Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

ai services in analytics > natural language > Flashcards

natural language Flashcards

1
Q

2 things under NLP

A

NLU
NLG

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

topics under NLU

A

phonology
morphology
pragmatics
syntax
semantics

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

what is phonology

A

Part of Linguistics which refers to the
systematic arrangement of sound

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

what is morphology

A

Study of the internal structure of
words that represent the smallest
units of meaning known as
morphemes

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

2 types of morphemes

A

free/base morphemes
bound morphemes

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

what are morphemes

A

words that represent the smallest
units of meaning

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

what is free/base morphemes

A

word cannot
be divided and have meaning by itself
(e.g. table, phone)

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

what is bound morphemes

A

occur as part of
a word after adding prefix or suffix
(e.g. un-happy, cat-s)

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

what is inflectional morphemes

A
  • Changes what a word does in terms of grammar but does not create a new word
  • Still the same word (e.g. run, running,
    ran)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

what is derivational morphemes

A
  • Creates a new word out of base words
  • e.g. re + act = react, act + or = actor
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

what is lexical

A
  • Interpret meaning of individual words
  • Assign most probable part-of-speech (PoS) tags
  • Use various techniques such stemming, lemmatization
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

what is syntax

A
  • Study of the structure of phrases and sentences
  • After PoS tagging is done at word level, words grouped to phrases, then grouped to sentences
  • Sentences show structural dependency between the words
  • Also known as Parsing – uncover phrases that covey more meaning compared to individual words
  • Examines word order, stop-words, morphology and PoS
  • Focus on identifying correct PoS (e.g. frowns on his face, frowns is a noun rather than verb)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

what is semantic

A
  • Determine proper meaning of a sentence by understanding most relevant words to derive concepts
  • If sentence has actor, script, rating, reviews, sentence is about movie
  • Also involves disambiguating words (e.g. bark)
  • Interpret meaning of words or context inside sentence
  • Focus on literal meaning of words
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

what is pragmatic

A
  • Focus on the knowledge or content that comes from outside the content of document (i.e. speaker implied or listener infers) – inferred meaning
  • Pragmatic ambiguity arises when different persons derive different interpretations of the text
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

what is an example of pragmatic vs semantics

A

Example “Do you know what time is it?

  • Semantic: Asking for the current time
  • Pragmatic: Expressing resentment to someone who missed the deadline
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

what are the text preprocessing activities

A

raw documents

tokenization

(case conversion, remove punctuations, normalize text, remove stop words, extract compound terms, strip special characters noises)

data structure (features representing the text)

17
Q

GCP pre trained model supports ?

A
  • Analyse Syntax
  • Analyse Entities
  • Analyse Sentiment
  • Analyse Entities Sentiment
  • Classify Content
18
Q

analyse syntax does 2 operations ?

A
  • Sentence Extraction
  • Tokenisation
19
Q

classify text must have enough tokens to generate a classification

A

True

the classification gives you different topics and their confidence levels

20
Q

what is magnitude and score in analyse sentiment method GCP

A

score
* Indicates overall emotion
* Between -1.0 (negative) and 1.0 (positive)
* Mixed emotions could cancel out

magnitude
* Indicates how much emotional content
* 0.0 to infinity
* Not normalised; each expression of emotion adds up
* Often proportional to length of document
* Essential for comparing between documents to gauge relevant amount of emotional content

21
Q

what are the keys in anlayse entities

A
  • type: Entity Types (UNKNOWN, PERSON, LOCATION, ORGANIZATION, EVENT, WORK_OF_ART, CONSUMER_GOOD, OTHER, PHONE_NUMBER, ADDRESS, DATE, NUMBER, PRICE)
  • salience
  • Importance or relevance of this entity to the
    entire document text
  • Assist information retrieval and summarization
    by prioritizing salient entities
  • Scores closer to 0.0 are less important, while scores closer to 1.0 are highly important
22
Q

what are the keys in analyse syntax

A

Keys in each token
* text
* partOfSpeech
* dependencyEdge
* lemma

23
Q

what are dependency edge field key in the API response for analyse syntax

A

part-of-speech and morphological information are returned within the response’s partOfSpeech field.

For each sentence within the text provided to the Natural Language API for syntactic analysis, the API constructs a dependency tree that describes the syntactic structure of that sentence. The syntactic information are returned within the response’s dependencyEdge field

ai services in analytics (1 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions