车超,金博,滕弘飞,屈福政.基于综合信息的汛期库水位实时动态控制方法[J].,2010,(4):603-608 |
基于综合信息的汛期库水位实时动态控制方法 |
Multi-strategy approach to Chinese word sense disambiguation based on sememe relations |
|
DOI:10.7511/dllgxb201004023 |
中文关键词: 知网 词义消歧 义原关系 语义相关度 |
英文关键词: HowNet word sense disambiguation sememe relation semantic relevancy |
基金项目:“八六三”国家高技术研究发展计划资助项目(2006AA04Z109);国家自然科学基金资助项目(60674078). |
|
摘要点击次数: 831 |
全文下载次数: 847 |
中文摘要: |
词义消歧是自然语言处理领域的重点和难点问题.提出了一种基于知网中义原关系的多策略词义消歧方法.该方法利用知网中义原间最基本和最重要的部件-整体和属性-宿主关系进行词义消歧,并辅以基于值-属性关系、中文信息结构和语义相关度的消歧方法.在SENSEVAL-3汉语词义消歧任务测试文本上的实验表明,该方法与官方结果相比,具有较好的计算性能. |
英文摘要: |
Word sense disambiguation (WSD) is an important and difficult problem in natural language processing. A multi-strategy approach for WSD is proposed based on sememe relations in HowNet. The approach benefits from part-whole and attribute-host relations, which are the most basic and important sememe relations in HowNet. In addition, value-attribute relation, message structure and semantic relevancy are utilized to do disambiguation as supplement. The experimental results of SENSEVAL-3 Chinese WSD task show that the proposed method performs well in comparison with the official results. |
查看全文
查看/发表评论 下载PDF阅读器 |
关闭 |
|
|
|