday.
 2)Non-task-oriented: engaging in conversational interaction, but without
necessarily being involved in a task that needs to be accomplished
e.g conversational companion for the elderly.
Perpectivising NLP: Areas of AI and
their inter-dependencies
Knowledge
Search Logic Representation

Machine
Planning
Learning

Expert
NLP Vision Robotics Systems
AI is the forcing function for Computer Science