NLP Learnings 03 – What is Linguistic in NLP and Linguistic Categories or Linguistic Levels

AI & ML & Blockchain, Blog, Data & Analytics, Machine Learning

What is Linguistic

Linguistics is the study of language and its structure.

The study includes analyzing a sentence into below mentioned Linguistic Categories or Linguistic Levels.

Consider a sentence: Data Scientists use various Natural Language Processing techniques. For this sentence, the study of linguistic analytics includes:

  1. Orthography – A sequence of letters in the above sentence
  2. Phonology – If we say the above sentence loud and observe the loudness as a sequence of sounds.
  3. Morphology – Sequence of meaningful units ( “morpho-” means “shape” and “-ology” means “the study of a matter.”). Morphology focuses on the internal structures (or sub-strings) of the word(s) for example word “Re-Construction”. In this word we can look for sub-strings like “Re”, “Construct”, and “ion” These (Re, Construct, ion) are called Morphemes. To restate, Morphology focuses on the internal structures or sub-strings of a word. 
  4. Lexicon – Set of words 
  5. Syntax – Sequence of Phrases
  6. Semantics – As a meaning – example from an NLP perspective a sentence could be a question or command
  7. Pragmatics – A sentence meaning “in a context” – example (from above semantics), a sentence could be a “reply” to someone (here someone is the context) or a sentence could be a “request” to someone. Here again “to someone” is the context.
  8. Discourse

More About Morphology:

Again, Morphology focuses on the “internal structures” or “sub-strings” of a Word. For example, “Re-Construction”.

What are Morphemes? – Morphology again sub-divided based on “internal structures” or “sub-strings” and called Morphemes

A Word typically has “roots” and “affixes”. A root is the core of a word that is irreducible into more meaningful elements. Root and affix both independently are called Morphemes.

In morphology, a root is a morphologically simple unit that can be left bare or to which a prefix or a suffix can attach

Morphology with an example:

For the sentence “Data Scientists use various Natural Language Processing techniques.”,  below is the linguistic analysis using free online software tools referenced:

Phonology – tophonetics.com – ˈdeɪtə ˈsaɪəntɪsts juːz ˈveərɪəs ˈnæʧrəl ˈlæŋɡwɪʤ ˈprəʊsɛsɪŋ tɛkˈniːks.

Morphology – morphological.org

Lemma: DATA
Part of speech:noun
Grammar: narrative, plural
Forms: data

Lemma: DATUM
Part of speech:noun
Grammar: narrative, plural
Forms: datum, data


Lemma: SCIENTIST
Part of speech:noun
Grammar: narrative, plural
Forms: scientist, scientists


Lemma: USE
Part of speech:verb
Grammar: infinitive
Forms: use, uses, used, using


Lemma: VARIOUS
Part of speech:pronomial adjective
Grammar:
Forms: various


Lemma: NATURAL
Part of speech:noun
Grammar: narrative, singular
Forms: natural, naturals


Lemma: LANGUAGE
Part of speech:noun
Grammar: narrative, singular
Forms: language, languages


Lemma: PROCESSING
Part of speech:noun
Grammar: narrative, singular
Forms: processing, processings

Lemma: PROCESS
Part of speech:verb
Grammar: gerund
Forms: process, processes, processed, processing


Lemma: TECHNIQUE
Part of speech:noun
Grammar: narrative, plural
Forms: technique, techniques

 

Related Topics:

  1. Natural Language Processing Primer
  2. NLP Learnings 02 – After Primer – NLP Models & Evaluating NLP Models
  3. NLP Learnings 03 – What is Linguistic in NLP and Linguistic Categories or Linguistic Levels
  4. NLP Learnings 04 – Sentence Linguistic Analysis – Words As First Step
  5. NLP Learnings 05 – Sentence Linguistic Analysis – Pragmatics Analysis
  6. NLP Learnings 06 – What can we do with A Sentence in NLP Tasks
  7. NLP Learnings 07 – Introducing NLP Language Models
  8. NLP Learnings 08 – Language Models – Probability Types
  9. NLP Learnings 09 – Language Models – Measuring Text Based On Probability
  10. NLP Learnings 10 – Language Models – Defining Word Boundaries
  11. NLP Learnings 11 – Language Models – Your Business Text Data and Their Words Representation
  12. NLP Learnings 12 – Language Models – Regularization Techniques And Your Business Text Data
  13. NLP Learnings 13 – Language Models – Smoothing Regularization Techniques And Your Business Text Data
  14. NLP Learnings 14 – Language Models – NLP Key Terms and Concepts
  15. NLP Learnings 15 – Language Models – Classifiers Introduction
  16. NLP Learnings 16 – Language Models – Classifiers – What are Probabilistic Classifiers
  17. NLP Learnings 17 – Language Models – Classifiers – Simple Classifiers Introduction
  18. NLP Learnings 18 – Language Models – Classifiers – Simple Classifiers – Linear Probabilistic Classifier Introduction
  19. NLP Learnings 19 – Language Models – Classifiers – Evaluating Classifiers – Precision Recall F-Score Confusion Matrix
  20. NLP Learnings 20 – Language Models – Classifiers – Represent Words In A Document – Choosing and Representing Features In The Right Way
  21. NLP Learnings 21 – Language Models – Word Embeddings
  22. NLP Learnings 22 – Language Models – Sentence and Document Embeddings
  23. NLP Learnings 23 – Language Models – Sentence and Document Embeddings – Which one to consider

Post Views: 476