Resumen de A Cognitive Model of Chinese Word Segmentation for Machine Translation
The Chinese language, unlike English, is written without marked word boundaries, and Chinese word segmentation is often referred to as the bottleneck for Chinese-English machine translation. The current word-segmentation systems in machine translation are either linguistically-oriented or statistically-oriented. Chinese, however, is a pragmatically-oriented language, which explains why the existing Chinese word segmentation systems in machine translation are not successful in dealing with the language. Based on a language investigation consisting of two surveys and eight interviews, and its findings concerning how Chinese people segment a Chinese sentence into words in their reading, we have developed a new word-segmentation model, aiming to address the word-segmentation problem in machine translation from a cognitive perspective.
Plan de l'article
1. Status Quo of CWS Systems in MT
2. Pragmatically-oriented Feature of Chinese
3. A Cognitive Model of CWS for MT
3.1 Preliminary Processing Stage
3.1.1 Sign and Symbol Processing
3.1.2 Special Chinese Character Processing
3.2 Full Segmentation Stage
3.3 Contextual Semantic Analysis and Word Segmentation Selection Stage
3.3.1 Knowledge-based Rules
3.3.2 Contextual and Semantic Analysis and Word Segmentation Selection
4. Concluding Remarks
