Lecture 1 Flashcards

Introduction to NLP & Levels of Language

1
Q

NLP - Linguistics

A

Formal, structural models of language

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

NLP - Computer Science

A

Internal representations of data and algorithms for efficient processing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

NLP - Artificial Intelligence

A

Computational theory of human language processing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

NLP - Cognitive Psychology

A

Human cognition in language

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

NLP - Statistics

A

Frequencies and probabilities of linguistic patterns

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Computational Linguistics

A

doing linguistics on computers

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Natural Language Processing (NLP)

A

A range of computational
techniques:
* for analyzing and representing
naturally occurring texts at various
levels of linguistic analysis
* for the purpose of achieving
human like language processing
* for a range of particular tasks or
applications

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

NLP Application Areas:
Machine Translation

A

conversion of text from one language to another

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

NLP Application Areas:
Information Extraction

A

populating a database with specific data found in text

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

NLP Application Areas:
Human computer Interfaces

A

NLP assistants, chatbots , interactive querying of databases

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

NLP Application Areas:
Summarization

A

abstraction and condensation of major points

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

NLP Application Areas:
Question Answering Systems

A

provision of best answer to the given question

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

NLP Application Areas:
Information Retrieval / Search Engines

A

provision of documents

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

NLP Application Areas:
Image to Text, Speech to Text and
Text to speech solutions

A

Support

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Data:
Unstructured

A

Data that has no inherent structure and is usually stored as different types of files
eg txt, pdf, images, videos

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Data:
Quasi-Structured

A

Textual Data with erratic formats that can be formatted with effort and software tools
eg JSON (JavaScript Object Notation)

17
Q

Data:
Semi-Structured

A

Textual data files with an apparent pattern, enabling analysis
eg spreadsheets and XML files

18
Q

Data:
Structured

A

Data having a defined data model, format, structure
eg database

19
Q

Why is NLP difficult?

A

Usually people are largely
unaware of the complexity of the
language tasks they perform so
effortlessly (exception: adult

20
Q

Why is NLP difficult?

A
  • Subtleties of meaning
  • Irony, sarcasm, humor, metaphor
  • Ambiguity
  • Ambiguity is a fundamental
    problem of computational
    linguistics
  • Resolving ambiguity is a crucial goal
21
Q

Levels of Language Analysis (1)

22
Q

Levels of Language Analysis (2)

A

Morphological

23
Q

Levels of Language Analysis (3)

24
Q

Levels of Language Analysis (4)

25
Levels of Language Analysis (5)
Symantec
26
Levels of Language Analysis (6)
Discourse
27
Levels of Language Analysis (7)
Pragmatic
28
Transitive: eg Duck
(verb has a noun direct object) eg I cooked [waterfowl belonging to her]
29
Ditransitive: eg Duck
(verb has 2 noun objects) eg I made [her] (into) [undifferentiated waterfowl]
30
Action-transitive eg Duck
(verb has a direct object and another verb) eg I caused [her] [to move her body]
31
Ambiguity at Pragmatic Level eg ‘At what time did you call me?’
Literal Meaning: What time was it? Literal Response: A time (e.g. ’11 am.’)
32
Ambiguity at Pragmatic Level eg ‘At what time did you call me?’
(Pragmatic Meaning: a different question entirely, e.g. Why were you so late? Pragmatic Response: Explain the reason for being so late.)
33
Natural Language Toolkit (NLTK)
A suite of Python libraries for symbolic and statistical natural language programming * Developed at the University of Pennsylvania