专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

US07933766B2 Method for building a natural language understanding model for a spoken dialog system 有权
标题翻译：建立语言对话系统的自然语言理解模型的方法
公开(公告)号：US07933766B2
公开(公告)日：2011-04-26
申请号：US12582062
申请日：2009-10-20
申请人： Narendra K. Gupta , Mazin G. Rahim , Gokhan Tur , Antony Van der Mude
发明人： Narendra K. Gupta , Mazin G. Rahim , Gokhan Tur , Antony Van der Mude
IPC分类号： G06F17/27
CPC分类号： G10L15/193 , G10L15/063 , G10L15/183
摘要： A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received. After all the training data is received, at least once, the method comprises building a third NLU model using all the labeling data, wherein the third NLU model is used in generating the spoken dialog service.
摘要翻译：公开了一种生成在口头对话系统中使用的自然语言模型的方法。该方法包括对标签指南中定义的每个呼叫类型使用样本话语和创建许多手工制作规则。使用手工制作的规则和样品说话来生成和测试第一个NLU模型。使用示例语句作为新的训练数据并使用手工制作规则构建了第二个NLU模型。使用第一批标签数据对第二个NLU模型进行性能测试。通过将前一批标签数据添加到训练数据并使用新批签名数据作为测试数据来生成一系列NLU模型，训练数据不断增加，构建了一系列NLU模型。如果不是全部接收到标签数据，则该方法包括重复建立一系列NLU模型的步骤，直到接收到所有标记数据为止。在接收到所有训练数据之后，至少一次，该方法包括使用所有标签数据构建第三NLU模型，其中第三NLU模型用于生成口语对话服务。

32. 发明授权

US07295981B1 Method for building a natural language understanding model for a spoken dialog system 有权
标题翻译：建立语言对话系统的自然语言理解模型的方法
公开(公告)号：US07295981B1
公开(公告)日：2007-11-13
申请号：US10755014
申请日：2004-01-09
申请人： Narendra K. Gupta , Mazin G. Rahim , Gokhan Tur , Antony Van der Mude
发明人： Narendra K. Gupta , Mazin G. Rahim , Gokhan Tur , Antony Van der Mude
IPC分类号： G10L15/18
CPC分类号： G10L15/193 , G10L15/063 , G10L15/183
摘要： A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received. After all the training data is received, at least once, the method comprises building a third NLU model using all the labeling data, wherein the third NLU model is used in generating the spoken dialog service.
摘要翻译：公开了一种生成在口头对话系统中使用的自然语言模型的方法。该方法包括对标签指南中定义的每个呼叫类型使用样本话语和创建许多手工制作规则。使用手工制作的规则和样品说话来生成和测试第一个NLU模型。使用示例语句作为新的训练数据并使用手工制作规则构建了第二个NLU模型。使用第一批标签数据对第二个NLU模型进行性能测试。通过将前一批标签数据添加到训练数据并使用新批签名数据作为测试数据来生成一系列NLU模型，训练数据不断增加，构建了一系列NLU模型。如果不是全部接收到标签数据，则该方法包括重复建立一系列NLU模型的步骤，直到接收到所有标记数据为止。在接收到所有训练数据之后，至少一次，该方法包括使用所有标签数据构建第三NLU模型，其中第三NLU模型用于生成口语对话服务。

33. 发明申请

US20060190253A1 Unsupervised and active learning in automatic speech recognition for call classification 有权
公开(公告)号：US20060190253A1
公开(公告)日：2006-08-24
申请号：US11063910
申请日：2005-02-23
申请人： Dilek Hakkani-Tur , Mazin Rahim , Giuseppe Riccardi , Gokhan Tur
发明人： Dilek Hakkani-Tur , Mazin Rahim , Giuseppe Riccardi , Gokhan Tur
IPC分类号： G10L15/06
CPC分类号： G10L15/063 , G10L15/07 , G10L15/18 , G10L15/26 , G10L2015/0638
摘要： Utterance data that includes at least a small amount of manually transcribed data is provided. Automatic speech recognition is performed on ones of the utterance data not having a corresponding manual transcription to produce automatically transcribed utterances. A model is trained using all of the manually transcribed data and the automatically transcribed utterances. A predetermined number of utterances not having a corresponding manual transcription are intelligently selected and manually transcribed. Ones of the automatically transcribed data as well as ones having a corresponding manual transcription are labeled. In another aspect of the invention, audio data is mined from at least one source, and a language model is trained for call classification from the mined audio data to produce a language model.

34. 发明申请

US20060149544A1 Error prediction in spoken dialog systems 审中-公开
标题翻译：口语对话系统中的错误预测
公开(公告)号：US20060149544A1
公开(公告)日：2006-07-06
申请号：US11029278
申请日：2005-01-05
申请人： Dilek Hakkani-Tur , Giuseppe Riccardi , Gokhan Tur
发明人： Dilek Hakkani-Tur , Giuseppe Riccardi , Gokhan Tur
IPC分类号： G10L15/00
CPC分类号： G10L15/22
摘要： A spoken dialog system configured to use a combined confidence score. A first confidence score, indicating a confidence level in a speech recognition result of recognizing an utterance, is provided. A second confidence level, indicating a confidence level of mapping the speech recognition result to an intent, is provided. The first confidence score and the second confidence score are combined to form a combined confidence score. A determination is made, with respect to whether to accept the intent, based on the combined confidence score.
摘要翻译：配置为使用组合置信度得分的口语对话系统。提供了表示识别语音的语音识别结果中的置信水平的第一置信度得分。提供了第二置信水平，指示将语音识别结果映射到意图的置信水平。将第一信心分数和第二置信度分数组合以形成组合的置信度分数。根据组合的置信度得分，确定是否接受意图。

35. 发明授权

US08412514B1 Method and apparatus for compiling and querying a QA database 有权
标题翻译：用于编译和查询QA数据库的方法和装置
公开(公告)号：US08412514B1
公开(公告)日：2013-04-02
申请号：US11260412
申请日：2005-10-27
申请人： Junlan Feng , Mazin Gilbert , Dilek Hakkani-Tür , Gokhan Tur
发明人： Junlan Feng , Mazin Gilbert , Dilek Hakkani-Tür , Gokhan Tur
IPC分类号： G06F17/20 , G06F17/27 , G06F17/21
CPC分类号： G06N5/022 , G06F17/2211 , G06F17/30654 , G06F17/30657 , G06F17/30696 , G06F17/30867 , G09B5/00
摘要： Disclosed is a method and apparatus for responding to an inquiry from a client via a network. The method and apparatus receive the inquiry from a client via a network. Based on the inquiry, question-answer pairs retrieved from the network are analyzed to determine a response to the inquiry. The QA pairs are not predefined. As a result, the QA pairs have to be analyzed in order to determine whether they are responsive to a particular inquiry. Questions of the QA pairs may be repetitive and similar to one another even for very different subjects, and without additional contextual and meta-level information, are not useful in determining whether their corresponding answer responds to an inquiry.
摘要翻译：公开了一种用于经由网络从客户机响应询问的方法和装置。该方法和装置经由网络从客户端接收询问。基于查询，分析从网络检索的问答对以确定对查询的响应。 QA对未预先定义。因此，必须分析QA对以确定它们是否响应于特定查询。质量保证对的问题可能是重复的，即使对于非常不同的主题也是相似的，并且没有附加的上下文和元级信息在确定他们的对应答案是否响应于查询时也是无用的。

36. 发明授权

US07664644B1 Multitask learning for spoken language understanding 有权
标题翻译：多任务学习口语理解
公开(公告)号：US07664644B1
公开(公告)日：2010-02-16
申请号：US11423212
申请日：2006-06-09
申请人： Gokhan Tur
发明人： Gokhan Tur
IPC分类号： G10L15/18
CPC分类号： G10L15/063 , G10L13/08 , G10L15/1822 , G10L15/183 , G10L15/26 , G10L2015/0635 , H04M3/4936
摘要： A system, method and computer-readable medium provide a multitask learning method for intent or call-type classification in a spoken language understanding system. Multitask learning aims at training tasks in parallel while using a shared representation. A computing device automatically re-uses the existing labeled data from various applications, which are similar but may have different call-types, intents or intent distributions to improve the performance. An automated intent mapping algorithm operates across applications. In one aspect, active learning is employed to selectively sample the data to be re-used.
摘要翻译：系统，方法和计算机可读介质在口语理解系统中提供用于意图或呼叫类型分类的多任务学习方法。多任务学习旨在同时使用共享表示法来并行训练任务。计算设备自动重新使用来自各种应用程序的现有标记数据，这些应用程序类似但可能具有不同的调用类型，意图或意图分发以提高性能。自动化意图映射算法在应用程序之间运行。在一个方面，采用主动学习来选择性地对要再次使用的数据进行采样。

37. 发明申请

US20070136246A1 Answer determination for natural language questioning 有权
标题翻译：回答自然语言提问的决心
公开(公告)号：US20070136246A1
公开(公告)日：2007-06-14
申请号：US11319188
申请日：2005-12-28
申请人： Svetlana Stenchikova , Gokhan Tur , Dilek Tur
发明人： Svetlana Stenchikova , Gokhan Tur , Dilek Tur
IPC分类号： G06F17/30
CPC分类号： G06F17/30401 , G06F17/279 , G06F17/30657 , G06F17/30864
摘要： Open-domain question answering is the task of finding a concise answer to a natural language question using a large domain, such as the Internet. The use of a semantic role labeling approach to the extraction of the answers to an open domain factoid (Who/When/What/Where) natural language question that contains a predicate is described. Semantic role labeling identities predicates and semantic argument phrases in the natural language question and the candidate sentences. When searching for an answer to a natural language question, the missing argument in the question is matched using semantic parses of the candidate answers. Such a technique may improve the accuracy of a question answering system and may decrease the length of answers for enabling voice interface to a question answering system.
摘要翻译：开放域问答是使用大型域（如互联网）找到一个简明的自然语言问题答案的任务。描述了使用语义角色标注方法来提取对包含谓词的开放域factoid（Who / When / What / Where）自然语言问题的答案。自然语言问题和候选句子中的语义角色标识身份谓词和语义参数短语。在搜索自然语言问题的答案时，使用候选答案的语义分析来匹配问题中的缺失参数。这样的技术可以提高问答系统的准确性，并且可以减少用于启用语音接口到问答系统的答案的长度。

38. 发明授权

US10366336B2 Method and apparatus for exploiting human feedback in an intelligent automated assistant 有权
公开(公告)号：US10366336B2
公开(公告)日：2019-07-30
申请号：US13378525
申请日：2010-09-01
申请人： Gokhan Tur , Horacio E. Franco , William S. Mark , Norman D. Winarsky , Bart Peintner , Michael J. Wolverton , Neil Yorke-Smith
发明人： Gokhan Tur , Horacio E. Franco , William S. Mark , Norman D. Winarsky , Bart Peintner , Michael J. Wolverton , Neil Yorke-Smith
IPC分类号： G06N7/00 , G06N20/00 , G06N5/02 , G06N5/04 , G06F9/44 , G06F9/451
摘要： The present invention relates to a method and apparatus for exploiting human feedback in an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes inferring an intent from data entered by the human user, formulating a response in accordance with the intent, receiving feedback from a human advisor in response to at least one of the inferring and the formulating, wherein the human advisor is a person other than the human user, and adapting at least one model used in at least one of the inferring and the formulating, wherein the adapting is based on the feedback.

39. 发明申请

US20130346066A1 Joint Decoding of Words and Tags for Conversational Understanding 审中-公开
标题翻译：用于会话理解的单词和标签的联合解码
公开(公告)号：US20130346066A1
公开(公告)日：2013-12-26
申请号：US13528124
申请日：2012-06-20
申请人： Anoop Kiran Deoras , Dilek Zeynep Hakkani-Tur , Ruhi Sarikaya , Gokhan Tur
发明人： Anoop Kiran Deoras , Dilek Zeynep Hakkani-Tur , Ruhi Sarikaya , Gokhan Tur
IPC分类号： G06F17/27 , G10L15/00
CPC分类号： G06F17/27 , G10L2015/226
摘要： Joint decoding of words and tags may be provided. Upon receiving an input from a user comprising a plurality of elements, the input may be decoded into a word lattice comprising a plurality of words. A tag may be assigned to each of the plurality of words and a most-likely sequence of word-tag pairs may be identified. The most-likely sequence of word-tag pairs may be evaluated to identify an action request from the user.
摘要翻译：可以提供单词和标签的联合解码。一旦接收到来自包括多个元素的用户的输入，该输入可以被解码成包括多个单词的单词格。可以将标签分配给多个单词中的每一个，并且可以识别最可能的单词 - 标签对序列。可以评估最可能的字标签对序列以识别来自用户的动作请求。

40. 发明申请

US20130218836A1 Deep Linking From Task List Based on Intent 审中-公开
标题翻译：基于意图从任务列表中深入链接
公开(公告)号：US20130218836A1
公开(公告)日：2013-08-22
申请号：US13401876
申请日：2012-02-22
申请人： Anne K. Sullivan , Lisa Stifelman , Kathy Lee , Matt Klee , Larry Paul Heck , Gokhan Tur , Dilek Hakkani-Tur
发明人： Anne K. Sullivan , Lisa Stifelman , Kathy Lee , Matt Klee , Larry Paul Heck , Gokhan Tur , Dilek Hakkani-Tur
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06Q10/109 , G06Q10/06311
摘要： Task list linking may be provided. Upon receiving an input from a user, the input may be translated into at least one actionable item. The at least one actionable item may be linked to a data source and displayed to the user.
摘要翻译：可以提供任务列表链接。一旦接收到来自用户的输入，该输入可被翻译成至少一个可操作的项目。所述至少一个可操作的项目可以链接到数据源并显示给用户。

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