公开(公告)号：US20070106657A1

公开(公告)日：2007-05-10

申请号：US11270917

申请日：2005-11-10

申请人： Vadim Brzeski ,  Reiner Kraft

发明人： Vadim Brzeski ,  Reiner Kraft

IPC分类号： G06F17/30

CPC分类号： G06F16/367 ,  G06F16/36

摘要： Techniques for automatically disambiguating a term with multiple meanings are provided. Term disambiguation is based on both training data and the contents of the body of text in which the term occurs. Once the contextual meaning of a term has been determined, metadata associated with that term can be used to narrow the scope of an automated search. Consequently, documents that contain the term in a context other than the context of the body of text can be excluded from search results. User interface elements may be associated with selected key terms in a web page. User interface elements associated with key terms may be associated with the contextual meanings of those key terms. When such an element is activated, metadata associated with the meaning of the corresponding key term may be submitted to a search engine, which can use the metadata to focus a search for pertinent documents.

摘要翻译： 提供了自动消除含义多义的术语的技术。 短期消歧是基于训练数据和术语发生的文本的内容。 一旦确定了术语的上下文意义，可以使用与该术语关联的元数据来缩小自动搜索的范围。 因此，可以从搜索结果中排除在文本正文的上下文中包含术语的文档。 用户界面元素可以与网页中的所选关键词相关联。 与关键词相关联的用户界面元素可以与这些关键术语的上下文含义相关联。 当激活这样一个元素时，可以将与相应关键词的含义相关联的元数据提交给搜索引擎，搜索引擎可以使用元数据来集中搜索相关文档。