Named entity translation matching and learning with mining from multilingual news.

• Other Authors: Cheung, Pik Shan.
• Format: Others
• Language: English; Chinese
• Published: 2004
• Subjects: Machine translating; Cross-language information retrieval
• Online Access: http://library.cuhk.edu.hk/record=b5892099; http://repository.lib.cuhk.edu.hk/en/item/cuhk-324886

Cheung Pik Shan. === Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. === Includes bibliographical references (leaves 79-82). === Abstracts in English and Chinese. === Chapter 1 --- Introduction --- p.1 === Chapter 1.1 --- Named Entity Translation Matching --- p.2 === Chapter 1.2 --- Mining New Translations from News --- p.3 === Chapter 1.3 --- Thesis Organization --- p.4 === Chapter 2 --- Related Work --- p.5 === Chapter 3 --- Named Entity Matching Model --- p.9 === Chapter 3.1 --- Problem Nature --- p.9 === Chapter 3.2 --- Matching Model Investigation --- p.12 === Chapter 3.3 --- Tokenization --- p.15 === Chapter 3.4 --- Hybrid Semantic and Phonetic Matching Algorithm --- p.16 === Chapter 4 --- Phonetic Matching Model --- p.22 === Chapter 4.1 --- Generating Phonetic Representation for English --- p.22 === Chapter 4.1.1 --- Phoneme Generation --- p.22 === Chapter 4.1.2 --- Training the Tagging Lexicon and Transformation Rules --- p.25 === Chapter 4.2 --- Generating Phonetic Representation for Chinese --- p.29 === Chapter 4.3 --- Phonetic Matching Algorithm --- p.31 === Chapter 5 --- Learning Phonetic Similarity --- p.37 === Chapter 5.1 --- The Widrow-Hoff Algorithm --- p.39 === Chapter 5.2 --- The Exponentiated-Gradient Algorithm --- p.41 === Chapter 5.3 --- The Genetic Algorithm --- p.42 === Chapter 6 --- Experiments on Named Entity Matching Model --- p.43 === Chapter 6.1 --- Results for Learning Phonetic Similarity --- p.44 === Chapter 6.2 --- Results for Named Entity Matching --- p.46 === Chapter 7 --- Mining New Entity Translations from News --- p.48 === Chapter 7.1 --- Metadata Generation --- p.52 === Chapter 7.2 --- Discovering Comparable News Cluster --- p.54 === Chapter 7.2.1 --- News Preprocessing --- p.54 === Chapter 7.2.2 --- Gloss Translation --- p.55 === Chapter 7.2.3 --- Comparable News Cluster Discovery --- p.62 === Chapter 7.3 --- Named Entity Cognate Generation --- p.64 === Chapter 7.4 --- Entity Matching --- p.66 === Chapter 7.4.1 --- Matching Algorithm --- p.66 === Chapter 7.4.2 --- Matching Result Production --- p.68 === Chapter 8 --- Experiments on Mining New Translations --- p.69 === Chapter 9 --- Experiments on Context-based Gloss Translation --- p.72 === Chapter 9.1 --- Results on Chinese News Translation --- p.73 === Chapter 9.2 --- Results on Arabic News Translation --- p.75 === Chapter 10 --- Conclusions and Future Work --- p.77 === Bibliography --- p.79 === A --- p.83 === B --- p.85 === C --- p.87 === D --- p.89 === E --- p.91 === F --- p.94 === G --- p.95