POS-Parsing 5

Question 1

What are the 8 POS tags in grammar school?

Answer 1

noun, verb, adjective, adverb, preposition, conjunction, pronoun, interjection

Question 2

The collection of POS tags used is called?

Answer 2

tagset

Question 3

What is a tagset?

Answer 3

A tagset contains all part of speech tags used for a specific corpus and what the tags mean (e.g., VBD = verb in past tense)
• Tags are usually uppercase (DT, ADJ, VBD)
• Similar tags often share a prefix (e.g., V… = related to verbs)
• Tagsets are language-specific and corpus-specific
(e.g., Social media corpora have a tag for emotions)

Question 4

Name two tagsets.

Answer 4

Penn Treebank Tagset and Universal Tagset

Question 5

Name three difficulties of POS tagging?

Answer 5

A word can have multiple POS tags
Most of them are common words
Can be difficult even for experienced human labellers

Question 6

What are homonyms?

Answer 6

Two distinct words that have the same spelling are called homonyms.

Question 7

Sentences that can be derived by a grammar are in the formal language defined by that grammar, and are called?

Answer 7

grammatical sentences

Question 8

Sentences that cannot be derived by a given formal grammar are not in the language defined by that grammar and are referred to as?

Answer 8

ungrammatical

Question 9

In linguistics, the use of formal languages to model natural languages
is called?

Answer 9

generative grammar

since the language is defined by the set of possible sentences “generated” by the grammar

Question 10

What is syntactic parsing?

Answer 10

the task of recognizing a sentence and assigning a syntactic structure to it.

Question 11

Name three types of parsing?

Answer 11

Constituency Parsing
Dependency Parsing
Syntactic Parsing

Question 12

What is constituency parsing?

Answer 12

Constituency parsing aims to extract a constituency-based parse tree
from a sentence that represents its syntactic structure according to a
phrase structure grammar

Question 13

What is dependency parsing?

Answer 13

Dependency grammars focuses on how words relate to other words
Dependency is a binary relation between a head (or: governor) and its dependents.
• The head of a sentence is usually the finite verb.
• Every other word in the sentence depends on it either directly or through a
path of dependencies
Caveat: there are multiple theories for dependency parsing that may yield different results!

Question 14

Why is syntactic parsing important?

Give 2 reasons.

Answer 14

• Grammar checking
• Understand the subject/main verb/object of a sentence; useful in
downstream tasks, e.g. question answering, information extraction

Question 15

What is Chunking?

Answer 15

Chunking is a process of extracting phrases from unstructured text.
• E.g. Instead of just extracting simple tokens which may not represent the
actual meaning of the text, it is advisable to use phrases such as
“South Africa” as a single word instead of ‘South’ and ‘Africa’
separate words.

Question 16

Give some reasons for chunking and areas it is used.

Answer 16

• For entity detection
• Proper names (e.g., Monty Python)
• Definite noun phrases (e.g., the knights who say “ni”)
• Sometimes also indefinite nouns or noun chunks
(e.g., every student or cats)
• Help multiple NLP tasks
• Information retrieval (search engines)
• Text classification
• Sentence simplification/paraphrase
• Summarisation

Question 17

What are named entities?

Answer 17

Named entities are definite noun phrases that refer to specific types of individuals, such as organizations, persons, dates, ..

Question 18

What is the goal of a named entity recognition (NER) systems? And what are NERs useful for?

Answer 18

is to identify all textual mentions of named entities
• Two steps
• Identify the boundaries of the NE (e.g., by NP-chunking)
• Identify the type of the NE (e.g., by Naïve Bayes classification)
• NER is useful for
• Information extraction
• Answering specific questions, e.g. “Who is the president of the US?”
• Instead of retrieving a whole sentence, just present the NE “Joe Biden”

Question 19

Give 4 problems associated with named entity recognition.

Answer 19

• Simple word lookup incorrectly identifies words as NE e.g. location discovery
• Lists with people names or organizations have poor coverage
e.g. Hard to keep up with new people or organizations
• Named entity terms are ambiguous
e.g. May and North are DATE and LOCATION, but can also be PERSON
• Further challenge: multi-word terms
e.g. Stanford University, …

Question 20

Why are POS tags helpful?

Answer 20

• Text to speech (how do we pronounce “abstract”, “lead”, “read”)
• Find phrases ( Article Adj* N à noun phrases)
• Input for downstream NLP tasks (e.g. parsing, chunking, named entity
recognition)

Question 21

Name three ways to design a POS tagger?

Answer 21

Idea 1:
• Collect a large dataset with sentences and their POS tags
• For each word, find its most likely POS tag
• For a new sentence, label each word with its most probable POS tag

Idea 2: Train a classifier
• Most probable POS tag of the word
• Prefixes: irreplaceable, unfortunate, inactive à strong clues for JJ
• Suffixes: fortunately, largely à a strong clue for RB (have exceptions, elderly)
• Capitalization: Meridian, USA, RHUL à a strong clue for NNP
• Other features, e.g. 35-year: digit-NN, a clue for JJ

Idea 3: Utilize contextual information
• Use POS tags of surrounding words as additional features

Question 22

What is syntactic constituency?

Answer 22

Syntactic constituency is the idea that groups of words can behave as
single units, or constituents.

Question 23

What is a context-free grammar?

Answer 23

A context-free grammar (CFG) consists of a set of rules or
productions, each of which expresses the ways that symbols of the
language can be grouped and ordered together, and a lexicon of
words and symbols.

Question 24

How would you identify named entities?

Answer 24

• Simple solution: look up each word in an appropriate list of names
• Doing this blindly has problems, e.g. with location discovery

Reading is also a place but can also be seen as reading a book.

Question 25

What is used for named entities and chunking in python?

Answer 25

spacy