Lesson 1 Introduction to Overview
Welcome, motivations, what is Natural Language Processing, hands-on demonstrations. Ambiguity and uncertainty in language. The Turing test. Course outline and logistics.
o Examples of Text
o Funny Sentences
o Why is NLP hard?
Lesson 2: Introduction to Parts of Speech, Morphology and the Lexicon, ACLO
This topic will cover Parts of Speech, Morphology, Text Similarity, and Text Preprocessing. Parts of speech
o Morphology and the Lexicon
o Text Similarity: Introduction
o Morphological Similarity: Stemming
o Spelling Similarity: Edit Distance
Lesson 3: NLP Tasks and Text Similarity
This topic will cover Vector Semantics, Text Similarity, and Dimensionality Reduction. I will also go through a long list of sample NLP tasks (e.g., Information Extraction, Text Summarization, and Semantic Role Labeling) and introduce each of them briefly.
o Semantic Similarity: Synonymy and other Semantic Relations
o Thesaurus-based Word Similarity Methods
o The Vector Space Model
o Dimensionality Reduction
Lesson4: Syntax and Parsing, Part 1
This topic will cover the basics of Syntax and Parsing, including CKY parsing and the Earley parser.
o Classic Parsing Methods
o Earley Parser
o The Penn Treebank
Lesson 5: Syntax and Parsing, Part 2
This topic is related to parsing, including Statistical, Lexicalized, and Dependency Parsing as well as Noun Sequence Parsing, Prepositional Phrase Attachment, and Alternative Grammatical Formalisms.
o Parsing Introduction and recap/Parsing noun sequences
o Prepositional phrase attachment 1/3 Prepositional phrase attachment 2/3 Prepositional phrase attachment 3/3
o Statistical Parsing
o Lexicalized Parsing
o Dependency Parsing
o Alternative Parsing Formalisms
Lesson 6: Language Modeling
This topic will cover Probabilities, Language Modeling, and Word Sense Disambiguation (WSD).
o Bayes Theorem
o Language Modeling 1/3
o Language Modeling 1/3
o Language Modeling 2/3
o Language Modeling 3/3
o Word Sense Disambiguation
Lesson 7: Part of Speech Tagging and Information Extraction
This topic includes the Noisy Channel Model, Hidden Markov Models, Part of Speech Tagging (all needed for the second programming assignment) and a short introduction to Information Extraction.
o Noisy Channel Model
o Part of Speech Tagging
o Hidden Markov Models 1/2
o Hidden Markov Models 2/2
o Statistical POS Tagging
o Information Extraction
o Relation Extraction
Lesson 8: Question Answering
This topic will cover different topics related to Question Answering, including Question Type Classification and Evaluation of Question Answering Systems.
o Question Answering
o Evaluation of QA
o System Architecture
o QA System Architecture
Lesson 9: Text Summarization
This topic covers Text Summarization and related topics such as Sentence Compression.
o Summarization Techniques 1/3
o Summarization Techniques 2/3
o Summarization Techniques3/3
o Summarization Evaluation
o Sentence Simplification
Lesson 10: Collocations and Information Retrieval
This topic covers Information Retrieval (including Document Indexing, Ranking, Evaluation), Text Classification and Text Clustering, as well as a short lecture on Collocations.
o Information Retrieval
o Evaluation of IR
o Text Classification
o Text Clustering
o Information Retrieval Toolkits
Lesson 11: Sentiment Analysis and Semantics
This topic covers Semantics and related topics such as Sentiment Analysis, Semantic Parsing, and Knowledge Representation.
o Sentiment Analysis
o Sentiment Lexicons
o Representing and Understanding Meaning
o First Order Logic
o Knowledge Representation
o Semantic Parsing
Lesson 12: Discourse, Machine Translation, and Generation (Includes Final Exam)
This topic briefly covers Discourse Analysis, Dialogue, Machine Translation, and Text Generation.
o Discourse Analysis
o Dialogue Systems
o Machine Translation
o Machine Translation Basic Techniques
o Machine Translation Noisy Channel Methods
o Machine Translation Advanced Methods
o Text Generation
o Post-course Survey