-
公开(公告)号：US08175873B2
公开(公告)日：2012-05-08
申请号：US12333863
申请日：2008-12-12
CPC分类号： G06F17/2881 , G06F17/279 , G10L13/027
摘要： Systems, methods, and non-transitory computer-readable media for referring to entities. The method includes receiving domain-specific training data of sentences describing a target entity in a context, extracting a speaker history and a visual context from the training data, selecting attributes of the target entity based on at least one of the speaker history, the visual context, and speaker preferences, generating a text expression referring to the target entity based on at least one of the selected attributes, the speaker history, and the context, and outputting the generated text expression. The weighted finite-state automaton can represent partial orderings of word pairs in the domain-specific training data. The weighted finite-state automaton can be speaker specific or speaker independent. The weighted finite-state automaton can include a set of weighted partial orderings of the training data for each possible realization.
摘要翻译： 用于引用实体的系统，方法和非暂时计算机可读介质。 该方法包括接收在上下文中描述目标实体的句子的特定领域的训练数据，从训练数据中提取讲者历史和视觉上下文，基于说话者的历史，视觉上的至少一个来选择目标实体的属性 上下文和说话人首选项，基于所选择的属性，说话者历史和上下文中的至少一个生成参考目标实体的文本表达，并输出所生成的文本表达。 加权有限状态自动机可以表示域特定训练数据中单词对的部分排序。 加权有限状态自动机可以是扬声器专用或扬声器独立的。 加权有限状态自动机可以包括用于每个可能实现的训练数据的一组加权部分排序。
-
公开(公告)号：US08566090B2
公开(公告)日：2013-10-22
申请号：US13465685
申请日：2012-05-07
IPC分类号： G10L13/027
CPC分类号： G06F17/2881 , G06F17/279 , G10L13/027
摘要： Systems, methods, and non-transitory computer-readable media for referring to entities. The method includes receiving domain-specific training data of sentences describing a target entity in a context, extracting a speaker history and a visual context from the training data, selecting attributes of the target entity based on at least one of the speaker history, the visual context, and speaker preferences, generating a text expression referring to the target entity based on at least one of the selected attributes, the speaker history, and the context, and outputting the generated text expression. The weighted finite-state automaton can represent partial orderings of word pairs in the domain-specific training data. The weighted finite-state automaton can be speaker specific or speaker independent. The weighted finite-state automaton can include a set of weighted partial orderings of the training data for each possible realization.
摘要翻译： 用于引用实体的系统，方法和非暂时计算机可读介质。 该方法包括接收在上下文中描述目标实体的句子的特定领域的训练数据，从训练数据中提取讲者历史和视觉上下文，基于说话者的历史，视觉上的至少一个来选择目标实体的属性 上下文和说话人首选项，基于所选择的属性，说话者历史和上下文中的至少一个生成参考目标实体的文本表达，并输出所生成的文本表达。 加权有限状态自动机可以表示域特定训练数据中单词对的部分排序。 加权有限状态自动机可以是扬声器专用或扬声器独立的。 加权有限状态自动机可以包括用于每个可能实现的训练数据的一组加权部分排序。
-
公开(公告)号：US20100131274A1
公开(公告)日：2010-05-27
申请号：US12324340
申请日：2008-11-26
申请人： Amanda Stent , Srinivas Bangalore
发明人： Amanda Stent , Srinivas Bangalore
IPC分类号： G10L15/18
CPC分类号： G10L15/063 , G06F17/22 , G06F17/2241 , G06F17/227 , G10L15/005 , G10L15/04 , G10L15/08 , G10L15/18 , G10L15/183 , G10L15/22 , G10L25/12 , G10L2015/0638
摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable media for dialog modeling. The method includes receiving spoken dialogs annotated to indicate dialog acts and task/subtask information, parsing the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs, and constructing a functional task structure of the parsed spoken dialogs. The method can further either interpret user utterances with the functional task structure of the parsed spoken dialogs or plan system responses to user utterances with the functional task structure of the parsed spoken dialogs. The parse-based dialog model can be a shift-reduce model, a start-complete model, or a connection path model.
摘要翻译： 本文公开了用于对话建模的系统，计算机实现的方法和计算机可读介质。 该方法包括接收注释以指示对话行为和任务/子任务信息的口头对话，用从层级，基于解析的对话模型解析口头对话，该对话模型从左向右逐渐操作，并且仅分析前一对话上下文以产生解析的口语对话 ，并构建解析的语音对话的功能任务结构。 该方法还可以用解析的口头对话的功能任务结构或用解析的口语对话的功能性任务结构对用户话语的计划系统响应来解释用户话语。 基于分析的对话模型可以是移位减少模型，起始完成模型或连接路径模型。
-
公开(公告)号：US20120221332A1
公开(公告)日：2012-08-30
申请号：US13465685
申请日：2012-05-07
IPC分类号： G10L15/26
CPC分类号： G06F17/2881 , G06F17/279 , G10L13/027
摘要： Systems, methods, and non-transitory computer-readable media for referring to entities. The method includes receiving domain-specific training data of sentences describing a target entity in a context, extracting a speaker history and a visual context from the training data, selecting attributes of the target entity based on at least one of the speaker history, the visual context, and speaker preferences, generating a text expression referring to the target entity based on at least one of the selected attributes, the speaker history, and the context, and outputting the generated text expression. The weighted finite-state automaton can represent partial orderings of word pairs in the domain-specific training data. The weighted finite-state automaton can be speaker specific or speaker independent. The weighted finite-state automaton can include a set of weighted partial orderings of the training data for each possible realization.
摘要翻译： 用于引用实体的系统，方法和非暂时计算机可读介质。 该方法包括接收在上下文中描述目标实体的句子的特定领域的训练数据，从训练数据中提取讲者历史和视觉上下文，基于说话者的历史，视觉上的至少一个来选择目标实体的属性 上下文和说话人首选项，基于所选择的属性，说话者历史和上下文中的至少一个生成参考目标实体的文本表达，并输出所生成的文本表达。 加权有限状态自动机可以表示域特定训练数据中单词对的部分排序。 加权有限状态自动机可以是扬声器专用或扬声器独立的。 加权有限状态自动机可以包括用于每个可能实现的训练数据的一组加权部分排序。
-
公开(公告)号：US20100153105A1
公开(公告)日：2010-06-17
申请号：US12333863
申请日：2008-12-12
IPC分类号： G10L15/26
CPC分类号： G06F17/2881 , G06F17/279 , G10L13/027
摘要： Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for referring to entities. The method includes receiving domain-specific training data of sentences describing a target entity in a context, extracting a speaker history and a visual context from the training data, selecting attributes of the target entity based on at least one of the speaker history, the visual context, and speaker preferences, generating a text expression referring to the target entity based on at least one of the selected attributes, the speaker history, and the context, and outputting the generated text expression. The weighted finite-state automaton can represent partial orderings of word pairs in the domain-specific training data. The weighted finite-state automaton can be speaker specific or speaker independent. The weighted finite-state automaton can include a set of weighted partial orderings of the training data for each possible realization.
摘要翻译： 本文公开了用于引用实体的系统，计算机实现的方法和有形的计算机可读介质。 该方法包括接收在上下文中描述目标实体的句子的特定领域的训练数据，从训练数据中提取讲者历史和视觉上下文，基于说话者的历史，视觉上的至少一个来选择目标实体的属性 上下文和说话人首选项，基于所选择的属性，说话者历史和上下文中的至少一个生成参考目标实体的文本表达，并输出所生成的文本表达。 加权有限状态自动机可以表示域特定训练数据中单词对的部分排序。 加权有限状态自动机可以是扬声器专用或扬声器独立的。 加权有限状态自动机可以包括用于每个可能实现的训练数据的一组加权部分排序。
-
公开(公告)号：US09129601B2
公开(公告)日：2015-09-08
申请号：US12324340
申请日：2008-11-26
申请人： Amanda Stent , Srinivas Bangalore
发明人： Amanda Stent , Srinivas Bangalore
IPC分类号： G06F17/22 , G10L15/08 , G10L15/22 , G10L15/183 , G10L15/18
CPC分类号： G10L15/063 , G06F17/22 , G06F17/2241 , G06F17/227 , G10L15/005 , G10L15/04 , G10L15/08 , G10L15/18 , G10L15/183 , G10L15/22 , G10L25/12 , G10L2015/0638
摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable media for dialog modeling. The method includes receiving spoken dialogs annotated to indicate dialog acts and task/subtask information, parsing the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs, and constructing a functional task structure of the parsed spoken dialogs. The method can further either interpret user utterances with the functional task structure of the parsed spoken dialogs or plan system responses to user utterances with the functional task structure of the parsed spoken dialogs. The parse-based dialog model can be a shift-reduce model, a start-complete model, or a connection path model.
摘要翻译： 本文公开了用于对话建模的系统，计算机实现的方法和计算机可读介质。 该方法包括接收注释以指示对话行为和任务/子任务信息的口头对话，用从层级，基于解析的对话模型解析口头对话，该对话模型从左向右逐渐操作，并且仅分析前一对话上下文以产生解析的口语对话 ，并构建解析的语音对话的功能任务结构。 该方法还可以用解析的口头对话的功能任务结构或用解析的口语对话的功能性任务结构对用户话语的计划系统响应来解释用户话语。 基于分析的对话模型可以是移位减少模型，起始完成模型或连接路径模型。
-
公开(公告)号：US09767221B2
公开(公告)日：2017-09-19
申请号：US12901075
申请日：2010-10-08
IPC分类号： G06F17/30
CPC分类号： G06F17/30976 , G06F17/30345 , G06F17/30997
摘要： Delivering targeted content includes collecting, via at least one tangible processor, user activity data for users during a specified time period. questions asked by the users during the specified time period are extracted from the user activity data, via the at least one tangible processor, and stored in user profiles for the users. The user profiles are clustered, via the at least one tangible processor, based on the questions asked. Targeted content is delivered, via the at least one tangible processor, to a subset of the users based on the clustering.
-
公开(公告)号：US09323746B2
公开(公告)日：2016-04-26
申请号：US13311836
申请日：2011-12-06
IPC分类号： G06F17/28
CPC分类号： G06F17/2854 , G06F3/04842 , G06F17/2836 , G06F17/289
摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for presenting a machine translation and alternative translations to a user, where a selection of any particular alternative translation results in the re-ranking of the remaining alternatives. The system then presents these re-ranked alternatives to the user, who can continue proofing the machine translation using the re-ranked alternatives or by typing an improved translation. This process continues until the user indicates that the current portion of the translation is complete, at which point the system moves to the next portion.
摘要翻译： 本文公开了用于向用户呈现机器翻译和替代翻译的系统，方法和非暂时的计算机可读存储介质，其中任何特定替代翻译的选择导致其余替代方案的重新排序。 然后，该系统将这些重新排列的替代品呈现给用户，他们可以使用重新排列的替代品或通过输入改进的翻译来继续打印机器翻译。 该过程继续，直到用户指示翻译的当前部分完成，在该点系统移动到下一部分。
-
公开(公告)号：US09092425B2
公开(公告)日：2015-07-28
申请号：US12963161
申请日：2010-12-08
CPC分类号： G06F17/28
摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size. Then the system processes each X-dimensional vector, based on the external data, to generate respective Y-dimensional vectors, wherein each Y-dimensional vector represents a dense continuous space, and outputs at least one next word predicted to follow the sequence of words based on the respective Y-dimensional vectors. The X-dimensional vector, which is a binary sparse representation, can be higher dimensional than the Y-dimensional vector, which is a dense continuous space. The external data can include part-of-speech tags, topic information, word similarity, word relationships, a particular topic, and succeeding parts of speech in a given history.
摘要翻译： 这里公开了用于预测语言模型的单词概率的系统，方法和非暂时的计算机可读存储介质。 配置为实施该方法的示例性系统接收与该单词序列相关联的单词序列和外部数据序列，并将该单词序列映射到对应于词汇大小的X维向量。 然后系统根据外部数据对每个X维向量进行处理，以产生各自的Y维向量，其中每个Y维向量表示密集的连续空间，并且输出至少一个预测的下一个单词以跟随单词序列 基于相应的Y维向量。 作为二进制稀疏表示的X维向量可以比作为密集连续空间的Y维向量更高的维度。 外部数据可以包括在给定历史中的部分词汇标签，主题信息，单词相似性，单词关系，特定主题以及后续部分语音。
-
公开(公告)号：US09081760B2
公开(公告)日：2015-07-14
申请号：US13042890
申请日：2011-03-08
CPC分类号： G06F17/28 , G06F17/21 , G06F17/27 , G06F17/2705 , G06F17/2715 , G06F17/2735 , G06F17/2765 , G10L2015/0633
摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.
摘要翻译： 本文公开了用于收集网络数据以便创建不同语言模型的系统，方法和非暂时的计算机可读存储介质。 被配置为实践该方法的系统首先通过根据访问策略的互连设备的网络中的诸如通过在计算设备上操作的爬行器来爬行一组文档，其中所述访问策略被配置为专注于新颖区域 目前的语言模型是从以前的爬行周期构建的，通过抓取其词汇被认为可能填补当前语言模型的空白的文档。 来自上一个循环的语言模型可用于指导在以下循环中创建语言模型。 新奇区域可以包括与当前语言模型相比具有高困惑价值的文档。
-
-
-
-
-
-
-
-
-
搜索结果
132 条记录 (耗时 0.018 秒)
