NLP_Unit 1
NLP_Unit 1
Processing (CS735E01) – 7 th
Semester
Mithun B N
Asst. Prof
Unit 1:
Introduction to
Natural Language Processing
Agenda
• The Study of language
• Applications of Natural language understanding
• Evaluating Language understanding system
• The different levels of language analysis
• Representation and Understanding
The study of Language
• Language is on the fundamental aspects of human behaviour.
• It is a crucial component of our lives.
• It could be written or spoken form:
• Written form would serve as long term record for knowledge from one
generation to the next.
• Spoken form serves as our primary means of coordinating our day-to-day
behaviour with others.
The study of Language (Contd.,) Goals of
NLP research
• Create computational models of language
• Able to specify models that approach human performance in the
linguistic tasks.
• Linguistic tasks are: reading, writing, hearing and speaking.
• Computational model are useful for scientific and practical purposes
• Scientific purpose – nature of linguistic communication
• Practical purpose – enabling effective human machine interaction
The study of Language (Contd.,)
Different academic disciplines
• The linguist – structure of the language
• The Philosopher – how words mean anything at all and not
• The Psycholinguists – process of human language production and
comprehension
• The Computational Linguists – computational theory of language
Applications of Natural Language
Processing
• Text based application
• Dialogue based application
Text Based Applications
• Processing of written text – books, newspapers, reports, manuals,
email messages and so on.
• Finding appropriate documents on certain topics from database of
texts
• Extracting information from messages or articles on certain topics
• Translating documents from one language to another
• Summarizing texts for certain purposes
Text Based Applications (Contd.,)
• All may not use NLP, articles can be retrieved by simple matching
technique.
• Machine translation systems built on pattern matching - fails as it is
inability to use an understanding of content to disambiguate word
senses and sentence meanings
• Instead, produce a representation of meaning of each sentence in one
language and then producing a sentence in the other language that
realizes the same meaning
Dialogue Based applications
• Involve human machine communication
• Question-answering systems, where natural language is used to query
a database
• Automated customer service over the telephone
• Tutoring systems, where the maching interacts with a student
• Spoken language control of the machine
• General cooperative problem solving system
Perhaps I could learn to get along with my mother Tell me more about your family
My mother takes care of me Who else in your family takes care of you?
My father Your father
You are like my father in some ways What resemblance do you see?
The Different Levels of Language
Analysis
• Considerable knowledge about the structure of the language
• what words are, how words are combined to sentences, their meaning.
Different forms of knowledge relevant for NLP:
• Phonetic and phonological knowledge: how words are related to
sounds
• Morphological Knowledge: how words are constructed from
more basic meaning units called morphemes (primitive unit of
meaning in a language)
• Syntactic knowledge: how words can be put together to form
correct sentences and structural roles
• Semantic knowledge: what words mean and how these
meanings combine in sentences to form sentence meanings
The Different Levels of Language Analysis
If I ask you where are you going and you reply – “ I go store”
Representation and Understanding
• Most words have multiple meanings – called as senses.
• Cook – has a sense as a verb and a sense as a noun
• Dish – as a noun and as a verb
Pronouns possessiveness
Number First person Second person Third person
Singular My Your His, her, its
Plural our Your Their