Automatic text summarization

Incluye índice y bibliografía.

Introduction -- Part 1. Foundations -- 1. Why Summarize Texts? -- 1.1. The Need For Automatic Summarization -- 1.2. Definitions Of Text Summarization -- 1.3. Categorizing Automatic Summaries -- 1.4. Applications Of Automatic Text Summarization -- 1.5. About Automatic Text Summarization -- 1.6. Conclusion -- 2. Automatic Text Summarization: Some Important Concepts -- 2.1. Processes Before The Process -- 2.1.1. Sentence-Term Matrix: The Vector Space Model (VSM) Model -- 2.2. Extraction, Abstraction Or Compression? -- 2.3. Extraction-Based Summarization -- 2.3.1. Surface-Level Algorithms -- 2.3.2. Intermediate-Level Algorithms -- 2.3.3. Deep Parsing Algorithms -- 2.4. Abstract Summarization -- 2.4.1. FRUMP -- 2.4.2. Information Extraction And Abstract Generation -- 2.5. Sentence Compression And Fusion -- 2.5.1. Sentence Compression -- 2.5.2. Multisentence Fusion -- 2.6. The Limits Of Extraction -- 2.6.1. Cohesion And Coherence -- 2.6.2. The HexTAC Experiment -- 2.7. The Evolution Of Text Summarization Tasks -- 2.7.1. Traditional Tasks -- 2.7.2. Current And Future Problems -- 2.8. Evaluating Summaries -- 2.9. Conclusion -- 3. Single-Document Summarization -- 3.1. Historical Approaches -- 3.1.1. Luhn’s Automatic Creation Of Literature Abstracts -- 3.1.2. The Luhn Algorithm -- 3.1.3. Edmundson’s Linear Combination -- 3.1.4. Extracts By Elimination -- 3.2. Machine Learning Approaches -- 3.2.1. Machine Learning Parameters -- 3.3. State-Of-The-Art Approaches -- 3.4. Latent Semantic Analysis -- 3.4.1. Singular Value Decomposition (SVD) -- 3.4.2. Sentence Weighting By SVD -- 3.5. Graph-Based Approaches -- 3.5.1. PAGERANK And SNA Algorithms -- 3.5.2. Graphs And Automatic Text Summarization -- 3.5.3. Constructing The Graph -- 3.5.4. Sentence Weighting -- 3.6. DIVTEX: A Summarizer Based On The Divergence Of Probability Distribution -- 3.7. CORTEX -- 3.7.1. Frequential Measures -- 3.7.2. Hamming Measures -- 3.7.3. Mixed Measures -- 3.7.4. Decision Algorithm -- 3.8. ARTEX -- 3.9. ENERTEX -- 3.9.1. Spins And Neural Networks -- 3.9.2. The Textual Energy Similarity Measure -- 3.9.3. Summarization By Extraction And Textual Energy -- 3.10. Approaches Using Rhetorical Analysis -- 3.11. Lexical Chains -- 3.12. Conclusion -- 4. Guided Multi-Document Summarization -- 4.1. Introduction -- 4.2. The Problems Of Multidocument Summarization -- 4.3. DUC/TAC & INEX Tweet Contextualization -- 4.4. The Taxonomy Of MDS Methods -- 4.4.1. Structure Based -- 4.4.2. Vector Space Model Based -- 4.4.3. Graph Based -- 4.5. Some Multi-Document Summarization Systems And Algorithms -- 4.5.1. SUMMONS -- 4.5.2. Maximal Marginal Relevance -- 4.5.3. A Multidocument Biography Summarization System -- 4.5.4. Multi-Document ENERTEX -- 4.5.5. MEAD -- 4.5.6. CATS -- 4.5.7. SUMUM And SUMMA -- 4.5.8. NEO-CORTEX -- 4.6. Update Summarization -- 4.6.1. Update Summarization Pilot Task At DUC 2007 -- 4.6.2. Update Summarization Task At TAC 2008 And 2009 -- 4.6.3. A Minimization-Maximization Approach -- 4.6.4. The ICSI System At TAC 2008 And 2009 -- 4.6.5. The CBSEAS System At TAC -- 4.7. Multidocument Summarization By Polytopes -- 4.8. Redundancy -- 4.9. Conclusion -- Part 2. Emerging Systems -- 5. Multi And Cross-Lingual Summarization -- 5.1. Multilingualism, The Web And Automatic Summarization -- 5.2. Automatic Multilingual Summarization -- 5.3. MEAD -- 5.4. SUMMARIST -- 5.5. COLUMBIA NEWSBLASTER -- 5.6. NEWSEXPLORER -- 5.7. GOOGLE NEWS -- 5.8. CAPS -- 5.9. Automatic Cross-Lingual Summarization -- 5.9.1. The Quality Of Machine Translation -- 5.9.2. A Graph-Based Cross-Lingual Summarizer -- 5.10. Conclusion -- 6. Source And Domain-Specific Summarization -- 6.1. Genre, Specialized Documents And Automatic Summarization -- 6.2. Automatic Summarization And Organic Chemistry -- 6.2.1. YACHS2 -- 6.3. Automatic Summarization And Biomedicine -- 6.3.1. SUMMTERM -- 6.3.2. A Linguistic-Statistical Approach -- 6.4. Summarizing Court Decisions -- 6.5. Opinion Summarization -- 6.5.1. CBSEAS At TAC 2008 Opinion Task -- 6.6.Web Summarization -- 6.6.1. Web Page Summarization -- 6.6.2. OCELOT And The Statistical Gist -- 6.6.3. Multitweet Summarization -- 6.6.4. Email Summarization -- 6.7. Conclusion -- 7. Text Abstracting -- 7.1. Abstraction-Based Automatic Summarization -- 7.2. Systems Using Natural Language Generation -- 7.3. An Abstract Generator Using Information Extraction -- 7.4. Guided Summarization And A Fully Abstractive Approach -- 7.5. Abstraction-Based Summarization Via Conceptual Graphs -- 7.6. Multisentence Fusion -- 7.6.1. Multisentence Fusion Via Graphs -- 7.6.2. Graphs And Keyphrase Extraction: The Takahé System -- 7.7. Sentence Compression -- 7.7.1. Symbolic Approaches -- 7.7.2. Statistical Approaches -- 7.7.3. A Statistical-Linguistic Approach -- 7.8. Conclusion -- 8. Evaluating Document Summaries -- 8.1. How Can Summaries Be Evaluated? -- 8.2. Extrinsic Evaluations -- 8.3. Intrinsic Evaluations -- 8.3.1. The Baseline Summary -- 8.4. TIPSTER SUMMAC Evaluation Campaigns -- 8.4.1. Ad Hoc Task -- 8.4.2. Categorization Task -- 8.4.3. Question-Answering Task -- 8.5. NTCIR Evaluation Campaigns -- 8.6. DUC/TAC Evaluation Campaigns -- 8.6.1. Manual Evaluations -- 8.7. CLEF-INEX Evaluation Campaigns -- 8.8. Semi-Automatic Methods For Evaluating Summaries -- 8.8.1. Level Of Granularity: The Sentence -- 8.8.2. Level Of Granularity: Words -- 8.9. Automatic Evaluation Via Information Theory -- 8.9.1. Divergence Of Probability Distribution -- 8.9.2. FRESA -- 8.10. Conclusion -- Conclusion -- Appendix 1. Information Retrieval, NLP And ATS -- Appendix 2. Automatic Text Summarization Resources -- Bibliography -- Index