NLP Chapter 1

1.
Introduction
History of NLP
Generic NLP system
Levels of NLP
1. Knowledge in language processing
Introduction Ambiguity in Natural language
Stages in NLP
Challenges of NLP
Applications of NLP
•Mode of
Language
Communication
NLP
•Artificial
Two Language
types
•Natural language
Natural language
•Two types
Natural •Spoken form
Language •Written form
Why processing??
NLP
•Natural Language Processing
• The process of computer analysis of input provided in a human
language ( any natural language), and conversion of this input into
a useful form of representation.
History of NLP
• 1950- Attempts to automate translation between Russian and
English
• 1960- The work of Chomsky and others on formal language theory
and generative syntax
• 1990- Probabilistic and data-driven models had become quite
standard
• 2000- A Large amount of spoken and textual data become available
History of NLP
• 1950
• The obvious place to look for help was from Linguistics.
• The literature of the 1950s shows a growing awareness of work in
mainstream Linguistics, and
• young researchers in Linguistics joined Machine Translation teams.
• 1960
• John bought a ticket for Mary in the Symphony Hall Booking Office.
• We know from the position of the words John and ticket that John is
the agent instigating the action and that the ticket is the patient (or
object) of the action.
• We know that Mary is the beneficiary of the action because of the
use of the preposition for before her name.
Generic NLP systems
Levels of NLP
Phonology Morphology Syntax
Semantics Reasoning
Levels of NLP
• Phonology
• Speech processing
• Morphology
• The cats are fighting
Levels of NLP
• Syntax/Syntactic
processing
• It is a study of formal
relationships
between words.
• The cat chased the

mouse
• Parts of speech
• The--- determinant
• Cat- noun
• Chase- verb
• Mouse - noun
Levels of NLP
• Semantics
• Determining the meaning of the words
• Bat is flying in the sky

Levels of NLP- reasoning
• To produce an answer to a question which is not explicitly stored in a
database;
• Natural Language Interface to Database (NLIDB) carries out reasoning
based on data stored in the database.
• For example, consider the database that holds the academic
information about student,
• and user posed a query such as:
• ‘Which student is likely to fail in Maths subject?’.
• To answer the query, NLIDB needs a domain expert to narrow down
the reasoning process.
Bat is flying in the sky
[bat, flying, in, sky] [is, the]

Knowledge in Flying ---- fly. (Morphology)
language
[batNN, flyVB, inPP, skyNN]
processing
Bat fly, sky. (dependency / syntactic)
Bat – mammal ( semantics)

Lexical • “The crane is loaded.”
Semantic • “The beak of the crane is very
Ambiguity big.”
Lexical • “She received three silver vessels.

Ambiguity in Ambiguity • “Reena gave a silver talk”
Natural
Language Syntactic
Ambiguity
• “He saw a man with binoculars.”
Anaphoric • “Cat went up the hill. It was

Ambiguity slipery. It got angry”
Ambiguity in Natural Language
Pronoun Translation Parallel Corpus Ambiguity
• “Monkey ate the • “Monkey ate the • “Bank”

banana as it was banana as it was • “उ र ”
hungry.” hungry”
• “Monkey ate the • “माकडा ने केळ खा ल
banana as it was ripe” कारण तो भुकेला होता.”
• “बंदर ने केला खाया
यो॑ क उसे भूख लगी थी
।”
Stages in NLP
Stages in NLP
• Lexical Analysis
• Refer the dictionary and obtain the properties of the word
• Eg: Dog
• Noun
• Take ‘s’ in plural
• Animate
• 4 legged
• carnivore
Stages in NLP
Challenges in Lexical analysis
Stages in
NLP
Syntactic Parsing strategy
Stages of NLP
• Challenges in Syntactic Processing
Stages in
NLP
Stages in NLP- semantic analysis
• John gave book to Mary
• Agent is john
• Object is book
• Mary is recipient
• Challenges:
• Bat/crane/ tank
• Uttar/peru in marathi
Stages in NLP- Disclosure Integration
• Disclosure Integration
• The meaning of any sentence depends upon the meaning of the sentence just
before it. In addition, it also brings about the meaning of immediately
succeeding sentence.
• Example
• Manoj went to the bank. He said it was crowded

Stages in NLP- Disclosure Integration
Stages in NLP - Pragmatics
• During this, what was said is re-interpreted on what it actually meant.
• It involves deriving those aspects of language which require real
world knowledge.
Challenges of NLP • POS tagging
Challenges of NLP
• Pronoun resolution
• a. The thieves stole the paintings. They were subsequently sold.

• b. The thieves stole the paintings. They were subsequently caught.
• c. The thieves stole the paintings. They were subsequently found.
Word sense
disambiguation
Challenges of a. He went to the bank

NLP to withdraw money
b. He went near the

river bank
Applications of NLP
Machine Information Question

translation Retrieval Answering
Sentiment Text
analysis summarization

NLP Chapter 1

Uploaded by

Copyright:

Available Formats

NLP Chapter 1

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

NLP Chapter 1

Uploaded by

Copyright:

Available Formats

1.

Generic NLP system

1. Knowledge in language processing

Introduction Ambiguity in Natural language

Phonology Morphology Syntax

• The cat chased the

• Bat is flying in the sky

[bat, flying, in, sky] [is, the]

Bat – mammal ( semantics)

Lexical • “She received three silver vessels.

Anaphoric • “Cat went up the hill. It was

• “Monkey ate the • “Monkey ate the • “Bank”

• Manoj went to the bank. He said it was crowded

• a. The thieves stole the paintings. They were subsequently sold.

Challenges of a. He went to the bank

b. He went near the

Machine Information Question

You might also like