Natural Language Processing

Instructor: Prof. Pushpak Bhattacharyya, Department of Computer Science and Engineering, IIT Bombay.

This course provides an understanding of natural language processing, its tools, techniques, philosophy and principle. Topics covered include sound, words and word forms, structures, meaning, and web 2.0 applications:

Sound: Biology of Speech Processing; Place and Manner of Articulation; Word Boundary Detection; Argmax based computations; HMM and Speech Recognition.
Words and Word Forms: Morphology fundamentals; Morphological Diversity of Indian Languages; Morphology Paradigms; Finite State Machine Based Morphology; Automatic Morphology Learning; Shallow Parsing; Named Entities; Maximum Entropy Models; Random Fields.
Structures: Theories of Parsing, Parsing Algorithms; Robust and Scalable Parsing on Noisy Text as in Web documents; Hybrid of Rule-Based and Probabilistic Parsing; Scope Ambiguity and Attachment Ambiguity resolution.
Meaning: Lexical Knowledge Networks, Wordnet Theory; Indian Language Wordnets and Multilingual Dictionaries; Semantic Roles; Word Sense Disambiguation; WSD and Multilinguality; Metaphors; Coreferences.
Web 2.0 Applications: Sentiment Analysis; Text Entailment; Robust and Scalable Machine Translation; Question Answering in Multilingual Setting; Cross-Lingual Information Retrieval (CLIR).

Mod-01 Lec-01 Introduction.
Mod-01 Lec-02 Stages of NLP.
Mod-01 Lec-03 Stages of NLP Continue....
Mod-01 Lec-04 Two approaches to NLP.
Mod-01 Lec-05 Sequence Labelling and Noisy Channel.
Mod-01 Lec-06 Noisy Channel: Argmax Based Computation.
Mod-01 Lec-07 Argmax Based Computation.
Mod-01 Lec-08 Noisy Channel Application to NLP.
Mod-01 Lec-09 Brief on Probabilistic Parsing & Start of Part of Speech Tagging.
Mod-01 Lec-10 Part of Speech Tagging.
Mod-01 Lec-11 Part of Speech Tagging counted....
Mod-01 Lec-12 Part of Speech Tagging counted... & Indian Language in Focus; Morphology Analysis.
Mod-01 Lec-13 PoS Tagging contd... , Indian Language Consideration; Accuracy Measure.
Mod-01 Lec-14 PoS Tagging; Fundamental Principle; Why Challenging; accuracy.
Mod-01 Lec-15 PoS Tagging; Accuracy Measurement; Word categories.
Mod-01 Lec-16 AI and Probability; HMM.
Mod-01 Lec-17 HMM.
Mod-01 Lec-18 HMM, Viterbi, Forward Backward Algorithm.
Mod-01 Lec-19 HMM, Viterbi, Forward Backward Algorithm Contd..9.
Mod-01 Lec-20 HMM, Forward Backward Algorithms, Baum Welch Algorithm.
Mod-01 Lec-21 HMM, Forward Backward Algorithms, Baum Welch Algorithm Contd....
Mod-01 Lec-22 Natural Language Processing and Informational Retrieval.
Mod-01 Lec-23 CLIA; IR Basics.
Mod-01 Lec-24 IR Models: Boolean Vector.
Mod-01 Lec-25 IR Models: NLP and IR Relationship.
Mod-01 Lec-26 NLP and IR: How NLP has used IR, Toward Latent Semantic.
Mod-01 Lec-27 Least Square Method; Recap of PCA; Towards Latent Semantic Indexing(LSI).
Mod-01 Lec-28 PCA; SVD; Towards Latent Semantic Indexing(LSI).
Mod-01 Lec-29 Wordnet and Word Sense Disambiguation.
Mod-01 Lec-30 Wordnet and Word Sense Disambiguation(contd...).
Mod-01 Lec-31 Wordnet; Metonymy and Word Sense Disambiguation.
Mod-01 Lec-32 Word Sense Disambiguation.
Mod-01 Lec-33 Word Sense Disambiguation; Overlap Based Method; Supervised Method.
Mod-01 Lec-34 Word Sense Disambiguation: Supervised and Unsupervised methods.
Mod-01 Lec-35 Word Sense Disambiguation: Semi - Supervised and Unsupervised method.
Mod-01 Lec-36 Resource Constrained WSD; Parsing.
Mod-01 Lec-37 Parsing.
Mod-01 Lec-38 Parsing Algorithm.
Mod-01 Lec-39 Parsing Ambiguous Sentences; Probabilistic Parsing.
Mod-01 Lec-40 Probabilistic Parsing Algorithms.