M.Tech (CSE-DS) Course: Natural Language Processing
CSDS116: Natural Language Processing
M.Tech – I (CSE) Data Science, Semester II, Core Elective 3/4. L–T–P–C: 3–0–2–4. [file:22]
Schedule
| Week | Date | Topic | Readings / Notes | Assignments / Labs |
|---|---|---|---|---|
| 1 | YYYY-MM-DD | Course introduction; computational linguistics overview; word meaning; distributional semantics; word sense disambiguation. [file:22] | Slides: Intro to NLP and word meaning (PDF). [file:22] | Lab 1 out: Python + NLTK tokenization and basic preprocessing. [file:22] |
| 2 | YYYY-MM-DD | Sequence models; n-gram language models; evaluation; smoothing. [file:22] | Notes: N-gram language models. [file:22] | Lab 1 due; Lab 2 out: building and evaluating n-gram LMs. [file:22] |
| 3 | YYYY-MM-DD | Feed-forward and recurrent neural language models; word embeddings. [file:22] | Slides: Neural LMs and embeddings. [file:22] | Lab 2 due; Lab 3 out: word embeddings with modern libraries. [file:22] |
| 4 | YYYY-MM-DD | Tokenization, lemmatization, stemming, sentence segmentation; POS tagging and sequence labeling; structured perceptron, Viterbi. [file:22] | Notes: POS tagging and sequence labeling. [file:22] | Lab 3 due; Lab 4 out: POS tagging and sequence labeling. [file:22] |
| 5 | YYYY-MM-DD | Information extraction from text; sequential labeling; named entity recognition. [file:22] | Slides: IE and NER. [file:22] | Lab 4 due; Lab 5 out: NER with spaCy / HuggingFace. [file:22] |
| 6 | YYYY-MM-DD | Semantic lexicon induction; relation extraction; paraphrase and inference rules. [file:22] | Notes: Relation extraction and paraphrases. [file:22] | Lab 5 in progress. [file:22] |
| 7 | YYYY-MM-DD | Summarization; event extraction; opinion extraction; temporal and open IE; knowledge base population. [file:22] | Slides: Summarization and event extraction. [file:22] | Lab 6 out: opinion / event extraction mini-project. [file:22] |
| 8 | YYYY-MM-DD | Narrative event chains and script learning; knowledge-graph-augmented neural networks for NLP. [file:22] | Notes: Knowledge graphs and narrative chains. [file:22] | Lab 6 in progress. [file:22] |
| 9 | YYYY-MM-DD | Machine translation; encoder–decoder models; beam search. [file:22] | Slides: Seq2seq and beam search. [file:22] | Lab 7 out: encoder–decoder for translation. [file:22] |
| 10 | YYYY-MM-DD | Attention models; multilingual models; syntax and trees; parsing basics. [file:22] | Notes: Attention and dependency parsing. [file:22] | Lab 7 in progress. [file:22] |
| 11 | YYYY-MM-DD | Transition-based and graph-based dependency parsing; transfer learning; deep generative models; text analytics and mining. [file:22] | Slides: Transfer learning and generative models. [file:22] | Lab 8 out: parsing / transfer learning experiment. [file:22] |
| 12 | YYYY-MM-DD | Applications: spelling correction; sentiment analysis; word sense disambiguation; text classification. [file:22] | Notes: Classical NLP applications. [file:22] | Project proposal due; choose application and dataset. [file:22] |
| 13 | YYYY-MM-DD | Applications: machine translation; question answering; intent detection; false fact detection. [file:22] | Slides: QA, intent detection, and fact verification. [file:22] | Project intermediate checkpoint. [file:22] |
| 14 | YYYY-MM-DD | Conversational AI; AQL-based information extraction; integration and revision. [file:22] | Notes: Conversational AI and course wrap-up. [file:22] | Project presentations; course review. [file:22] |