Natural Language Processing
Natural Language Processing. Instructor: Prof. Pawan Goyal, Department of Computer Science and Engineering, IIT Kharagpur. This course deals with various topics in natural language processing and its applications: basic text processing, spelling correction, language modeling, advanced smoothing for language modeling, Part of Speech tagging, models for sequential tagging, syntax, constituency parsing, dependency parsing, lexical semantics, distributional semantics, topic models, entity linking, information extraction, text summarization, text classification, sentiment analysis and opinion mining.
(from nptel.ac.in)
| Lecture 01 - Introduction |
| Lecture 02 - NLP Applications: Machine Translation, Sentiment Analysis |
| Lecture 03 - Why is NLP Hard? - Ambiguities in Language |
| Lecture 04 - Empirical Laws: Heap's Law, Zipf's Law, Type-Token Ratio |
| Lecture 05 - Text Processing: Word toKenization and Segmentation, Lemmatization, Stemming |
| Lecture 06 - Spelling Correction: Edit Distance - Dynamic Programming Approach |
| Lecture 07 - Weighted Edit Distance, Finding Dictionary Entries with Small Edit Distances |
| Lecture 08 - Noisy Channel Model for Spelling Correction |
| Lecture 09 - N-Gram Language Model |
| Lecture 10 - Evolution of Language Models, Basic Smoothing |
| Lecture 11 - Language Modeling: Advanced Smoothing Models |
| Lecture 12 - Computational Morphology |
| Lecture 13 - Finite State Methods for Morphology |
| Lecture 14 - Introduction to Part of Speech Tagging |
| Lecture 15 - Hidden Markov Models for PoS Tagging |
| Lecture 16 - Viterbi Decoding for Hidden Markov Models, Parameter Learning |
| Lecture 17 - Forward-Backward Algorithm, Baum Welch Algorithm |
| Lecture 18 - Maximum Entropy Models I |
| Lecture 19 - Maximum Entropy Models II: Maximum Entropy Markov Model, Beam Search |
| Lecture 20 - Conditional Random Fields |
| Lecture 21 - Syntax - Introduction |
| Lecture 22 - Syntax - Parsing I |
| Lecture 23 - Syntax - CKY Algorithm, PCFGs |
| Lecture 24 - PCFGs - Inside-Outside Probabilities |
| Lecture 25 - Inside-Outside Probabilities |
| Lecture 26 |
| Lecture 27 - Dependency Grammars and Parsing - Introduction |
| Lecture 28 - Transition based Parsing: Formulation |
| Lecture 29 - Transition based Parsing: Learning |
| Lecture 30 - Maximum Spanning Tree (MST) based Dependency Parsing |
| Lecture 31 - MST based Dependency Parsing: Learning |
| Lecture 32 - Distributional Semantics - Introduction |
| Lecture 33 - Distributional Models of Semantics |
| Lecture 34 - Distributional Semantics: Applications, Structured Models |
| Lecture 35 - Word Embeddings, Part I |
| Lecture 36 - Word Embeddings, Part II |
| Lecture 37 - Lexical Semantics |
| Lecture 38 - Lexical Semantics - Wordnet |
| Lecture 39 - Word Sense Disambiguation: Lesk Algorithm, Random Walk Approach, Naive Bayes |
| Lecture 40 - Word Sense Disambiguation: Semi-Supervised and Unsupervised Approaches |
| Lecture 41 - Novel Word Sense Detection |
| Lecture 42 - Topic Models - Introduction |
| Lecture 43 - Latent Dirichlet Allocation: Formulation |
| Lecture 44 - Gibbs Sampling for LDA, Applications |
| Lecture 45 - LDA Variants and Applications: Correlated Topic Models, Dynamic Topic Models, Supervised LDA |
| Lecture 46 - LDA Variants and Applications: Relational Topic Models, Bayesian Nonparametrics |
| Lecture 47 - Entity Linking: Wikification, Mention Detection, Link Disambiguation, Key Phraseness |
| Lecture 48 - Entity Linking: Relatedness, Learning to Link |
| Lecture 49 - Information Extraction: Definition and Applications, Regex, Hand-built Patterns |
| Lecture 50 - Bootstrapping and Supervised Relation Extraction |
| Lecture 51 - Distort Supervision, Freebase, Syntactic Dependency Paths |
| Lecture 52 - Text Summarization - Concepts, Lexrank, Maximal Marginal Relevance |
| Lecture 53 - Optimization based Approaches for Summarization |
| Lecture 54 - Summarization Evaluation: Manual Evaluation, Rouge Evaluation |
| Lecture 55 - Text Classification: Naive Bayes, Bag of Words, Add One Smoothing |
| Lecture 56 - Text Classification: Naive Bayes, Multi-value Classification, Confusion Matrix |
| Lecture 57 - Tokenization and Pre-processing for Sentiment Analysis |
| Lecture 58 - Sentiment Analysis - Affective Lexicons |
| Lecture 59 - Learning Affective Lexicons |
| Lecture 60 - Computing with Affective Lexicons |
| Lecture 61 - Aspect based Sentiment Analysis |
| References |
Natural Language Processing
Instructor: Prof. Pawan Goyal, Department of Computer Science and Engineering, IIT Kharagpur. This course deals with various topics in natural language processing and its applications.
|