POS tagging Flashcards

1
Q

What is POS

A

Part of speech
a linguistic category of words, which is generally
defined by their syntactic or morphological behaviour
POS explains not what the word is about, but how it is used

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

What are open word classes

A

Constantly acquire new members
verb, noun, adverb, adjective, interjection
e.g. nouns: Internet, blog, Covid,
§ e.g. verbs: to google, to tweet, to self-isolate

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

Two classes for all words in POS tagging

A

open word classes
closed word classes

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

What are closed word classes

A

Generally do not acquire new members
pronouns, prepositions, conjunctions
e.g. prepositions: to, from, in
§ e.g. pronouns: I, you, he/she/it, we, you, they

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

What are content(lexical) words

A

words that carry the content or the meaning of a sentence
open class words

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

What are function words

A

have little lexical meaning, but instead serve to
express grammatical relationships
such as articles (the) or conjunctions (and) can be found in almost any utterance, no matter what it is about
Usually not inflected

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

What is the main issue with POS tagging

A

same word form can have different POS tags depending on the context: walk as a verb or a noun
The main task of POS tagging is to resolve the lexical ambiguities given the context

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

Internal Cues for POS tagging

A

Morphology is used for unknown words
extract-ed -> ed is common for verbs

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

External Cues for POS tagging

A

Using context
I will book a ticket

In this context book is a verb as will is usually follow by a verb

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

What are rule-based taggers

A

Uses a large set of rules
1. Starts with a dictionary
2. Assign all possible tags to words from dict
3. Apply rules to selectively remove tags leaving the correct tag for each word

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

What are stochastic taggers

A

resolve ambiguities by using a training dataset
to estimate the probability of given word having
a given POS in a given context

Considers all possible sequences of tags
Chooses the most probable given the sequence
Requires a trained POS tagged corpus

Want the highest P(t1…tn | w1…wn)

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

Stochastic tagging formula

A

argmax f(x) means the x for which f(x) is maximised

argmax P(POS|word) = argmaxP(word|POS) x P(POS)

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

What is the transition probability

A

what is the probability of tag ti following tag ti-1 (like n-gram does for words)
Eg tags: DT, NN
P(DT |NN) = C(NN,DT) / C(NN)
We are calculating the probability of seeing the DT tag after the NN tag

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

What is the emission probability

A

given a tag ti, how likely is it that the corresponding word is wi
P(is | VBZ) = C(VBZ, is) / C(VBZ)

C(VBZ, is): The count of occurrences where the pos tag is VBZ and the word is ‘is’

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

What are transformation taggers

A

shares features from both rule based and stochastic tagging
rules are automatically induced from a
previously tagged training dataset

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

Steps of transformation taggers

A

start with simple solution to the problem

iteration: apply transformations to get best results, e.g. by correcting errors (from the simple solution)

stop when no more (or little) improvement can be made

Rules for transformation are automatically induced from the training data - learning in the training phase

17
Q

What is the Brill tagger

A
  • at the start, each word is tagged with its most likely tag
  • but errors will appear
  • learn transformations (rules) that correct errors from tagged data
    Once rules are learnt:
    -Apply the intial tagging
    -Apply re-write rules based on the training data

The system can easily be re-trained with new data
(error-driven)

18
Q

How do we evaluate POS tagging

A
  • Accuracy: how many tags we got right
  • Overall error rate
    • on particular tags
    • on particular words
    • tag confusions