公开(公告)号：US20050022114A1

公开(公告)日：2005-01-27

申请号：US09683238

申请日：2001-12-05

Applicant: James Shanahan ,  Gregory Grefenstette

Inventor： James Shanahan ,  Gregory Grefenstette

IPC: G06F17/24 ,  G06F17/30

CPC classification number: G06F21/10 ,  G06F16/93

Abstract: A digitally readable identifier located proximate to a physical object communicates a personality identifier. The personality identifier is automatically or manually associated with document content. The personality identifier is automatically associated with document content using context information that identifies the place of a physical object and/or the time the personality identifier is communicated. Once the personality identifier is associated with document content, a meta-document server enriches the document content in accordance with a predefined thematic set of document services identified by the personality identifier.

Abstract translation: 位于物理对象附近的数字可读标识符传达个性标识符。 人格标识符与文档内容自动或手动关联。 使用识别物理对象的位置和/或个性标识符被传达的时间的上下文信息来自动地将个性标识符与文档内容相关联。 一旦个性标识符与文档内容相关联，元文档服务器根据由个性标识符标识的文档服务的预定专题集来丰富文档内容。

公开(公告)号：US08219904B2

公开(公告)日：2012-07-10

申请号：US12784840

申请日：2010-05-21

Applicant: James Shanahan ,  Gregory Grefenstette

Inventor： James Shanahan ,  Gregory Grefenstette

IPC: G06F17/00 ,  G06F7/16 ,  G06F15/16

CPC classification number: G06F17/30011

Abstract: A system includes a meta-document, i.e., a document including content information which has a set of document service requests associated with it. A document service is a process which uses a portion of the document content as a starting point to obtain other information pertaining to that content. A scheduler selects a document service request from the set, then initiates and manages managing communication with a service provider to satisfy the selected document service. Any results received from the selected document service are integrated into the document.

Abstract translation: 系统包括元文档，即包括具有与其相关联的一组文档服务请求的内容信息的文档。 文档服务是使用文档内容的一部分作为起点获得与该内容有关的其他信息的过程。 调度器从集合中选择文档服务请求，然后启动和管理管理与服务提供商的通信以满足选定的文档服务。 从所选文档服务收到的任何结果都将整合到文档中。

公开(公告)号：US20100235337A1

公开(公告)日：2010-09-16

申请号：US12784840

申请日：2010-05-21

Applicant: James Shanahan ,  Gregory Grefenstette

Inventor： James Shanahan ,  Gregory Grefenstette

IPC: G06F17/30

CPC classification number: G06F17/30011

Abstract: A system includes a meta-document, i.e., a document including content information which has a set of document service requests associated with it. A document service is a process which uses a portion of the document content as a starting point to obtain other information pertaining to that content. A scheduler selects a document service request from the set, then initiates and manages managing communication with a service provider to satisfy the selected document service. Any results received from the selected document service are integrated into the document.

Abstract translation: 系统包括元文档，即包括具有与其相关联的一组文档服务请求的内容信息的文档。 文档服务是使用文档内容的一部分作为起点获得与该内容有关的其他信息的过程。 调度器从集合中选择文档服务请求，然后启动和管理管理与服务提供商的通信以满足选定的文档服务。 从所选文档服务收到的任何结果都将整合到文档中。

公开(公告)号：US07757168B1

公开(公告)日：2010-07-13

申请号：US09543962

申请日：2000-04-07

Applicant: James Shanahan ,  Gregory Grefenstette

Inventor： James Shanahan ,  Gregory Grefenstette

IPC: G06F17/00 ,  G06F15/16

CPC classification number: G06F17/30011

Abstract: A system includes a meta-document, i.e., a document including content information which has a set of document service requests associated with it. A document service is a process which uses a portion of the document content as a starting point to obtain other information pertaining to that content. A scheduler selects a document service request from the set, then initiates and manages managing communication with a service provider to satisfy the selected document service. Any results received from the selected document service are integrated into the document.

Abstract translation: 系统包括元文档，即包括具有与其相关联的一组文档服务请求的内容信息的文档。 文档服务是使用文档内容的一部分作为起点获得与该内容有关的其他信息的过程。 调度器从集合中选择文档服务请求，然后启动和管理管理与服务提供商的通信以满足选定的文档服务。 从所选文档服务收到的任何结果都将整合到文档中。

公开(公告)号：US20080005651A1

公开(公告)日：2008-01-03

申请号：US11852960

申请日：2007-09-10

Applicant: Gregory Grefenstette ,  James Shanahan

Inventor： Gregory Grefenstette ,  James Shanahan

IPC: G06F15/00

CPC classification number: G06F17/3061 ,  G06F17/30867

Abstract: A method, system and article of manufacture therefor, are disclosed for automatically generating a query from document content.

Abstract translation: 公开了一种用于从文档内容自动生成查询的方法，系统及其制造。

公开(公告)号：US20070021956A1

公开(公告)日：2007-01-25

申请号：US11481584

申请日：2006-07-06

Applicant: Yan Qu ,  Gregory Grefenstette

Inventor： Yan Qu ,  Gregory Grefenstette

IPC: G06F17/20 ,  G06F17/27

CPC classification number: G06F17/275 ,  G06F17/2223

Abstract: A method of generating an ideographic representation of a name given in a letter based system begins with a determination of the language of original. After determining the language of origin for the name, the name is segmented into a segmentation sequence in response to the determined language of origin. A candidate representation is generated for the segmentation sequence based on ideographic representations of the segments. A corpus is used to validate the candidate representation. The corpus can be either a monolingual corpus or a multilingual corpus. The method can also include adding an additional validation step using either a monolingual corpus or a multilingual corpus, which ever was not used in the first validation step. Because of the rules governing abstracts, this abstract should not be used to construe the claims.

Abstract translation: 生成基于字母的系统中给出的名称的表意表示的方法开始于原始语言的确定。 在确定名称的起源语言之后，根据确定的起源语言将该名称分割成分段序列。 基于段的表意图表示为分割序列生成候选表示。 语料库用于验证候选人的表示。 语料库可以是单语语料库或多语言语料库。 该方法还可以包括使用单语语料库或多语言语料库添加额外的验证步骤，该语料库在第一个验证步骤中没有使用。 由于管理摘要的规则，本摘要不应用于解释索赔。

公开(公告)号：US20100114558A1

公开(公告)日：2010-05-06

申请号：US12532280

申请日：2008-03-12

Applicant: Christian Fluhr ,  Gregory Grefenstette ,  Nasredlne Semmar

Inventor： Christian Fluhr ,  Gregory Grefenstette ,  Nasredlne Semmar

IPC: G06F17/28

CPC classification number: G06F17/2827 ,  G06F17/2845

Abstract: The present invention relates to an automatic translation method.When a sentence in a source language is translated into a sentence in a target language, the method comprises: a step (1) of extracting the set of sentence portions of the target language from a textual database that correspond to a total or partial translation of the source sentence to be translated; a step (2) of determining all the assemblies of these target sentence portions that overlap the source sentence; a step (3) of choosing the best assemblies according to a criterion of maximum overlap between the target sentence portions assembled in the preceding step and according to a criterion of minimizing the number of assembled elements; a step (4) of determining the target sentence by choosing the best assembly according to coherence criteria. The invention is notably applicable to the translation of texts in a rare language.More generally, it applies to translation with no previously established bilingual texts.

Abstract translation: 本发明涉及一种自动翻译方法。 当源语言中的句子被翻译成目标语言的句子时，该方法包括：步骤（1）从对应于完全或部分翻译的文本数据库中提取目标语言的一组句子部分 要翻译的源句; 确定与源语句重叠的目标句子部分的所有组合的步骤（2）; 根据在前述步骤中组装的目标句子部分之间的最大重叠的标准并根据最小化组装元件的数量的标准来选择最佳组件的步骤（3） 通过根据相干标准选择最佳组合来确定目标句子的步骤（4）。 本发明特别适用于以罕见语言翻译文本。 更一般地说，它适用于没有既定双语文本的翻译。

公开(公告)号：US06473729B1

公开(公告)日：2002-10-29

申请号：US09466823

申请日：1999-12-20

Applicant: Michel Gastaldo ,  Gregory Grefenstette

Inventor： Michel Gastaldo ,  Gregory Grefenstette

IPC: G06F1728

CPC classification number: G06F17/2827

Abstract: A system and method are provided for translating an input text from a natural source language to a natural target language. The system stores a database that contains a plurality of pairs of text fragments with each pair including a text fragment in the source language and a corresponding text fragment in the target language. Each text fragment contains at least one word phrase and represents a primary grammatical unit such as a sentence or a clause. For translating a word phrase, the database is queried using a phrase index of the database, where the phrase index indexes text fragments by word phrases. Word phrases are noun phrases or word phrases. Alternatively, word phrases are predicates involving at least one verb and one noun or adjective used as a noun. The system further comprises a phrase extractor for extracting a word phrase from a text fragment of an input text.

Abstract translation: 提供了一种用于将输入文本从自然源语言翻译成自然目标语言的系统和方法。 系统存储包含多对文本片段的数据库，每对文本片段包括源语言中的文本片段和目标语言中的相应文本片段。 每个文本片段至少包含一个单词，并表示一个主要的语法单元，例如句子或子句。 对于翻译单词短语，使用数据库的短语索引查询数据库，其中短语索引通过单词短语索引文本片段。 词短语是名词短语或单词短语。 或者，词语是涉及用作名词的至少一个动词和一个名词或形容词的谓词。 该系统还包括用于从输入文本的文本片段中提取词组的短语提取器。

公开(公告)号：US06289304B1

公开(公告)日：2001-09-11

申请号：US09270457

申请日：1999-03-17

Applicant: Gregory Grefenstette

Inventor： Gregory Grefenstette

IPC: G06F1727

CPC classification number: G06F17/30719 ,  G10L13/00

Abstract: Text is summarized using part-of-speech (POS) data indicating parts of speech for tokens in the text. The POS data can be obtained using input text data defining the text, such as by POS tagging. The POS data can be used to obtain group data indicating groups of tokens of the text, such as verb groups and noun groups. The group data can also indicate, within each group, any tokens that meet a POS based removal criterion. The group data can be used to obtain summarized text data by removing tokens that meet the removal criterion. The original text may be obtained via scanner or video camera from a user's document, and may be recognized to obtain input text data. The summarized text may output as text or as audio pronunciation using a speech synthesizer.

Abstract translation: 使用说明文字中的令牌的部分语音的部分（POS）数据来概括文本。 可以使用定义文本的输入文本数据（例如通过POS标记）来获得POS数据。 POS数据可以用于获取指示文本的令牌组的组数据，例如动词组和名词组。 组数据还可以在每个组内指示符合基于POS的删除标准的任何令牌。 组数据可用于通过删除符合删除标准的令牌来获取汇总的文本数据。 原始文本可以通过扫描仪或摄像机从用户的文档获得，并且可以被识别以获得输入的文本数据。 汇总的文本可以使用语音合成器作为文本或作为音频发音输出。

公开(公告)号：US06973423B1

公开(公告)日：2005-12-06

申请号：US09100189

申请日：1998-06-18

Applicant: Geoffrey D. Nunberg ,  Hinrich Schuetze ,  Jan O. Pedersen ,  Brett L. Kessler ,  Gregory Grefenstette

Inventor： Geoffrey D. Nunberg ,  Hinrich Schuetze ,  Jan O. Pedersen ,  Brett L. Kessler ,  Gregory Grefenstette

IPC: G06F17/20 ,  G06F17/27 ,  G06F17/30

CPC classification number: G06F17/2745 ,  G06F17/274

Abstract: A processor implemented method of identifying the text genre of a machine-readable, untagged text. The processor implemented method begins by generating a cue vector from the text, which represents occurrences in the text of a first set of nonstructural, surface cues, which are easily computable. Afterward, the processor determines whether the text is an instance of a first text genre using the cue vector and a weighting vector associated with the first text genre.

Abstract translation: 一种处理器实现的方法，用于识别机器可读，未标记的文本的文本类型。 处理器实现的方法开始于从文本生成提示向量，其代表第一组非结构化表面线索的文本中的出现，其易于计算。 之后，处理器确定文本是否是使用提示向量的第一文本类型的实例以及与第一文本类型相关联的加权向量。