Natural Language Processing - CS60075

Spring Semester - 2021-22

Instructor

Pawan Goyal

Course Timings

Lectures

Monday - 14:00 - 15:00 (Online)

Tuesday - 16:00 - 18:00 (Online)

Teaching Assistants

Bishal Santra, Rajdeep Mukherjee, Soumya Sharma, Aniruddha Roy, Yash Butala

Lecture Material

The lecture material of the course will be uploaded every week on Microsoft Teams.

Announcements

The course will start from Jan 4th on MS Teams from 4-6 PM. Link to join this meeting : Click here

Semester Registration: The registration is now closed. I have approved the students via ERP (as permissible by the course strength, based on a cut-off). Please register by January 7th positively. I will then send a code to join the Teams.

Reference Books

  1. Daniel Jurafsky and James H. Martin. 2021. Speech and Language Processing. 3rd Edition (draft)
  2. Christopher D. Manning and Hinrich Schütze. 1999. Foundations of Statistical Natural Language Processing. MIT Press.
  3. Sowmya Vajjala, Bodhisattwa Majumder, Anuj Gupta, Harshit Surana. 2020. Practical Natural Language Processing. O'Reilly.
  4. Hobson Lane, Cole Howard, Hannes Hapke. 2019. Natural Language Processing in Action. Live Book.

Course Contents

Major Components of the Course include topics from basic NLP as well as Deep Learning for NLP (Tentative)
  1. Empirical Laws, Basic Text Processing: Tokenization, Stemming
  2. Language Modeling: N-grams, smoothing
  3. Text Classification
  4. Distributional Semantics, Word Embeddings
  5. Recurrent Neural Networks (RNNs) based Language Modeling
  6. Parts of Speech Tagging, Named Entity Recognition
  7. RNNs for Sequence Tagging, Sequence to Sequence
  8. Syntax: PCFGs, Dependency Parsing
  9. Transformers, ELMO, BERT
  10. Information Extraction: Relation extraction
  11. More Applications: Question Answering, Summarization