원문정보
목차
요약
Abstract
1. Introduction
2. The parallel corpus and it's pre-processing
3. Ailgning the Parallel Corpus
3.1 Length-Based Methods
3.2 Methods Using Cognates
3.3 Methods Using Words as Lexical Information
3.4 Our method - Using Markups as Cognates
4. Pre-processing before model training - chinese Segmentation and English Expression Extraction
4.1 Chinese Segmentation
4.1 English Expression Extraction
5. Translation Model Training
6. Evaluation and analysis
6.1 Translation model as Lexicons
6.2 Effects of Stop-lists
6.3 Analysis of Errors
7. Summary
References
Abstract
1. Introduction
2. The parallel corpus and it's pre-processing
3. Ailgning the Parallel Corpus
3.1 Length-Based Methods
3.2 Methods Using Cognates
3.3 Methods Using Words as Lexical Information
3.4 Our method - Using Markups as Cognates
4. Pre-processing before model training - chinese Segmentation and English Expression Extraction
4.1 Chinese Segmentation
4.1 English Expression Extraction
5. Translation Model Training
6. Evaluation and analysis
6.1 Translation model as Lexicons
6.2 Effects of Stop-lists
6.3 Analysis of Errors
7. Summary
References
저자정보
참고문헌
자료제공 : 네이버학술정보