-
公开(公告)号：US20060277033A1
公开(公告)日：2006-12-07
申请号：US11142432
申请日：2005-06-01
申请人： Jianfeng Gao , Hisami Suzuki
发明人： Jianfeng Gao , Hisami Suzuki
IPC分类号： G06F17/21
CPC分类号： G10L15/063 , G10L15/197
摘要： A method of training language model parameters trains discriminative model parameters in the language model based on a performance measure having discrete values.
摘要翻译： 训练语言模型参数的方法是基于具有离散值的性能度量来训练语言模型中的歧视模型参数。
-
公开(公告)号：US20050125429A1
公开(公告)日：2005-06-09
申请号：US10979626
申请日：2004-11-02
CPC分类号： G06F17/30684 , B42D15/00 , B42D15/0053 , Y10S707/917 , Y10S707/954 , Y10S707/956 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936 , Y10S707/99942 , Y10S707/99943 , Y10S707/99944 , Y10S707/99945
摘要： A system is utilized for determining a relationship between first and second textual inputs. The system identifies constituents in the first textual input, having predetermined characteristics indicative of usefulness in determining the relationship. The relationship is then determined based on the constituents identified. The constituents can be eliminated from the first textual input, weighted in the first textual input, or simply annotated in one of a variety of ways.
-
23.发明授权System for improving the performance of information retrieval-type tasks by identifying the relations of constituents 有权通过确定组成部分的关系，提高信息检索类型任务的绩效的系统公开(公告)号：US07299238B2
公开(公告)日：2007-11-20
申请号：US10979532
申请日：2004-11-02
IPC分类号： G06F17/30
CPC分类号： G06F17/30684 , B42D15/00 , B42D15/0053 , Y10S707/917 , Y10S707/954 , Y10S707/956 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936 , Y10S707/99942 , Y10S707/99943 , Y10S707/99944 , Y10S707/99945
摘要： A system is utilized for determining a relationship between first and second textual inputs. The system identifies constituents in the first textual input, having predetermined characteristics indicative of usefulness in determining the relationship. The relationship is then determined based on the constituents identified. The constituents can be eliminated from the first textual input, weighted in the first textual input, or simply annotated in one of a variety of ways.
摘要翻译： 系统用于确定第一和第二文本输入之间的关系。 系统识别第一文本输入中的成分，具有指示在确定关系中有用的预定特征。 然后根据所确定的成分确定关系。 组成成分可以从第一个文本输入中消除，在第一个文本输入中加权，或者以各种方式简单地注释。
-
24.发明申请System for improving the performance of information retrieval-type tasks by identifying the relations of constituentes 有权通过识别组成部分的关系来提高信息检索型任务的绩效的系统公开(公告)号：US20050091243A1
公开(公告)日：2005-04-28
申请号：US10979299
申请日：2004-11-02
CPC分类号： G06F17/30684 , B42D15/00 , B42D15/0053 , Y10S707/917 , Y10S707/954 , Y10S707/956 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936 , Y10S707/99942 , Y10S707/99943 , Y10S707/99944 , Y10S707/99945
摘要： A system is utilized for determining a relationship between first and second textual inputs. The system identifies constituents in the first textual input, having predetermined characteristics indicative of usefulness in determining the relationship. The relationship is then determined based on the constituents identified. The constituents can be eliminated from the first textual input, weighted in the first textual input, or simply annotated in one of a variety of ways.
摘要翻译： 系统用于确定第一和第二文本输入之间的关系。 系统识别第一文本输入中的成分，具有指示在确定关系中有用的预定特征。 然后根据所确定的成分确定关系。 组成成分可以从第一个文本输入中消除，在第一个文本输入中加权，或者以各种方式简单地注释。
-
公开(公告)号：US20050060139A1
公开(公告)日：2005-03-17
申请号：US10957974
申请日：2004-10-04
CPC分类号： G06F17/30684 , B42D15/00 , B42D15/0053 , Y10S707/917 , Y10S707/954 , Y10S707/956 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936 , Y10S707/99942 , Y10S707/99943 , Y10S707/99944 , Y10S707/99945
摘要： A system is utilized for determining a relationship between first and second textual inputs. The system identifies constituents in the first textual input, having predetermined characteristics indicative of usefulness in determining the relationship. The relationship is then determined based on the constituents identified. The constituents can be eliminated from the first textual input, weighted in the first textual input, or simply annotated in one of a variety of ways.
-
公开(公告)号：US5946648A
公开(公告)日：1999-08-31
申请号：US121655
申请日：1998-07-24
CPC分类号： G06F17/2755 , G06F17/274 , G06F17/277 , G06F17/2863
摘要： A word breaking facility operates to identify words within a Japanese text string. The word breaking facility performs morphological processing to identify postfix bound morphemes and prefix bound morphemes. The word breaking facility also performs opheme matching to identify likely stem characters. A scoring heuristic is applied to determine an optimal analysis that includes a postfix analysis, a stem analysis, and a prefix analysis. The morphological analyses are stored in an efficient compressed format to minimize the amount of memory they occupy and maximize the analysis speed. The morphological analyses of postfixes, stems, and prefixes is performed in a right-to-left fashion. The word breaking facility may be used in applications that demand identity of selection granularity, autosummarization applications, content indexing applications, and natural language processing applications.
摘要翻译： 单词断开设施用于识别日语文本字符串中的单词。 词突破设施执行形态处理以识别后缀绑定语素和前缀绑定语素。 单词破解工具还执行opheme匹配以识别可能的字符字符。 应用得分启发式来确定包括后缀分析，茎分析和前缀分析的最佳分析。 形态分析以有效的压缩格式存储，以最小化其占用的内存量并最大化分析速度。 后缀，茎和前缀的形态学分析以从右到左的方式进行。 单词破解工具可用于需要选择粒度，自动归类应用程序，内容索引应用程序和自然语言处理应用程序的身份的应用程序。
-
公开(公告)号：US08209163B2
公开(公告)日：2012-06-26
申请号：US11504285
申请日：2006-08-15
申请人： Hisami Suzuki , Kristina Toutanova
发明人： Hisami Suzuki , Kristina Toutanova
IPC分类号： G06F17/28
CPC分类号： G06F17/2818 , G06F17/274
摘要： Grammatical element prediction is used in the context of machine translation. Features from both the source language and the target language sentences (or other text fragments) are used in predicting the grammatical elements.
摘要翻译： 语法元素预测用于机器翻译的上下文中。 源语言和目标语言句子（或其他文本片段）的特征用于预测语法元素。
-
公开(公告)号：US07865352B2
公开(公告)日：2011-01-04
申请号：US11483943
申请日：2006-07-10
申请人： Hisami Suzuki , Kristina Toutanova
发明人： Hisami Suzuki , Kristina Toutanova
IPC分类号： G06F17/28
CPC分类号： G06F17/2775 , G06F17/2863
摘要： Grammatical element prediction is used to predict grammatical elements in text fragments (such as phrases or sentences). In one embodiment, a statistical model, using syntax features, is used to predict grammatical elements.
摘要翻译： 语法元素预测用于预测文本片段（如短语或句子）中的语法元素。 在一个实施例中，使用语法特征的统计模型用于预测语法元素。
-
公开(公告)号：US07680659B2
公开(公告)日：2010-03-16
申请号：US11142432
申请日：2005-06-01
申请人： Jianfeng Gao , Hisami Suzuki
发明人： Jianfeng Gao , Hisami Suzuki
CPC分类号： G10L15/063 , G10L15/197
摘要： A method of training language model parameters trains discriminative model parameters in the language model based on a performance measure having discrete values.
摘要翻译： 训练语言模型参数的方法是基于具有离散值的性能度量来训练语言模型中的歧视模型参数。
-
公开(公告)号：US20080109425A1
公开(公告)日：2008-05-08
申请号：US11591937
申请日：2006-11-02
CPC分类号： G06F17/30719
摘要： Document summarization is performed by scoring individual words in sentences in a document or document cluster. Sentences from the document or document cluster are selected to form a summary based on the scores of the words contained in those sentences.
摘要翻译： 通过在文档或文档集群中的句子中的单个单词进行评分来执行文档摘要。 选择文档或文档集合中的句子，以便根据这些句子中包含的单词的分数来形成一个摘要。
-
-
-
-
-
-
-
-
-
搜索结果
31 条记录 (耗时 0.017 秒)
