POS Tagging
Let's see what POS tagging is and how we can use it on our NLP applications.
What is POS tagging?
The POS tagging acronym expands as part-of-speech tagging. A part of speech is a syntactic category in which every word falls into a category according to its function in a sentence. For example, English has nine main categories: verb, noun, pronoun, determiner, adjective, adverb, preposition, conjunction, and interjection. We can describe the functions of each category as follows:
Verb: Expresses an action or a state of being.
Noun: Identifies a person, a place, or a thing, or names a particular one of these (a proper noun).
Determiner: Is placed in front of a noun to express a quantity or clarify what the noun refers to—briefly, a noun introducer.
Adjective: Modifies a noun or a pronoun.
Adverb: Modifies a verb, an adjective, or another adverb.
Preposition: Connects a noun/pronoun to other parts of the sentence.
Conjunction: Glues words, clauses, and sentences together.
Interjection: Expresses emotion in a sudden and exclamatory way.
These categories, without any language-specific morphological or syntactic features, are called universal tags. spaCy captures universal tags via the pos_ feature and describes them with examples as follows:
POS | Description | Examples |
ADJ | adjective | big, old, green, incomprehensible, first |
ADP | adposition | in, to, during |
ADV | adverb | very, tomorrow, down, where, there |
AUX | auxillary | is, has (done), will (do), should (do) |
CONJ | conjunction | and, or, but |
CCONJ | coordinating conjunction | and, or, but |
Throughout the course, we provide ...