Website summarization: a topic hierarchy based approach.

Liu Nan.Thesis (M.Phil.)--Chinese University of Hong Kong, 2006.Includes bibliographical references (leaves 84-88).Abstracts in English and Chinese.Abstract --- p.1Acknowledgements --- p.3Contents --- p.4List of Figures --- p.6List of Tables --- p.7Chapter Chapter 1 --- Introduction --- p.8Chapter Chapter 2 --- Related Work --- p.12Chapter 2.1 --- Web Structure Mining --- p.12Chapter 2.1.1 --- HITS Algorithm --- p.13Chapter 2.1.2 --- PageRank Algorithm --- p.13Chapter 2.2 --- Website Mining --- p.14Chapter 2.2.1 --- Website Classification --- p.14Chapter 2.2.2 --- Web Unit Mining --- p.16Chapter 2.2.3 --- Logical Domain Extraction --- p.16Chapter 2.2.4 --- Web Thesaurus Construction --- p.17Chapter Chapter 3 --- Website Topic Hierarchy Generation --- p.19Chapter 3.1 --- Problem Definition --- p.19Chapter 3.2 --- Graph Based Algorithms --- p.21Chapter 3.2.1 --- Breadth First Search --- p.21Chapter 3.2.2 --- Shortest Path Search --- p.23Chapter 3.2.3 --- Minimum Directed Spanning Tree --- p.24Chapter 3.2.4 --- Discussion --- p.27Chapter 3.3 --- Edge Weight Function --- p.28Chapter 3.3.1 --- Relevance Method --- p.29Chapter 3.3.2 --- Machine Learning Method --- p.32Chapter 3.4 --- Experiments --- p.47Chapter 3.4.1 --- Data Preparation --- p.47Chapter 3.4.2 --- Performances of Breadth-first Search --- p.50Chapter 3.4.3 --- Performances of Shortest-path Search --- p.50Chapter 3.4.4 --- Performances of Directed Minimum Spanning Tree --- p.54Chapter 3.4.5 --- Comparison of Different Algorithms --- p.55Chapter Chapter 4 --- Website Summarization Through Keyphrase Extraction --- p.58Chapter 4.1 --- Introduction --- p.58Chapter 4.2 --- Background --- p.60Chapter 4.3 --- Keyphrase Extraction --- p.69Chapter 4.3.1 --- Candidate Phrases Idenfication --- p.69Chapter 4.3.2 --- Feature Calculation without Topic Hierarchy --- p.70Chapter 4.3.3 --- Feature Calculation with Topic Hierarchy --- p.72Chapter 4.3.4 --- Extraction of Keyphrases --- p.75Chapter 4.4 --- Experiments --- p.76Chapter Chapter 5 --- Conclusion and Future Work --- p.82References: --- p.8