Natural Language Processing Primer

AI & ML & Blockchain, Blog, Machine Learning

What is Natural Language Processing?

Natural language processing (NLP) is the analysis, generation, and acquisition of human language via computational means to solve practical problems in “human language technologies”. 

NLP is an engineering-oriented field as it uses computer science, linguistics, and allied fields to solve practical problems in human language. However, it is different from computational linguistics.

What is NLP?
What is NLP?

What is Computational Linguistics?

The theory and application of computational models and approaches/techniques to investigate scientific hypotheses about human languages. In “computational linguistics”, human language is the object of study.

NLP and Computational Linguistics overlap each other in the usage of computational techniques.

What are NLP Applications?

Following are some of the possible applications we can do:

  1. Analysis and Generation of Text
  2. Text to Speech, Automatic Speech Recognition (ASR), Spoken dialogue

What Tasks are Involved in NLP Applications?

Some of the tasks involved in NLP Applications are:

  1. Information Retrieval (IR)
  2. Question Answering (Q & A)
  3. Text Summarization – take large text and give back smaller text
  4. Text Mining (statistics of a large body of text)
  5. Information Extraction IE) – take unstructured text and pull structured text out of unstructured text
  6. Machine Translation (MT) – take text/speech in one language and translates it into another language
  7. Speech Synthesis and Text to Speech (TTS)
  8. Automatic Speech Recognition (ASR)
  9. Dialog Systems – Chatbots, Spoken Dialog Systems (speak back and forth with the computer systems)

Ethics of NLP

The following are possible positive or negative impacts of NLP on societies:

NLP technologies like BERT, EMlo, GPT-2, GPT-3

  1. Can improve or enhance people’s lives
    • through understanding “people’s” text
    • providing recommendations based on the “text understanding”
  2. Can negatively affect lives in terms of freedom, privacy, and security
    • extract people’s “sensitive information” unwantedly
    • understand the “emotions” of people through “text understanding” which is not “desirable” in true “people” internal thinking

How do you prevent yourself from NLP Ethics:

While NLP Ethics is to help people, still following suggestions might help you from such NLP software applications that do not follow NLP Ethics (race, gender, sexual orientation, social economic condition, political context ext):

  1. Avoid making decisions that can significantly and negatively impact your lives based on NLP software application output
  2. Understand for whom the NLP software application is built for

What are NLP Models or Pre-Trained Models?

NLP Language models are built to predict any probability of a pattern or sequence of words.

NLP Tasks / Software Applications use these models to comprehend the predictability of languages and words.

The below image should provide a high-level view on what are NLP models and/or Pre-Trainer models.

NLP Models and Behavior
NLP Models and Behavior

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: 567