WordNet

Question 1

Polysemous

Answer 1

having multiple meanings

Question 2

Word sense

Answer 2

A discrete representation of one aspect of the meaning of a word.

Question 3

thesaurus

Answer 3

Database that represents word senses.

Question 4

Antonymy

Answer 4

When two words / lemmas have two opposite meanings.

Question 5

WSD (abbreviation)

Answer 5

word sense disambiguation

Question 6

word sense disambiguation

Answer 6

The task of determining which sense of a word is being used in a particular context.

Question 7

How does WordNet represent different senses of the same word?

Answer 7

with superscript:
mouse¹, mouse² etc.

Question 8

embedding

Answer 8

a point in semantic space

Question 9

glosses

Answer 9

textual definitions for each sense, in dictionaries or thesauruses.

Question 10

Why can a gloss still be useful, even though it is often circular and relies on real-world knowledge that we as humans have?

Answer 10

It is just a sentence, and we can compute sentence embeddings that show something about the meaning of the sense.

Question 11

Zeugma

Answer 11

A conjunction of different readings of a word, for example ‘Air France serves breakfast and the USA’.

Question 12

Synonymy

Answer 12

When two senses of two different words / lemmas are identical.

Question 13

Reversives

Answer 13

A group of antonyms that describe change or movement in opposite directions.

Question 14

Hyponymy

Answer 14

When a word/sense is more specific, denoting a subclass of another word/sense.

Question 15

Hypernymy

Answer 15

When a word/sense describes a less specific or superclass of another word/sense.

Question 16

Superordinate ==

Answer 16

Hypernym

Question 17

Other word for hypernym

Answer 17

Superordinate

Question 18

What does ‘A IS-A B’ mean?

Answer 18

A is an instance of B, or B contains A.

Question 19

Meronymy

Answer 19

A part-whole relation.

Question 20

Holynymy

Answer 20

A whole-part relation. Example: car is a holonym of wheel.

Question 21

Structured polysemy

Answer 21

When the senses of a word are related semantically.

Question 22

Metonymy

Answer 22

A type of polysemy relation. When the use of one aspect of a concept or entity is used to refer to other aspects of the entity or the entity itself.

Question 23

Synset

Answer 23

The set of near-synonyms for a WordNet sense.

Question 24

Supersenses

Answer 24

The lexicographic categories in which senses are grouped in WordNet.

Question 25

Lexical sample tasks

Answer 25

Situations where we just need to disambiguate a small number of words.

Question 26

All-words task

Answer 26

A problem in which we have to disambiguate all the words in some text.

Question 27

Semantic concordance

Answer 27

A corpus in which each open-class word in each sentence is labeledwith its word sense from a specific dictionary or thesaurus.

Question 28

Most frequent sense baseline

Answer 28

Choose the most frequent sense for each word from the senses in a labeled corpus. Can be quite accurate.

Question 29

One sense per discourse baseline

Answer 29

Not generally used as a baseline, but holds better for coarse-grained senses.

Question 30

How does the 1-nearest-neighbor WSD algorithm produce contextual sense embeddings (v_{s<\sub>) for sense _s_?}

Answer 30

It averages the _n_ contextual representations v_i for each of the _n_ tokens of the sense _s_.

Question 31

How does the 1-nearest-neighbor WSD algorithm produce its output?

Answer 31

It chooses the sense whose embedding has the highest cosine similarity with the target word in context.

Question 32

What class of WSD algorithms does not require labeled data?

Answer 32

knowledge-based algorithms

Question 33

Lesk algorithm

Answer 33

A WSD algorithm that chooses the sense whose dictionary/gloss/definition shares the most words with the target word's neighborhood.

Question 34

WiC (abbreviation)

Answer 34

word-in-context

Question 35

word-in-context task

Answer 35

Given two sentences with a target word in different contexts, the system must decide whether the words are used in the same sense or in different senses.

Question 36

Retrofitting / counterfitting

Answer 36

Methods that learn a second mapping after embeddings have been trained, shifting the embeddings such that synonyms are closer to each other and antonyms are further apart.

Question 37

WSI (abbreviation)

Answer 37

word sense induction

Question 38

Word sense induction

Answer 38

An unsupervised approach to WSD

Question 39

Agglomerative clustering

Answer 39

Type of clustering where each of the _N_ training instances is initially assigned to its own cluster. New clusters are formed bottom-up by merging similar clusters.