Brainscape's Knowledge GenomeTM

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


See full index

NLP > Lexical And Vector Semantics > Flashcards

Lexical And Vector Semantics Flashcards

1
Q

Semantics

A

Linguistic or logical study of meaning

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

Lexical Semantics

A

Is the linguistic study of word meaning

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

Word Lemma

A

Dictionary form of a word

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

Word Senses

A

A word can represent multiple meanings or concepts

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

Word Sense Disambiguation

A

A method to understand the meaning of a word in a specific context

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

Wordform

A

Is a specific form of lemma, sing is a lemma, sing, sung and sang are all word forms

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

Synonyms

A

Words whose sense is identical but are different words

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

Word Similarity

A

Is where two or more words have similar relationships but are not necessarily synonyms

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

Word Relatedness or Association

A

Words that share common connection such as context, but are not similar.

E.g, tea and cup

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

Semantic Field

A

Set of related words from a domain

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

Topic models

A

Can learn automatically associations between words

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

Semantic Frame

A

A set of words including perspectives or participants of a particular event

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

How can semantic frames change?

A

They can change from perspective

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

What is sentiment analysis?

A

Labelling positive or negative meanings to words and sentences

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

What is Representational Learning?

A

The automated learning of useful representations of text

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

What are Vector Semantics?

A

The use of embedding to represent word meaning

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What are embeddings in relation to vector semantics?

A

Vectors representing words in a multidimensional space

18
Q

Example of a sparse embedding?

A

TF-IDF

19
Q

Example of a dense embedding

A

word2vec

20
Q

What is a term document matrix?

A

It is a common way to display words within a sparse embedding

21
Q

In a term-document matrix, what is a vector?

A

It is an array of numbers representing the word frequencies

22
Q

In a term-document matrix, what is a vector space?

A

This is a collection of the vectors

23
Q

What is information retrieval?

A

It is finding a document that matches a set of query terms. Documents and queries are represented as vectors and similarity is calculated

24
Q

What does a term-term matrix show?

A

It shows the number of times a word co-occurs within a specified context window with another word

25
Q

What is the dot product equation to find similarity between two vectors?

A
26
Q

What is the problem with the dot product?

A

It favours longer vectors

27
Q

What is the equation of the normalised dot product (cosine similarity)?

A
28
Q

What does TF-IDF stand for?

A

Term Frequency-Inverse Document Frequency

29
Q

What does Term Frequency (TF) mean?

A

It is the number of times a term occurs in a corpus but is not a good discriminator

30
Q

What does Document Frequency (DF) mean?

A

It is the number of documents a term appears in - Inverse DF is the fraction of total documents a term appears in

31
Q

What is the equation for term frequency?

A
32
Q

What is the equation for IDF?

A
33
Q

Why is TF-IDF good?

A

It is a balance between TF and IDF as TF does not discriminate well, and IDF alone picks terms that hardly ever occur

34
Q

What is the equation for TF-IDF?

A
35
Q

What does PMI stand for?

A

PMI stands for Pointwise Mutual Information

36
Q

What does PMI do?

A

It compares how often words co-occur against what we would expect if they were indpendent

37
Q

What is the equation for PMI?

A
38
Q

What does a positive and negative PMI mean?

A

Positive means they occur more often than if they were independent, negative meaning they occur less often - but negative is unreliable unless you have a large corpus

39
Q

What is Positive PMI (PPMI)?

A

It replaces negative values with zero

40
Q

What is the equation of PPMI?

A
41
Q

Is indirect or direct evaluation better for vector models?

A

Indirect models, using a task-specific performance metric with a better ground truth

42
Q

What are some direct evaluation methods for vector models?

A

Correlation of word similarity to human ratings (global)
Correlation of word similarity to human ratings (per scenario)
Analogy task
Average over multiple embeddings

NLP (20 decks)

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