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

US07467081B2 Language-understanding training database action pair augmentation using bidirectional translation 有权
标题翻译：语言理解训练数据库动作对增强使用双向翻译
公开(公告)号：US07467081B2
公开(公告)日：2008-12-16
申请号：US11656155
申请日：2007-01-22
申请人： Hiyan Alshawi , Shona Douglas
发明人： Hiyan Alshawi , Shona Douglas
IPC分类号： G06F17/21 , G06F17/28
CPC分类号： G06F17/2827 , G10L15/22 , G10L15/26 , G10L2015/223 , H04M3/4936 , H04M2201/40
摘要： Embodiments of the present invention relate to a method and system for augmenting a training database of an automated language-understanding system. In one embodiment, a training example in a first language is received from the training database. The first language-training example translated to a second language output. The second language output is translated to a first variant of the first language-training example. An action pair including the first variant of the first language-training example and an action command associated with the first language-training example is stored in an augmented training database.
摘要翻译：本发明的实施例涉及一种用于增强自动语言理解系统的训练数据库的方法和系统。在一个实施例中，从训练数据库接收第一语言的训练示例。第一语言训练示例转换为第二语言输出。第二语言输出被转换为第一语言训练示例的第一变体。将包括第一语言训练示例的第一变体和与第一语言训练示例相关联的动作命令的动作对存储在增强训练数据库中。

2. 发明授权

US08073683B2 Language-understanding training database action pair augmentation using bidirectional translation 有权
标题翻译：语言理解训练数据库动作对增强使用双向翻译
公开(公告)号：US08073683B2
公开(公告)日：2011-12-06
申请号：US12336429
申请日：2008-12-16
申请人： Hiyan Alshawi , Shona Douglas
发明人： Hiyan Alshawi , Shona Douglas
IPC分类号： G06F17/21 , G06F17/26
CPC分类号： G06F17/2827 , G10L15/22 , G10L15/26 , G10L2015/223 , H04M3/4936 , H04M2201/40
摘要： Embodiments of the present invention relate to a method and system for augmenting a training database of an automated language-understanding system. In one embodiment, a training example in a first language is received from the training database. The first language-training example is translated to a second language output. The second language output is translated to a first variant of the first language-training example. An action pair including the first variant of the first language-training example and an action command associated with the first language-training example is stored in an augmented training database.
摘要翻译：本发明的实施例涉及一种用于增强自动语言理解系统的训练数据库的方法和系统。在一个实施例中，从训练数据库接收第一语言的训练示例。第一语言训练示例被转换为第二语言输出。第二语言输出被转换为第一语言训练示例的第一变体。将包括第一语言训练示例的第一变体和与第一语言训练示例相关联的动作命令的动作对存储在增强训练数据库中。

3. 发明授权

US06195631B1 Method and apparatus for automatic construction of hierarchical transduction models for language translation 有权
标题翻译：自动构建语言翻译分层转换模型的方法和装置
公开(公告)号：US06195631B1
公开(公告)日：2001-02-27
申请号：US09198109
申请日：1998-11-23
申请人： Hiyan Alshawi , Shona Douglas
发明人： Hiyan Alshawi , Shona Douglas
IPC分类号： G06F1728
CPC分类号： G06F17/2827
摘要： A method and apparatus for automatically constructing hierarchical transduction models for language translation is presented. The input to the construction process may be a database of examples each consisting of a transcribed speech utterance and its translation into another language. A translation pairing score is assigned (or computed) for translating a word in the source language into each of the possible translations it has in the target language. For each instance of the resulting training dataset, a head transducer may be constructed that translates the source string into the target string by splitting the source string into a source head word, the words preceding the source head word, and the words following the source head word. This process may be performed recursively to generate a set of transducer fragments. The transducer fragments may form a statistical head transducer model. The head transducer translation model may then be input into a transduction search module.
摘要翻译：提出了一种自动构建语言翻译分层转换模型的方法和装置。对施工过程的输入可以是每个由转录的语音说话和其翻译成另一种语言的例子的数据库。分配（或计算）用于将源语言中的单词翻译成目标语言中的每个可能的翻译的翻译配对分数。对于所得到的训练数据集的每个实例，可以构造头传感器，其通过将源字符串分割成源头字，源头字前面的字和源头之后的字，将源字符串转换为目标字符串字。该过程可以递归地执行以产生一组换能器碎片。传感器碎片可以形成统计头传感器模型。然后可以将头部换能器转换模型输入到换能搜索模块中。

4. 发明授权

US07912726B2 Method and apparatus for creation and user-customization of speech-enabled services 有权
标题翻译：支持语音的服务的创建和用户定制的方法和设备
公开(公告)号：US07912726B2
公开(公告)日：2011-03-22
申请号：US11215756
申请日：2005-08-30
申请人： Hiyan Alshawi , Shona Douglas
发明人： Hiyan Alshawi , Shona Douglas
IPC分类号： G10L21/00
CPC分类号： G06F17/2827 , G10L15/22 , G10L15/26 , G10L2015/223 , H04M3/4936 , H04M2201/40
摘要： Embodiments of the invention relate to a system and method for providing speech-enabled application programs. The speech-enabled programs automatically execute requests input by users. One or more natural language variants may be mapped with at least one natural language exemplar. The natural language exemplar may correspond to a typical way to express a request relevant to the speech-enabled application program. The natural language variant may correspond to an alternative way of expressing the same request. A recognized input string is received and a prospective variant that most resembles the received recognized input string is selected from the natural language variants. The natural language exemplar mapped to the prospective variant is identified. An action instruction associated with the identified natural language exemplar is executed to fulfill the user's request.
摘要翻译：本发明的实施例涉及一种用于提供支持语音的应用程序的系统和方法。启用语音的程序自动执行用户输入的请求。一个或多个自然语言变体可以用至少一个自然语言样本来映射。自然语言示例可以对应于表达与启用语音的应用程序相关的请求的典型方式。自然语言变体可以对应于表达相同请求的替代方式。接收到识别的输入字符串，并且从自然语言变体中选择最类似于所接收的识别输入字符串的预期变体。确定映射到预期变体的自然语言范例。执行与所识别的自然语言示例相关联的动作指令以满足用户的请求。

5. 发明授权

US07212964B1 Language-understanding systems employing machine translation components 有权
标题翻译：使用机器翻译组件的语言理解系统
公开(公告)号：US07212964B1
公开(公告)日：2007-05-01
申请号：US10103049
申请日：2002-03-22
申请人： Hiyan Alshawi , Shona Douglas
发明人： Hiyan Alshawi , Shona Douglas
IPC分类号： G06F17/21 , G06F17/28
CPC分类号： G06F17/2827 , G10L15/22 , G10L15/26 , G10L2015/223 , H04M3/4936 , H04M2201/40
摘要： Embodiments of the present invention relate to a method and system for augmenting a training database of an automated language-understanding system. In one embodiment, a training example in a first language may be received from the training database. The first language-training example may be translated to a second language output. The second language output may be translated to a first variant of the first language-training example. An action pair including the first variant of the first language-training example and an action command associated with the first language-training example may be stored in an augmented training database.
摘要翻译：本发明的实施例涉及一种用于增强自动语言理解系统的训练数据库的方法和系统。在一个实施例中，可以从训练数据库接收第一语言的训练示例。第一语言训练示例可以被翻译成第二语言输出。可以将第二语言输出转换为第一语言训练示例的第一变体。包括第一语言训练示例的第一变型和与第一语言训练示例相关联的动作命令的动作对可以存储在增强训练数据库中。

6. 发明申请

US20090099837A1 LANGUAGE-UNDERSTANDING TRAINING DATABASE ACTION PAIR AUGMENTATION USING BIDIRECTIONAL TRANSLATION 有权
标题翻译：使用双向翻译语言理解培训数据库行动付款
公开(公告)号：US20090099837A1
公开(公告)日：2009-04-16
申请号：US12336429
申请日：2008-12-16
申请人： Hiyan Alshawi , Shona Douglas
发明人： Hiyan Alshawi , Shona Douglas
IPC分类号： G06F17/28
CPC分类号： G06F17/2827 , G10L15/22 , G10L15/26 , G10L2015/223 , H04M3/4936 , H04M2201/40
摘要： Embodiments of the present invention relate to a method and system for augmenting a training database of an automated language-understanding system. In one embodiment, a training example in a first language is received from the training database. The first language-training example is translated to a second language output. The second language output is translated to a first variant of the first language-training example. An action pair including the first variant of the first language-training example and an action command associated with the first language-training example is stored in an augmented training database.
摘要翻译：本发明的实施例涉及一种用于增强自动语言理解系统的训练数据库的方法和系统。在一个实施例中，从训练数据库接收第一语言的训练示例。第一语言训练示例被转换为第二语言输出。第二语言输出被转换为第一语言训练示例的第一变体。将包括第一语言训练示例的第一变体和与第一语言训练示例相关联的动作命令的动作对存储在增强训练数据库中。

7. 发明申请

US20070118352A1 Language-understanding systems employing machine translation components 有权
公开(公告)号：US20070118352A1
公开(公告)日：2007-05-24
申请号：US11656155
申请日：2007-01-22
申请人： Hiyan Alshawi , Shona Douglas
发明人： Hiyan Alshawi , Shona Douglas
IPC分类号： G06F17/28
CPC分类号： G06F17/2827 , G10L15/22 , G10L15/26 , G10L2015/223 , H04M3/4936 , H04M2201/40
摘要： Embodiments of the present invention relate to a method and system for augmenting a training database of an automated language-understanding system. In one embodiment, a training example in a first language may be received from the training database. The first language-training example may be translated to a second language output. The second language output may be translated to a first variant of the first language-training example. An action pair including the first variant of the first language-training example and an action command associated with the first language-training example may be stored in an augmented training database.

8. 发明申请

US20060004575A1 Method and apparatus for creation and user-customization of speech-enabled services 有权
公开(公告)号：US20060004575A1
公开(公告)日：2006-01-05
申请号：US11215756
申请日：2005-08-30
申请人： Hiyan Alshawi , Shona Douglas
发明人： Hiyan Alshawi , Shona Douglas
IPC分类号： G10L15/18
CPC分类号： G06F17/2827 , G10L15/22 , G10L15/26 , G10L2015/223 , H04M3/4936 , H04M2201/40
摘要： Embodiments of the invention relate to a system and method for providing speech-enabled application programs. The speech-enabled programs automatically execute requests input by users. One or more natural language variants may be mapped with at least one natural language exemplar. The natural language exemplar may correspond to a typical way to express a request relevant to the speech-enabled application program. The natural language variant may correspond to an alternative way of expressing the same request. A recognized input string is received and a prospective variant that most resembles the received recognized input string is selected from the natural language variants. The natural language exemplar mapped to the prospective variant is identified. An action instruction associated with the identified natural language exemplar is executed to fulfill the user's request.

9. 发明授权

US08429148B1 Method and apparatus for automatically generating headlines based on data retrieved from a network and for answering questions related to a headline 有权
标题翻译：基于从网络检索的数据自动产生标题并回答与标题有关的问题的方法和装置
公开(公告)号：US08429148B1
公开(公告)日：2013-04-23
申请号：US11264650
申请日：2005-11-01
申请人： Shona Douglas , Junlan Feng , Mazin Gilbert
发明人： Shona Douglas , Junlan Feng , Mazin Gilbert
IPC分类号： G06F17/30
CPC分类号： G06F17/30905 , G06F17/2247 , G06F17/30516 , G06F17/30539 , G06F17/30867 , G06F2216/03 , H04L67/02
摘要： Disclosed is a web server that includes a headlines module for automatically generating headlines based on data retrieved from a network (e.g., World Wide Web). The web server also includes an interactive agent for generating responses to inquiries relating to the headlines based on the data.
摘要翻译：公开了一种网络服务器，其包括用于基于从网络检索的数据（例如万维网）自动生成标题的标题模块。 Web服务器还包括交互式代理，用于基于数据生成关于标题的查询的响应。

10. 发明授权

US08589172B2 Automatic detection, summarization and reporting of business intelligence highlights from automated dialog systems 有权
标题翻译：从自动对话系统中自动检测，总结和报告商业智能
公开(公告)号：US08589172B2
公开(公告)日：2013-11-19
申请号：US13305077
申请日：2011-11-28
申请人： Tirso M. Alonso , Shona Douglas , Mazin G. Rahim , Benjamin J. Stern
发明人： Tirso M. Alonso , Shona Douglas , Mazin G. Rahim , Benjamin J. Stern
IPC分类号： G10L21/00 , G10L15/28 , H04M1/64
CPC分类号： G06Q30/02
摘要： A method and system for reporting data from a spoken dialog service is disclosed. The method comprises extracting data regarding user dialogs using a dialog logging module in the spoken dialog service, analyzing the data to identify trends and reporting the trends. The data may be presented in a visual form for easier consumption. The method may also relate to identifying data within the control or outside the control of a service provider that is used to adjust the spoken dialog service to maximize customer retention.
摘要翻译：公开了一种用于从口头对话服务报告数据的方法和系统。该方法包括使用口语对话服务中的对话记录模块提取关于用户对话的数据，分析数据以识别趋势并报告趋势。数据可以以视觉形式呈现，以便于消费。该方法还可以涉及识别用于调整口头对话服务以最大化客户保留的服务提供商的控制之内或外部的数据。

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