Welcome to Scribd, the world's digital library. Read, publish, and share books and documents. See more
Download
Standard view
Full view
of .
Save to My Library
Look up keyword or section
Like this
3Activity

Table Of Contents

1.2 A Brief History of WSD Research
1.3 What is a Word Sense?
1.4 Applications of WSD
1.5 Basic Approaches to WSD
1.6 State-of-the-Art Performance
1.7 Promising Directions
1.8 Overview of This Book
1.9 Further Reading
2 Word Senses
2.1 Introduction
2.2 Lexicographers
2.3 Philosophy
2.3.1 Meaning is Something You Do
2.3.2 The Fregean Tradition and Reification
2.3.3 Two Incompatible Semantics?
2.3.4 Implications for Word Senses
2.4 Lexicalization
2.5 Corpus Evidence
2.5.1 Lexicon Size
2.5.2 Quotations
2.6 Conclusion
2.7 Further Reading
Acknowledgments
3 Making Sense About Sense
3.1 Introduction
3.2 WSD and the Lexicographers
3.3 WSD and Sense Inventories
3.4 NLP Applications and WSD
3.6 What Now for WSD?
3.7 Conclusion
4 Evaluation of WSD Systems
4.1 Introduction
4.1.1 Terminology
4.1.2 Overview
4.2 Background
4.2.1 WordNet and Semcor
4.2.2 The Line and Interest Corpora
4.2.3 The DSO Corpus
4.2.4 Open Mind Word Expert
4.3 Evaluation Using Pseudo-Words
4.4 Senseval Evaluation Exercises
4.4.1 Senseval-1
Evaluation and Scoring
4.4.2 Senseval-2
English All-Words Task
English Lexical Sample Task
4.4.3 Comparison of Tagging Exercises
4.5 Sources of Inter-Annotator Disagreement
4.6 Granularity of Sense: Groupings for WordNet
4.6.1 Criteria for WordNet Sense Grouping
4.6.2 Analysis of Sense Grouping
4.7 Senseval-3
4.8 Discussion
5 Knowledge-Based Methods for WSD
5.1 Introduction
5.2 Lesk Algorithm
5.2.1 Variations of the Lesk Algorithm
Augmented Semantic Spaces
Summary
5.3 Semantic Similarity
5.3.1 Measures of Semantic Similarity
5.3.2 Using Semantic Similarity Within a Local Context
5.3.3 Using Semantic Similarity Within a Global Context
5.4 Selectional Preferences
5.4.1 Preliminaries: Learning Word-to-Word Relations
5.4.2 Learning Selectional Preferences
5.4.3 Using Selectional Preferences
5.4 Heuristics for Word Sense Disambiguation
5.5.1 Most Frequent Sense
5.5.2 One Sense Per Discourse
5.5.3 One Sense Per Collocation
5.6 Knowledge-Based Methods at Senseval-2
5.7 Conclusions
6 Unsupervised Corpus-Based Methods for WSD
6.1 Introduction
6.1.1 Scope
6.1.2 Motivation
Distributional Methods
Translational Equivalence
6.1.3 Approaches
6.2 Type-Based Discrimination
6.2.1 Representation of Context
6.2.2 Algorithms
Latent Semantic Analysis (LSA)
Hyperspace Analogue to Language (HAL)
Clustering By Committee (CBC)
6.2.3 Discussion
6.3 Token-Based Discrimination
6.3.1 Representation of Context
6.3.2 Algorithms
McQuitty’s Similarity Analysis
6.3.3 Discussion
6.4 Translational Equivalence
6.4.1 Representation of Context
6.4.2 Algorithms
6.4.3 Discussion
6.5 Conclusions and the Way Forward
7 Supervised Corpus-Based Methods for WSD
7.1 Introduction to Supervised WSD
7.1.1 Machine Learning for Classification
An Example on WSD
7.2 A Survey of Supervised WSD
7.2.1 Main Corpora Used
7.2.2 Main Sense Repositories
7.2.3 Representation of Examples by Means of Features
7.2.4 Main Approaches to Supervised WSD
Probabilistic Methods
Methods Based on the Similarity of the Examples
Methods Based on Discriminating Rules
Methods Based on Rule Combination
Linear Classifiers and Kernel-Based Approaches
7.2.5 Supervised Systems in the Senseval Evaluations
7.3 An Empirical Study of Supervised Algorithms for WSD
7.3.1 Five Learning Algorithms Under Study
Naïve Bayes (NB)
Exemplar-Based Learning (kNN)
Decision Lists (DL)
AdaBoost (AB)
Support Vector Machines (SVM)
7.3.2 Empirical Evaluation on the DSO Corpus
Experiments
7.4 Current Challenges of the Supervised Approach
7.4.1 Right-Sized Training Sets
7.4.2 Porting Across Corpora
7.4.3 The Knowledge Acquisition Bottleneck
Automatic Acquisition of Training Examples
Active Learning
Combining Training Examples from Different Words
Parallel Corpora
7.4.4 Bootstrapping
7.4.5 Feature Selection and Parameter Optimization
7.4.6 Combination of Algorithms and Knowledge Sources
7.5 Conclusions and Future Trends
References
8.3.1 Target-Word Specific Features
8.3.2 Local Features
8.3.3 Global Features
8.4 Identifying Knowledge Sources in Actual Systems
8.4.1 Senseval-2 Systems
8.4.2 Senseval-3 Systems
8.5 Comparison of Experimental Results
8.5.1 Senseval Results
8.5.2 Yarowsky and Florian (2002)
8.5.3 Lee and Ng (2002)
8.5.4 Martínez et al. (2002)
8.5.5 Agirre and Martínez (2001a)
8.5.6 Stevenson and Wilks (2001)
8.6 Discussion
8.7 Conclusions
9 Automatic Acquisition of Lexical Information and Examples
9.1 Introduction
9.2 Mining Topical Knowledge About Word Senses
9.2.1 Topic Signatures
Association of Web Directories to Word Senses
9.3 Automatic Acquisition of Sense-Tagged Corpora
9.3.1 Acquisition by Direct Web Searching
9.3.2 Bootstrapping from Seed Examples
9.3.3 Acquisition via Web Directories
9.3.4 Acquisition via Cross-Language Evidence
9.3.5 Web-Based Cooperative Annotation
9.4 Discussion
10.1 Introduction
10 Domain-Specific WSD
10.2 Approaches to Domain-Specific WSD
10.2.1 Subject Codes
10.2.2 Topic Signatures and Topic Variation
Topic Variation
Top-Down Domain Tuning
Bottom-Up Domain Tuning
10.3 Domain-Specific Disambiguation in Applications
10.3.1 User-Modeling for Recommender Systems
10.3.2 Cross-Lingual Information Retrieval
10.3.3 The MEANING Project
10.4 Conclusions
11 WSD in NLP Applications
11.1 Introduction
11.2 Why WSD?
Argument from Faith
Argument by Analogy
11.3 Traditional WSD in Applications
11.3.1 WSD in Traditional Information Retrieval
11.3.2 WSD in Applications Related to Information Retrieval
Question Answering
11.3.3 WSD in Traditional Machine Translation
11.3.4 Sense Ambiguity in Statistical Machine Translation
11.3.5 Other Emerging Applications
11.4 Alternative Conceptions of Word Sense
11.4.1 Richer Linguistic Representations
11.4.2 Patterns of Usage
11.4.3 Cross-Language Relationships
11.5 Conclusions
A.2.1 Raw Corpora
A.2.2 Sense-Tagged Corpora
A.2.3 Automatically Tagged Corpora
A.3 Other Resources
A.3.1 Software
A.3.2 Utilities, Demos, and Data
A.3.3 Language Data Providers
A.3.4 Organizations and Mailing Lists
0 of .
Results for:
No results containing your search query
P. 1
Word Sense Disambiguation

Word Sense Disambiguation

Ratings: (0)|Views: 253 |Likes:
Published by ThienAn Nguyen

More info:

Published by: ThienAn Nguyen on Oct 05, 2011
Copyright:Attribution Non-commercial

Availability:

Read on Scribd mobile: iPhone, iPad and Android.
download as PDF, TXT or read online from Scribd
See more
See less

11/20/2012

pdf

text

original

You're Reading a Free Preview
Pages 8 to 19 are not shown in this preview.
You're Reading a Free Preview
Pages 27 to 234 are not shown in this preview.
You're Reading a Free Preview
Pages 245 to 356 are not shown in this preview.
You're Reading a Free Preview
Pages 364 to 384 are not shown in this preview.

You're Reading a Free Preview

Download
/*********** DO NOT ALTER ANYTHING BELOW THIS LINE ! ************/ var s_code=s.t();if(s_code)document.write(s_code)//-->