NATURAL LANGUAGE PROCESSING FOR ONLINE APPLICATIONS 

Peter Jackson & Isabelle Moulinier
 
 

TABLE OF CONTENTS
 

1. Natural Language Processing 

1.1. What is NLP? 

1.2. NLP and Linguistics 

1.2.1. Syntax and Semantics

1.2.2. Pragmatics and Context

1.2.3. Two Views of NLP

1.2.4. Tasks and Supertasks

1.3. Linguistic Tools

1.3.1. Sentence Delimiters and Tokenizers

1.3.2. Stemmers and Taggers 

1.3.3. Noun Phrase and Name Recognizers 

1.3.4. Parsers and Grammars

1.4. Plan of the Book

 

2. Document Retrieval

2.1. Information Retrieval

2.2. Indexing Technology

2.3. Query Processing

2.3.1. Boolean Search

2.3.2. Ranked Retrieval

2.3.3. Probabilistic Retrieval

2.3.4. Language Modeling

2.4. Evaluating Search Engines

2.4.1. Evaluation Studies

2.4.2. Evaluation Metrics

2.4.3. Relevance Judgments

2.4.4. System Evaluation

2.5. Attempts to Enhance Search Engine Performance

2.5.1. Query Expansion and Thesauri

2.5.2. Query Expansion from Relevance Information

2.6. The Future of Web Searching

2.6.1. Indexing the Web

2.6.2. Searching the Web

2.6.3. Ranking and Reranking Documents

2.6.4. The State of Online Search

2.7. Summary of Information Retrieval

 

3. Information Extraction

3.1. The Message Understanding Conferences

3.2. Regular Expressions

3.3. Finite Automata in FASTUS

3.3.1. Finite State Machines and Regular Languages 

3.3.2. Finite State Machines as Parsers

3.4. Pushdown Automata and Context-Free Grammars

3.4.1. Analyzing Case Reports

3.4.2. Context Free Grammars

3.4.3. Parsing with a Pushdown Automaton

3.4.4. Coping with Incompleteness and Ambiguity

3.5. Limitations of Current Technology and Future Research

3.5.1. Explicit versus Implicit Statements

3.5.2. Machine Learning for Extraction

3.5.3. Statistical Language Models of Information Extraction

3.6. Summary of Information Extraction

 

4. Text Categorization 

4.1. Overview of Categorization Tasks and Methods 

4.2. Handcrafted Rule Based Methods

4.3. Inductive Learning for Text Classification

4.3.1. Naive Bayes Classifiers

4.3.2. Linear Classifiers

4.3.3. Decision Trees & Decision Lists

4.4. Nearest Neighbor Algorithms

4.5. Combining Classifiers

4.5.1. Data Fusion

4.5.2. Boosting

4.5.3. Using Multiple Classifiers

4.6. Evaluation of Text Categorization Systems

4.6.1. Evaluation Studies

4.6.2. Evaluation Metrics

4.6.3. Relevance Judgments

4.6.4. Total System Evaluation 

 

5. Towards Text Mining

5.1. What is Text Mining?

5.2. Reference & Coreference

5.2.1. Named Entity Recognition

5.2.2. The Coreference Task

5.3. Automatic Summarization

5.3.1. Summarization Tasks

5.3.2. Constructing Summaries from Document Fragments

5.3.3. Multi-Document Summarization

5.4. Testing of Automatic Summarization Programs

5.4.1. Evaluation Problems in Summarization Research

5.4.2. Building a Corpus for Training & Testing

5.5. Prospects for Text Mining & NLP

 

Visit authors' webpage dedicated to the book

Back to John Benjamins' book series on NLP