Nlp

Front 1

study of language at the level of sounds

Back 1

Phonetics

Front 2

study of the combination of sounds

Back 2

phonology

Front 3

study of the patterns of formation of words by the combination of sounds

Back 3

morphology

Front 4

study of how words combine to form phrases, phrases combine to form clauses and clauses join to make sentences

Back 4

syntax/syntactic knowledge

Front 5

concerns the meaning of the words and sentences

Back 5

semantic knowledge

Front 6

extension of the meanings or semantics

Back 6

pragmatic knowledge

Front 7

concerns connected sentences

Back 7

Discourse knowledge

Front 8

nothing but everyday knowledge that all the speakers share about the world

Back 8

word knowledge

Front 9

applications of NLP

Back 9

text analytics

smart assistants

predictive text

machine translation

Front 10

converts unstructured text data into meaningful data for analysis

Back 10

text analytics

Front 11

recognize patterns in speech thanks to voice recognition, then infer meaning and provide a useful response

Back 11

smart assistants

Front 12

predict things to say based on what you type, finishing the word or suggesting a relevant one

Back 12

predictive text

Front 13

generally translating phrases from one language to another

Back 13

machine translation

Front 14

used to specify strings we might want to extract from a document

Back 14

regular expressions

Front 15

putting characters in sequence

Back 15

concatenation

Front 16

used to specify what a single character cannot be by the use of caret^

Back 16

square braces

Front 17

Set of operation that allows us to say things like "some number of as" are based on the asterisk or *

Back 17

Kleene * (cleany star)

Front 18

one or more occurrences of the immediately preceding character or regex

Back 18

Kleene+

Front 19

Process of cleaning your corpus is called

Back 19

Text cleaning

Front 20

Diacritics, often loosely called

Back 20

accents

Front 21

regex has another method, used to remove punctuations from corpora

Back 21

sub() — substitution

Front 22

An international encoding standard for use with different languages and scripts by which each letter, digit, or symbol is assigned with a unique numeric value

Back 22

unicode

Front 23

Combination of words that are shortened by dropping letters and replacing them with apostrophes

Back 23

Contractions

Front 24

Refers to the process of converting a sequence of text into smaller parts known as tokens

Back 24

Tokenization

Front 25

Breaks up text into smaller trunks or segments with more focus information content

Back 25

Segmentation

Front 26

Builds a vocabulary containing g words but are limited to

Back 26

Words

punctuation marks

numbers

Front 27

Carry sentiment and meaning

Back 27

Graphemes

Front 28

Are parts of words that contains meaning in and of themselves

Back 28

Morphemes

Front 29

Word extraction includes

Back 29

One word

pair

triplets

quadruplets

Front 30

Enables your machine to know about "ice cream" as well as the "ice" and "cream" that comprise it

Back 30

n-grams

Front 31

Simplest way to tokenize a sentence is to use white space within a string as the

Back 31

Delimeter

Front 32

Occurrences of tokens in the sentence/ paragraph/corpora

Back 32

One hot vector

Front 33

Word frequency

Back 33

Frequency vector

Front 34

Presence or absence of a particular word in a particular sentence

Back 34

Binary vector

Front 35

When a sequence of tokens is vectorized it loses a lot of meaning inherent in the order of words

Back 35

N grams

Front 36

Common words in any language that occur with the high frequency but carry less substantive information about the meaning of a phrase

Back 36

Stop words

Front 37

Removes suffixes from words in an attempt to combine words with similar meanings together under their common stem

Back 37

Stemming

Front 38

One of the most popular stemming methods proposed in 1980 by a british computer scientist named martin f porter

Back 38

Porter stemming

Front 39

Multilingual as it can handle non-english words

Back 39

Snowball stemmer

Front 40

More aggressive and dynamic compared to the other two stemmers

Back 40

Lancaster stammer

Front 41

Save the rules externally and basically used an iterative algorithm

Back 41

Lancaster stemmer

Front 42

Is way more aggressive than porter stemmer and is also referred to as porter2 stemmer

Back 42

Snowball stemmer

Front 43

Steming algorithm that utilizes regular expression to identify and remove suffixes from words

Back 43

regexp stemmer