CHALLENGES IN NLP

Question 1

Main NLP Tasks

Answer 1

Information retrieval (searching through docs)
Document classification
Question answering
Text summarisation
Conversational agents

Many more emerging

Question 2

What is Lexical ambiguity

Answer 2

A word with multiple POS tags
eg can be a verb or a noun
synonymy/ polysemy/ antonymy
I made her DUCK

Question 3

What is Lexical-semantic Ambiguity

Answer 3

a word with different senses
bank : river bank or financial institution

Question 4

What is Syntactic Ambiguity

Answer 4

ambiguity comes from word groupings

Question 5

POS tags

Answer 5

tag we place on a word to define it lexically
noun/pronoun/verb

Question 6

What is an Open class word

Answer 6

In POS tagging
nouns, verbs, adjectives, adverbs

Question 7

What is a Closed class word

Answer 7

In POS tagging
pronouns, prepositions,
auxiliaries, determiners

Question 8

What are features/attributes in word tagging

Answer 8

person, number, tense, aspect, voice

Question 9

What is a grammar

Answer 9

The way we group words

Question 10

What is a transitive verb

Answer 10

The verb requires a noun direct object
She read a book.
They painted the walls.
I love chocolate.

Question 11

What is a di-transitive verb

Answer 11

The verb requires both a direct object and an indirect object to complete its meaning
He gave me a gift.
She sent him an invitation.
We bought her a necklace.

Question 12

What is an action-transitive verb

Answer 12

The verb requires a direct object and another verb
I caused the girl to flinch

Question 13

What is attachment ambiguity

Answer 13

A type of syntactic ambiguity
Where do we attach?
Unclear which part of a sentence a particular word or phrase is grammatically connected to

I saw the man with the telescope

Question 14

What is Coordination ambiguity

Answer 14

A type of syntactic ambiguity
uncertainty about how phrases or clauses are grouped together

Old men and women
Mother and baby in pram hit by car

Question 15

What is local ambiguity

Answer 15

A type of syntactic ambiguity
a particular word or phrase in a sentence is unclear or ambiguous in its interpretation within its immediate context

Police help dog bite victim
The old man the boat

Question 16

What are the main groupings of challenges in NLP

Answer 16

Structuring
Variability of expressions
Ambiguity
Large volume of Data
“Special” expressions
Context, interpretation
Spoken language - much harder when we cant even see the spelling (I or eye)

Question 17

What are “special expressions”

Answer 17

idioms, sarcasm, irony

Question 18

What are the main 2 groups for language resources in NLP

Answer 18

Dictionaries of words/ phrases
Collections of text/speech (corpora)

Question 19

What are dictionaries

Answer 19

Words come with meaing, pronunctiation and how to use it contextually

Question 20

What are corpora

Answer 20

Language in use
(large) collections of linguistic data
may consist of written texts, spoken discourse, samples of spoken or written language
documents/ conversations/ essays

Question 21

What are the types of corpora

Answer 21

Mono vs multi-lingual
General
Specialised
Parallel (two texts translation of each other)

Question 22

What is an unannotated corpus

Answer 22

raw text/speech

Question 23

What is annotated corpus

Answer 23

is a repository of explicit linguistic information (added manually or automatically)
enhanced with linguistic information
(tagging/types)

Inline:
We <VERB>walk</VERB> down the street.
Let’s take a <NOUN>walk</NOUN> in the park

Can range from very simple POS to heavily specialised

Question 24

What are the 4 annotation types

Answer 24

Grammatical (e.g. POS tags, noun/verb phrases)
Semantic (e.g. person, drug)
Pragmatics – language in use (e.g. conversation)
Combined

Question 25

What are the two main reasons for annotation

Answer 25

Training
Train linguists
Researchers in language development
NLP development

Evaluation
Compare NLP results with a manually coded gold standard

Question 26

Annotation agreement

Answer 26

assess the consistency or agreement among multiple human annotators or raters