文摘
英文文摘
独创性声明和关于论文使用授权的说明
ACKNOWLEDGEMENTS
INTRODUCTION
CHAPTER 1 BASIC INFORMATION ABOUT MACHINE TRANSLATION
1.1 WHAT IS MACHINE TRANSLATION
1.2 THE HISTORY AND PRESENT CONDITION OF MACHINE TRANSLATION
1.3 STRATEGIES FOR MACHINE TRANSLATION
1.4 MACHINE TRANSLATION VS. HUMAN TRANSLATION
1.5 THE IMPORTANT ROLE OF MT IN INFORMATION AGE
1.6 SUMMARY
CHAPTER 2 WEB PAGES TRANSLATION
2.1 PRESENT SITUATION OF THE INTERNET
2.2 PRESENT SITUATION OF WEBPAGE TRANSLATION
2.3 THE COMPOSITION OF WEB PAGES
2.4 SUMMARY
CHAPTER 3 MODEL OF WEBPAGE TRANSLATION SYSTEM
3.1 APPROACH TO TAGGED TEXT TRANSLATION IN WEB PAGES
3.1.1 The Classification of Tags
3.1.2 HTML tag manager
3.1.3 Tagged text translation
3.2 APPROACH TO PURE TEXT TRANSLATION
3.2.1 Domain identification
3.2.2 Corpus-based MT on the pure text
3.3 SUMMARY
CHAPTER 4 AMBIGUITIES IN WEBPAGES MACHINE TRANSLATION
4.1 TAGGING AMBIGUITY
4.2 SEMANTIC AMBIGUITY
4.3 SYNTACTIC STRUCTURE AMBIGUITY
4.3.1 Ambiguities from modifiers
4.3.2 Ambiguities from prepositional phrases
4.3.3 Ambiguities from adverbs
4.3.4 Ambiguities from Parallel Structure
CHAPTER 5 CORPUS-BASED STRATEGY TO AMBIGUITIES IN MT
5.1. CORPORA
5.1.1 Training corpora
5.1.2 Raw corpora
5.1.3 Artificial corpora
5.2 SEMANTIC DISAMBIGUATION OF WORD SENSE
5.2.1 Domain determination
5.2.2 Statistical approach
5.2.3 Example-based strategy
5.3 DISAMBIGUATION OF SYNTACTIC ANALYSIS
5.4 TRANSFER DISAMBIGUATION
5.4.1 Ada Semantic Restrictions in the corpus
5.4.2 Mark Syntactic or Semantic Categories in the corpus
5.5 PRAGMATICS AND MT DISAMBIGUATION IN WEBPAGES
5.6 SUMMARY
CONCLUSION
APPENDIX A: AN HTML DOCUMENT
APPENDIXB:
BIBLIOGRAPHY
个人简历
科研成果
