SlideShare a Scribd company logo
2
Most read
3
Most read
6
Most read
BİL711 Natural Language Processing 1
What is Natural Language Processing (NLP)
• 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.
BİL711 Natural Language Processing 2
Forms of Natural Language
• The input/output of a NLP system can be:
– written text
– speech
• We will mostly concerned with written text (not speech).
• To process written text, we need:
– lexical, syntactic, semantic knowledge about the language
– discourse information, real world knowledge
• To process spoken language, we need everything required
to process written text, plus the challenges of speech
recognition and speech synthesis.
BİL711 Natural Language Processing 3
Knowledge of Language
• Phonology – concerns how words are related to the sounds that
realize them.
• Morphology – concerns how words are constructed from more
basic meaning units called morphemes. A morpheme is the
primitive unit of meaning in a language.
• Syntax – concerns how can be put together to form correct
sentences and determines what structural role each word plays in
the sentence and what phrases are subparts of other phrases.
• Semantics – concerns what words mean and how these meaning
combine in sentences to form sentence meaning. The study of
context-independent meaning.
BİL711 Natural Language Processing 4
Language and Intelligence
Turing Test
Computer Human
Human Judge
• Human Judge asks tele-typed questions to Computer and Human.
• Computer’s job is to act like a human.
• Human’s job is to convince Judge that he is not machine.
• Computer is judged “intelligent” if it can fool the judge
• Judgment of intelligence is linked to appropriate answers to
questions from the system.
BİL711 Natural Language Processing 5
NLP - an inter-disciplinary Field
• NLP borrows techniques and insights from several disciplines.
• Linguistics: How do words form phrases and sentences? What
constraints the possible meaning for a sentence?
• Computational Linguistics: How is the structure of sentences are
identified? How can knowledge and reasoning be modeled?
• Computer Science: Algorithms for automatons, parsers.
• Engineering: Stochastic techniques for ambiguity resolution.
• Psychology: What linguistic constructions are easy or difficult for
people to learn to use?
• Philosophy: What is the meaning, and how do words and
sentences acquire it?
BİL711 Natural Language Processing 6
Knowledge Representation for NLP
• Which knowledge representation will be used depends on the
application -- Machine Translation, Database Query System.
• Requires the choice of representational framework, as well as the
specific meaning vocabulary (what are concepts and relationship
between these concepts -- ontology)
• Must be computationally effective.
• Common representational formalisms:
– first order predicate logic
– conceptual dependency graphs
– semantic networks
– Frame-based representations
BİL711 Natural Language Processing 7
Discourse
• Discourses are collection of coherent sentences (not arbitrary set
of sentences)
• Discourses have also hierarchical structures (similar to sentences)
• anaphora resolution -- to resolve referring expression
– Mary bought a book for Kelly. She didn’t like it.
• She refers to Mary or Kelly. -- possibly Kelly
• It refers to what -- book.
– Mary had to lie for Kelly. She didn’t like it.
• Discourse structure may depend on application.
– Monologue
– Dialogue
– Human-Computer Interaction
BİL711 Natural Language Processing 8
Natural Language Generation
• NLG is the process of constructing natural language outputs from
non-linguistic inputs.
• NLG can be viewed as the reverse process of NL understanding.
• A NLG system may have two main parts:
– Discourse Planner -- what will be generated. which
sentences.
– Surface Realizer -- realizes a sentence from its internal
representation.
• Lexical Selection -- selecting the correct words describing the
concepts.
BİL711 Natural Language Processing 9
Machine Translation
• Machine Translation -- converting a text in language A into the
corresponding text in language B (or speech).
• Different Machine Translation architectures:
– interlingua based systems
– transfer based systems
• How to acquire the required knowledge resources such as
mapping rules and bi-lingual dictionary? By hand or acquire
them automatically from corpora.
• Example Based Machine Translation acquires the required
knowledge (some of it or all of it) from corpora.

More Related Content

PPT
NLP AI process of computer language analysis getting computers
PPT
Nlp--- --nlu -----nlg lec01-overview.PPT
PPT
CNN for NLP using text analysis by using deep learning
PPTX
Chapter #1 Introduction to NConfigure and administer Server LP.pptx
PDF
An Overview Of Natural Language Processing
PPT
PPT
PPTX
NATURAL LANGUAGE PROCESSING AA PPT1.pptx
NLP AI process of computer language analysis getting computers
Nlp--- --nlu -----nlg lec01-overview.PPT
CNN for NLP using text analysis by using deep learning
Chapter #1 Introduction to NConfigure and administer Server LP.pptx
An Overview Of Natural Language Processing
NATURAL LANGUAGE PROCESSING AA PPT1.pptx

Similar to Overview of Knowledge Representation for NLP (20)

PPTX
Computational linguistics
PPT
1004-nlp.ppt
PPTX
Natural Language Processing (NLP)
PPTX
Natural Language Processing.pptx
PPTX
naturallanguageprocessingnlp-231215172843-839c05ab.pptx
PPTX
natural language processing help at myassignmenthelp.net
DOCX
Natural Language Processing an introduction
PPT
introduction to natural language processing(NLP).ppt
PPTX
1 Natural Language Processing-Intro.pptx
PPTX
nlp-01.pptxvvvffffffvvvvvfeddeeddffffffffff
PPTX
NLP 1.pptx
PPTX
Computational Linguistics.pptx in the field of language change
PDF
Natural Language Processing from Object Automation
PPT
Intro 2 document
PDF
introduction to natural language processing
PPTX
Natural Language Processing - Lecture.pptx
PPT
natural-language-processing.ppt
PPTX
NLP-ppt.pptx nnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnn
PPTX
Introduction to Natural Language Processing
PPTX
Natural-Language-Processing -Stages and application area.pptx
Computational linguistics
1004-nlp.ppt
Natural Language Processing (NLP)
Natural Language Processing.pptx
naturallanguageprocessingnlp-231215172843-839c05ab.pptx
natural language processing help at myassignmenthelp.net
Natural Language Processing an introduction
introduction to natural language processing(NLP).ppt
1 Natural Language Processing-Intro.pptx
nlp-01.pptxvvvffffffvvvvvfeddeeddffffffffff
NLP 1.pptx
Computational Linguistics.pptx in the field of language change
Natural Language Processing from Object Automation
Intro 2 document
introduction to natural language processing
Natural Language Processing - Lecture.pptx
natural-language-processing.ppt
NLP-ppt.pptx nnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnn
Introduction to Natural Language Processing
Natural-Language-Processing -Stages and application area.pptx
Ad

Recently uploaded (20)

PPTX
IBA_Chapter_11_Slides_Final_Accessible.pptx
PPT
Quality review (1)_presentation of this 21
PDF
[EN] Industrial Machine Downtime Prediction
PPTX
mbdjdhjjodule 5-1 rhfhhfjtjjhafbrhfnfbbfnb
PPTX
Introduction to Firewall Analytics - Interfirewall and Transfirewall.pptx
PPTX
Qualitative Qantitative and Mixed Methods.pptx
PDF
Introduction to the R Programming Language
PPTX
Acceptance and paychological effects of mandatory extra coach I classes.pptx
PDF
Galatica Smart Energy Infrastructure Startup Pitch Deck
PDF
Introduction to Data Science and Data Analysis
PPTX
Computer network topology notes for revision
PDF
Mega Projects Data Mega Projects Data
PPTX
AI Strategy room jwfjksfksfjsjsjsjsjfsjfsj
PPTX
iec ppt-1 pptx icmr ppt on rehabilitation.pptx
PPTX
01_intro xxxxxxxxxxfffffffffffaaaaaaaaaaafg
PPTX
Data_Analytics_and_PowerBI_Presentation.pptx
PPTX
Microsoft-Fabric-Unifying-Analytics-for-the-Modern-Enterprise Solution.pptx
PPTX
DISORDERS OF THE LIVER, GALLBLADDER AND PANCREASE (1).pptx
PDF
.pdf is not working space design for the following data for the following dat...
IBA_Chapter_11_Slides_Final_Accessible.pptx
Quality review (1)_presentation of this 21
[EN] Industrial Machine Downtime Prediction
mbdjdhjjodule 5-1 rhfhhfjtjjhafbrhfnfbbfnb
Introduction to Firewall Analytics - Interfirewall and Transfirewall.pptx
Qualitative Qantitative and Mixed Methods.pptx
Introduction to the R Programming Language
Acceptance and paychological effects of mandatory extra coach I classes.pptx
Galatica Smart Energy Infrastructure Startup Pitch Deck
Introduction to Data Science and Data Analysis
Computer network topology notes for revision
Mega Projects Data Mega Projects Data
AI Strategy room jwfjksfksfjsjsjsjsjfsjfsj
iec ppt-1 pptx icmr ppt on rehabilitation.pptx
01_intro xxxxxxxxxxfffffffffffaaaaaaaaaaafg
Data_Analytics_and_PowerBI_Presentation.pptx
Microsoft-Fabric-Unifying-Analytics-for-the-Modern-Enterprise Solution.pptx
DISORDERS OF THE LIVER, GALLBLADDER AND PANCREASE (1).pptx
.pdf is not working space design for the following data for the following dat...
Ad

Overview of Knowledge Representation for NLP

  • 1. BİL711 Natural Language Processing 1 What is Natural Language Processing (NLP) • 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.
  • 2. BİL711 Natural Language Processing 2 Forms of Natural Language • The input/output of a NLP system can be: – written text – speech • We will mostly concerned with written text (not speech). • To process written text, we need: – lexical, syntactic, semantic knowledge about the language – discourse information, real world knowledge • To process spoken language, we need everything required to process written text, plus the challenges of speech recognition and speech synthesis.
  • 3. BİL711 Natural Language Processing 3 Knowledge of Language • Phonology – concerns how words are related to the sounds that realize them. • Morphology – concerns how words are constructed from more basic meaning units called morphemes. A morpheme is the primitive unit of meaning in a language. • Syntax – concerns how can be put together to form correct sentences and determines what structural role each word plays in the sentence and what phrases are subparts of other phrases. • Semantics – concerns what words mean and how these meaning combine in sentences to form sentence meaning. The study of context-independent meaning.
  • 4. BİL711 Natural Language Processing 4 Language and Intelligence Turing Test Computer Human Human Judge • Human Judge asks tele-typed questions to Computer and Human. • Computer’s job is to act like a human. • Human’s job is to convince Judge that he is not machine. • Computer is judged “intelligent” if it can fool the judge • Judgment of intelligence is linked to appropriate answers to questions from the system.
  • 5. BİL711 Natural Language Processing 5 NLP - an inter-disciplinary Field • NLP borrows techniques and insights from several disciplines. • Linguistics: How do words form phrases and sentences? What constraints the possible meaning for a sentence? • Computational Linguistics: How is the structure of sentences are identified? How can knowledge and reasoning be modeled? • Computer Science: Algorithms for automatons, parsers. • Engineering: Stochastic techniques for ambiguity resolution. • Psychology: What linguistic constructions are easy or difficult for people to learn to use? • Philosophy: What is the meaning, and how do words and sentences acquire it?
  • 6. BİL711 Natural Language Processing 6 Knowledge Representation for NLP • Which knowledge representation will be used depends on the application -- Machine Translation, Database Query System. • Requires the choice of representational framework, as well as the specific meaning vocabulary (what are concepts and relationship between these concepts -- ontology) • Must be computationally effective. • Common representational formalisms: – first order predicate logic – conceptual dependency graphs – semantic networks – Frame-based representations
  • 7. BİL711 Natural Language Processing 7 Discourse • Discourses are collection of coherent sentences (not arbitrary set of sentences) • Discourses have also hierarchical structures (similar to sentences) • anaphora resolution -- to resolve referring expression – Mary bought a book for Kelly. She didn’t like it. • She refers to Mary or Kelly. -- possibly Kelly • It refers to what -- book. – Mary had to lie for Kelly. She didn’t like it. • Discourse structure may depend on application. – Monologue – Dialogue – Human-Computer Interaction
  • 8. BİL711 Natural Language Processing 8 Natural Language Generation • NLG is the process of constructing natural language outputs from non-linguistic inputs. • NLG can be viewed as the reverse process of NL understanding. • A NLG system may have two main parts: – Discourse Planner -- what will be generated. which sentences. – Surface Realizer -- realizes a sentence from its internal representation. • Lexical Selection -- selecting the correct words describing the concepts.
  • 9. BİL711 Natural Language Processing 9 Machine Translation • Machine Translation -- converting a text in language A into the corresponding text in language B (or speech). • Different Machine Translation architectures: – interlingua based systems – transfer based systems • How to acquire the required knowledge resources such as mapping rules and bi-lingual dictionary? By hand or acquire them automatically from corpora. • Example Based Machine Translation acquires the required knowledge (some of it or all of it) from corpora.