Knowledge-Base Refinement Mechanism towards Machine Translation
-
摘要: 给出了一些知识库求精原则;提出一种面向机器翻译的知识求精机制,以错误严重性为指示器,优先求解最严重的错误,并以系统有效性和知识收敛粒度的变化为依据衡量求精操作的可接受性;给出了基于案例的错误辨识策略以及基于聚焦修正的概化、特化操作.Abstract: Some principles to refine knowledge base are proposed. A knowledge-base (KB) refinement mechanism towards machine translation is provided,in which, the importance of errors serve as the refining indicators and the most serious errors are solved first, and the effectiveness and acceptance of KB refinement are determined based on system performance and the KB convergent gain alternation. The error identification strategy via case-based reasoning is presented. Generalizing and specializing operations based on focus revision are presented as well.
-
1. 李 未.一个开放的逻辑系统.中国科学(A辑), 1992,35(10):1103~1113 2. Morik K. Balanced cooperative modeling. Machine Learning, 1993, 11(2-3):217~236 3. Le Roux B. Knowledge acquisition as a constructive processa methodological issue.Decision Support Systems, 1996, 18:33~42 4. Chang C L.Report on the expert systems validation associate(EVA).Expert Syst Appl,1990, 1(3):217~230 5. 郭宏蕾,姚天顺.一个自然语言通用处理模式及实现机制.软件学报, 1996, 7(863专刊):39~44 6. Kohno T. Error repair and knowledge acquisition via case-based reasoning. Artificial Intelligence,1997, 91:85~101 7. MelCuk I A.Dependency syntax:theory and practice. New York:State University of New York Press,1992 -
点击查看大图
计量
- 文章访问数: 2196
- HTML全文浏览量: 84
- PDF下载量: 971
- 被引次数: 0
下载:
