Computational Linguistics: Lecture 1: Introduction

Computational Linguistics
Lecture 1: Introduction
Dr. Dina Khattab

dina.khattab@cis.asu.edu.eg
Year Work Grading
Mid-Term: 5
Lecture Work: 5
Final Exam: 40
Total: 50
2
AI 2001
I Robot 2004
3
Turing Test (Alan Turing 1950)
Alan M.Turing (1912-1954)

Computing machinery and intelligence. Mind, Vol. LIX. 433-460, 1950
The paper discussed conditions for considering a

machine to be intelligent
Can machines think?”  “Can machines behave intelligently?”
Led to Artificial Intelligence (AI)

• Expert systems 4
Acting Humanly: The Turing
Test
 The Turing test (The Imitation Game):

Operational definition of intelligence.
5
The Turing Test
Turing predicted that roughly by
the end of the twentieth century a
machine with 10 gigabytes of
memory would have around a
30% chance of fooling a human
interrogator after 5 minutes of
questioning 6
What is Computational
Linguistics?
Study of computer processing of

natural languages
7
The field goes by various
names…
 Computational linguistics (CL)
• The science of doing what linguists do
with language, but using computers.
 Natural language processing (NLP)
• The engineering discipline of doing
what people do with language, but
using computers.
8
Science vs. Engineering
What is the goal ?

• Understanding the phenomenon of human
language.
• Building better applications.
9
NLP Problems
1. English sentences are incomplete
descriptions of the information
that they are intended to convey.
 The speaker can be as vague or as precise as they wish.
They can leave out things they believe the hearer already
knows.
e.x. “ The boys are late” ! 10

NLP Problems
2. The same expression can have
different meaning in different
contexts
e.x. “ We need to put an eye on him”

11
NLP Problems
3. There are a lot of ways to say the
same thing.
e.x.
“ Ahmed was born on October 11th”
“Ahmed’s birthday is October 11th” 12
Knowledge of the language..
To write programs that
understand language, we have to
define precisely:
• What the underlying task is and..
• What the target representation
should look like. 13
Knowledge of the language..
Phonetics and Phonology – The study of linguistic
sounds. [in case of spoken language]
Morphology – The study of the meaningful
components of words.
Syntax – The study of the structural relationships
between words.
Semantics – The study of meaning.
Discourse – The study of linguistic units larger than a
single utterance
Pragmatics – The study of how language is used to
accomplish goals.
[All others are needed for written language] 14
Morphological Analysis
Individual words are analyzed into their
components and non-word tokens (punctuation) are
separated from the words.
 Morpheme: smallest linguistic unit that has

meaning
 Morphemes are combined into words
• duck + s = [Nduck] + [plurals]
• duck + s = [Vduck] + [3rd person singulars]
• happiness = [Adjhappy] + [ness] 15
Syntactic Analysis
The study of the structural relationships
between words
e.x. I Saw the man

Man the saw I
16
Semantic Analysis
Different words/structure, same meaning
e.x. She needed to make a quick decision in

that situation.
The scenario required her to make a split-
second judgment.
e.x. I saw the man.

The man was seen by me. 17
Semantic Analysis
Different words/structure, same meaning
I walked by the bank

• … to deposit my check.
• … to take a look at the river.
18
Discourse Analysis
The meaning of an individual sentence may depend
on the sentences that precede or follow it
 Pronoun reference:
“The dog wanted the bone, but Sam threw it
away.”
 Inference and other relations between sentences:
“The bomb exploded in front of the hotel. The
fountain was destroyed, but the lobby was
largely intact.” 19
Pragmatic Analysis
The structure representing what was said
is reinterpreted to determine what was
actually meant.
e.x. I’m afraid, I can’t be able to

help you
I won’t help you 20
Why is CL/NLP hard?
Ambiguity
21
Ambiguity
 I made her duck
have different interpretations….
E.x.
1. I cooked a duck for her
2. I cooked the duck belonging to her
3. I caused her to lower her head or body
4. I waved my magic wand and turned her into
duck ! 22
Ambiguity Analysis
 The words duck and her are
morphologically or syntactically
ambiguous.
 Duck can be a verb or a noun, while

her can be a dative pronoun or a
possessive pronoun. 23
Ambiguity Analysis
 The word make is semantically ambiguous;
it can mean create or cook.
 The verb make is syntactically ambiguous:

• It can be transitive, i.e. taking a single
direct object (e.x. 2),
• It can be ditransitive, i.e. taking two
objects (e.x. 4)
24
Ambiguity Analysis
make can take a direct object and

a verb (e.x 3), meaning that the
object (her) got caused to perform
the verbal action (duck)
25

Computational Linguistics: Lecture 1: Introduction

Uploaded by

Copyright:

Available Formats

Computational Linguistics: Lecture 1: Introduction

Uploaded by

Document Information

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

Computational Linguistics: Lecture 1: Introduction

Uploaded by

Copyright:

Available Formats

Computational Linguistics

Dr. Dina Khattab

Alan M.Turing (1912-1954)

The paper discussed conditions for considering a

Led to Artificial Intelligence (AI)

 The Turing test (The Imitation Game):

Study of computer processing of

What is the goal ?

e.x. “ The boys are late” ! 10

e.x. “ We need to put an eye on him”

 Morpheme: smallest linguistic unit that has

e.x. I Saw the man

e.x. She needed to make a quick decision in

e.x. I saw the man.

I walked by the bank

e.x. I’m afraid, I can’t be able to

 Duck can be a verb or a noun, while

 The verb make is syntactically ambiguous:

make can take a direct object and

You might also like