1 of 11

Natural Language Processing

By

S.V.V.D.Jagadeesh

Sr. Assistant Professor

Dept of Artificial Intelligence & Data Science

LAKIREDDY BALI REDDY COLLEGE OF ENGINEERING

2 of 11

  • Course Objectives
  • Course Outcomes
  • Course Contents
  • Text Books
  • Unit-I Outcomes
  • NLP
  • Definitions of NLP
  • Components of NLP
  • Applications of NLP

S.V.V.D.Jagadeesh

Wednesday, December 17, 2025

Previously Discussed Tpopics

LBRCE

NLP

3 of 11

At the end of this session, Student will be able to:

  • Understand the history and challenges of NLP(Understand-L2)

S.V.V.D.Jagadeesh

Wednesday, December 17, 2025

Session Outcomes

LBRCE

NLP

4 of 11

  • NLP is mistakenly called NLU
  • NLU involves only Interpretation where as NLP involves Interpretation (Understanding) and Generation (production).
  • NLP includes Speech Processing.
  • Computational models are divided into two types.
  • Knowledge driven : the system relay on explicitly coded linguistic knowledge represented as set of rules called grammar.
  • Data driven : presume the existence of large amount of data is used to learn syntactic patterns using ML techniques. The amount of human effort is less and the quality dependents on the quality of data.

S.V.V.D.Jagadeesh

Wednesday, December 17, 2025

Models in NLP

LBRCE

NLP

5 of 11

S.V.V.D.Jagadeesh

Wednesday, December 17, 2025

Four Eras of NLP

  • Four eras of NLP
  • 1940–1969 • Early Explorations • Machine Translations
  • 1970–1992 • Hand-built demonstration NLP systems, • of increasing formalization
  • 1993–2012 • Statistical or Probabilistic NLP and then • more general Supervised ML for NLP
  • 2013–now • Deep Learning or Artificial Neural • Networks for NLP. Unsupervised or Self -Supervised NLP. Reinforcement Learning

LBRCE

NLP

6 of 11

S.V.V.D.Jagadeesh

Wednesday, December 17, 2025

Early Explorations-1940–1959

LBRCE

NLP

7 of 11

S.V.V.D.Jagadeesh

Wednesday, December 17, 2025

NLP in 1960’s

LBRCE

NLP

8 of 11

S.V.V.D.Jagadeesh

Wednesday, December 17, 2025

History of NLP

LBRCE

NLP

9 of 11

  • Ambiguity - Words/sentences can have multiple meanings (e.g., “bank” → river bank vs. financial bank).
  • Context Understanding - Handling sarcasm, irony, pragmatics, and discourse-level understanding.
  • Multilinguality - Different grammar, word order, morphology across languages.
  • Low-Resource Languages - Many Indian and African languages lack annotated corpora.
  • World Knowledge Integration -Machines need background knowledge to interpret meaning correctly. • Bias and Fairness o Models can amplify social, gender, or cultural biases from training data. • Scalability o Large transformer models require huge computational resources. • Ethical Issues o Misinformation, deepfakes, surveillance, and misuse of NLP technology.

S.V.V.D.Jagadeesh

Wednesday, December 17, 2025

Challenges in NLP

LBRCE

NLP

10 of 11

  • Bias and Fairness - Models can amplify social, gender, or cultural biases from training data.
  • Scalability - Large transformer models require huge computational resources.
  • Ethical Issues - Misinformation, deepfakes, surveillance, and misuse of NLP technology.

S.V.V.D.Jagadeesh

Wednesday, December 17, 2025

Challenges in NLP

LBRCE

NLP

11 of 11

  • Previously Discussed Topics
  • Session Outcomes
  • Models in NLP
  • Four Eras of NLP
  • Early Explorations-1940-1959
  • NLP in 1960’s
  • History of NLP
  • Challenges in NLP

S.V.V.D.Jagadeesh

Wednesday, December 17, 2025

Summary

LBRCE

NLP