????? ????? 1 ??? NLP ?????? ??? NLP ?? ??????? ??? ???? ___________________________

1
????? ????? 1 ??? NLP?????? ??? NLP ?? ???????
??? ????___________________________

• ????? ???
• ????? ??? ???? ??????? ????
• ????? 85

2
University of Cmbridge-2006
Introduction Brief history of NLP research, current applications, generic NLP system architecture, knowledge-based versus probabilistic approaches.
Finite-state techniques Inflectional and derivational morphology, finite-state automata in NLP, finite-state transducers.
Prediction and part-of-speech tagging Corpora, simple N-grams, word prediction, stochastic tagging, evaluating system performance.
Parsing and generation Generative grammar, context-free grammars, parsing and generation with context-free grammars, weights and probabilities.
Parsing with constraint-based grammars Constraint-based grammar, unification.
Compositional and lexical semantics Simple compositional semantics in constraint-based grammar. Semantic relations, WordNet, word senses, word sense disambiguation.
Discourse and dialogue Anaphora resolution, discourse relations.
Applications Machine translation, email response, spoken dialogue systems.
3
Stanford University______________________________
________

• Introduction to and history of NLP
• Syntax
• the basics
• Syntax chart parsing
• Syntax transition network parsing
• Probability
• N-gram models
• Probabilistic algorithms
• Probabilistic context-free grammars
• Experimental design, information extraction
• Semantics
• The basics
• tbd

4
Stanford University (cont.)______________________
_____________________

• Learning extraction patterns Handout
• Transformation-based learning
• Semantics
• named entity recognition
• word sense disambiguation
• Discourse and pragmatics
• Semantics spreading activation techniques
• Conceptual dependency theory Handout
• Conceptual knowledge structures Handout
• Applications
• question answering
• spoken language understanding
• information retrieval
• machine translation

5
Columbia University
Week 1 Introduction and Course Overview
Week 1 Natural Language and Formal Language Regular Expressions and Finite State Automata
Week 2 Words and Their Parts  Morphology
Week 2 Word Construction and Analysis Morphological Parsing
Week 3 Words Tokenization and Spelling
Week 3 N-grams and Language Models
Week 4 Word Classes and POS Tagging
Week 4 Machine Learning Approaches to NLP
Week 5 Formal Grammars
Week 5 Parsing with Context Free Grammars
Week 6 Probabilistic and Lexicalized Parsing
Week 6 Representing Meaning
Week 7 Semantic Analysis
Week 8 Lexical Semantics Word Sense Disambiguation
Week 8 Lexical Semantics Word Relations
6
Columbia University (cont.)
Week 9 Lexical Semantics Semantic Roles
Week 9 Robust Semantics and Information Extraction
Week 10 Week 11 TBA
Week 10 Week 11 Pronouns and Reference Resolution
Week 12 Text Coherence and Discourse Structure
Week 12 Machine Translation
Week 13 Week 14 Natural Language  Summarization
Week 13 Week 14 Dialogue Systems
Week 9 Natural Language Generation
Week 9 Lexical Semantics Semantic Roles
Week 10 Robust Semantics and Information Extraction
Week 10 TBA
Week 11 Pronouns and Reference Resolution
Week 12 Text Coherence and Discourse Structure
Week 12 Machine Translation
7
University of Birmingham (2005/2006)_____________
_________________________

• Techniques of automatic speech processing
  representation
• Cognitive models of spoken word recognition
• Phonology
• Corpus techniques
• Language and the Corpus
• Statistical Techniques in NLP
• Meaning
• Word and sentence meaning
• Electronic Dictionaries and Lexicography
• Pragmatics and Discourse Processing
• Context Meaning
• Metaphor Metonymy

8
Washington University-2006(Advanced Statistical
Methods in Natural Language Processing)
Week Topic
1 Introduction FSA and HMM
2 Supervised Learning I -         Decision tree -         Decision list    
3 Supervised Learning II -         TBL    
4 Supervised Learning III -         Bagging
5 Supervised Learning IV -         System Combination -         Boosting 
Week Topic
6 Supervised Learning IV -         MaxEnt   
7 Semi-supervised Learning I - Self-training (Bootstrapping)  
8 Semi-supervised learning II - Co-training Unsupervised Learning I -   The EM algorithm (Part 1) - Forward-backward algorithm
9 Unsupervised Learning II -     Inside-outside algorithm -    The EM algorithm (Part 2)