专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US07526424B2 Sentence realization model for a natural language generation system 失效
标题翻译：自然语言生成系统的句子实现模型
公开(公告)号：US07526424B2
公开(公告)日：2009-04-28
申请号：US10103163
申请日：2002-03-20
申请人： Simon Corston-Oliver , Michael Gamon , Eric Ringger , Robert C. Moore , Zhu Zhang
发明人： Simon Corston-Oliver , Michael Gamon , Eric Ringger , Robert C. Moore , Zhu Zhang
IPC分类号： G06F17/27
CPC分类号： G06F17/2881
摘要： The present invention is a sentence realization system that processes an abstract linguistic representation (ALR) of a sentence into a structure that can be fully realizable. The system includes a tree conversion component that receives the ALR and generates a basic syntax tree from the ALR. A global movement component then receives the basic syntax tree and hierarchically orders child nodes in that syntax tree relative to ancestor nodes. An intra-constituent ordering component then establishes a linear order among the nodes such that the syntax tree is fully ordered. A surface cleanup component receives the fully ordered tree and performs a number of realization operations to generate surface realizations for constituents that are still represented in an abstract way in the fully ordered syntax tree.
摘要翻译：本发明是将句子的抽象语言表示（ALR）处理成可以完全实现的结构的句子实现系统。该系统包括接收ALR并从ALR生成基本语法树的树转换组件。然后，全局运动组件接收基本语法树，并相对于祖先节点分层排序该语法树中的子节点。然后，内部组件排序组件在节点之间建立一个线性顺序，使得语法树被完全排序。表面清理组件接收完全有序的树并执行多个实现操作，以便在完全有序的语法树中以抽象方式表示的组成部分生成表面实现。

2. 发明授权

US07346493B2 Linguistically informed statistical models of constituent structure for ordering in sentence realization for a natural language generation system 有权
标题翻译：语言知识的组织结构统计模型，用于自然语言生成系统的句子实现中的排序
公开(公告)号：US07346493B2
公开(公告)日：2008-03-18
申请号：US10396549
申请日：2003-03-25
申请人： Eric Ringger , Michael Gamon , Martine Smets , Simon Corston-Oliver , Robert C. Moore
发明人： Eric Ringger , Michael Gamon , Martine Smets , Simon Corston-Oliver , Robert C. Moore
IPC分类号： G06F17/21 , G06F17/27
CPC分类号： G06F17/2881 , G06F17/2715 , G10L15/26
摘要： The present invention is a tree ordering component within a sentence realization system which receives an unordered syntax tree and generates a ranked list of alternative ordered syntax trees from the unordered syntax tree. The present invention also includes statistical models of constituent structure employed by the tree ordering component in scoring the alternative ordered trees.
摘要翻译：本发明是句子实现系统中的树顺序分量，其接收无序语法树，并从无序语法树生成替代有序语法树的排序列表。本发明还包括由树排序组件在对替代有序树进行评分时使用的组成结构的统计模型。

3. 发明申请

US20060200341A1 Method and apparatus for processing sentiment-bearing text 有权
标题翻译：处理情感文本的方法和装置
公开(公告)号：US20060200341A1
公开(公告)日：2006-09-07
申请号：US11105619
申请日：2005-04-14
申请人： Simon Corston-Oliver , Anthony Aue , Eric Ringger , Michael Gamon
发明人： Simon Corston-Oliver , Anthony Aue , Eric Ringger , Michael Gamon
IPC分类号： G06F17/28
CPC分类号： G06F17/30707 , G06F17/274
摘要： The present invention provides a system for identifying, extracting, clustering and analyzing sentiment-bearing text. In one embodiment, the invention implements a pipeline capable of accessing raw text and presenting it in a highly usable and intuitive way.
摘要翻译：本发明提供一种用于识别，提取，聚类和分析情感文本的系统。在一个实施例中，本发明实现了能够访问原始文本并且以高度可用和直观的方式呈现它的流水线。

4. 发明申请

US20060200342A1 System for processing sentiment-bearing text 有权
标题翻译：处理情感文本的系统
公开(公告)号：US20060200342A1
公开(公告)日：2006-09-07
申请号：US11105624
申请日：2005-04-14
申请人： Simon Corston-Oliver , Anthony Aue , Eric Ringger , Michael Gamon
发明人： Simon Corston-Oliver , Anthony Aue , Eric Ringger , Michael Gamon
IPC分类号： G06F17/21
CPC分类号： G06F17/3071 , G06F17/274
摘要： The present invention provides a system for identifying, extracting, clustering and analyzing sentiment-bearing text. In one embodiment, the invention implements a pipeline capable of accessing raw text and presenting it in a highly usable and intuitive way.
摘要翻译：本发明提供一种用于识别，提取，聚类和分析情感文本的系统。在一个实施例中，本发明实现了能够访问原始文本并且以高度可用和直观的方式呈现它的流水线。

5. 发明申请

US20050091243A1 System for improving the performance of information retrieval-type tasks by identifying the relations of constituentes 有权
标题翻译：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
申请人： Simon Corston-Oliver , William Dolan , Hisami Suzuki
发明人： Simon Corston-Oliver , William Dolan , Hisami Suzuki
IPC分类号： B42D15/00 , G06F17/30 , G06F7/00
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。

6. 发明申请

US20050060139A1 System for improving the performance of information retrieval-type tasks by identifying the relations of constituents 有权
公开(公告)号：US20050060139A1
公开(公告)日：2005-03-17
申请号：US10957974
申请日：2004-10-04
申请人： Simon Corston-Oliver , William Dolan , Hisami Suzuki
发明人： Simon Corston-Oliver , William Dolan , Hisami Suzuki
IPC分类号： B42D15/00 , G06F17/30 , G06F17/28
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.

7. 发明申请

US20050125429A1 System for improving the performance of information retrieval-type tasks by identifying the relations of constituents 有权
公开(公告)号：US20050125429A1
公开(公告)日：2005-06-09
申请号：US10979626
申请日：2004-11-02
申请人： Simon Corston-Oliver , William Dolan , Hisami Suzuki
发明人： Simon Corston-Oliver , William Dolan , Hisami Suzuki
IPC分类号： B42D15/00 , G06F17/30 , G06F17/00
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.

8. 发明申请

US20050125404A1 System for improving the performance of information retrieval-type tasks by identifying the relations of constituents 有权
公开(公告)号：US20050125404A1
公开(公告)日：2005-06-09
申请号：US10979532
申请日：2004-11-02
申请人： Simon Corston-Oliver , William Dolan , Hisami Suzuki
发明人： Simon Corston-Oliver , William Dolan , Hisami Suzuki
IPC分类号： B42D15/00 , 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.

9. 发明申请

US20050114294A1 System for improving the performacne of information retrieval-type tasks by identifying the relations of constituents 有权
标题翻译：通过确定组成部分的关系，提高信息检索型任务的执行能力
公开(公告)号：US20050114294A1
公开(公告)日：2005-05-26
申请号：US10979531
申请日：2004-11-02
申请人： Simon Corston-Oliver , William Dolan , Hisami Suzuki
发明人： Simon Corston-Oliver , William Dolan , Hisami Suzuki
IPC分类号： B42D15/00 , 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。

10. 发明申请

US20060184351A1 Linguistically intelligent text compression 有权
公开(公告)号：US20060184351A1
公开(公告)日：2006-08-17
申请号：US11397503
申请日：2006-04-04
申请人： Simon Corston-Oliver , Sharad Mathur
发明人： Simon Corston-Oliver , Sharad Mathur
IPC分类号： G06F17/20
CPC分类号： G06F17/2785 , G06F17/271 , G06F17/2755 , G06F17/277 , G06F17/278
摘要： A text processor processes text in a message. The text processor generates a plurality of compressed forms of components of the message. The processor performs a linguistic analysis on the body of text to obtain a linguistic output indicative of linguistic components of the body of text. The processor then generates the plurality of compressed forms that can be used to compress the body of text. The plurality of compressed forms are generated based on the linguistic output. The invention can be implemented as a method of generating the compressed forms and as an apparatus.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式