专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明申请

US20070203869A1 Adaptive semantic platform architecture 审中-公开
标题翻译：自适应语义平台架构
公开(公告)号：US20070203869A1
公开(公告)日：2007-08-30
申请号：US11363747
申请日：2006-02-28
申请人： William D. Ramsey , Sanjeev Katariya , Jun Liu , Jianfeng Gao , Qi Yao , Zhanliang Chen
发明人： William D. Ramsey , Sanjeev Katariya , Jun Liu , Jianfeng Gao , Qi Yao , Zhanliang Chen
IPC分类号： G06N7/02
CPC分类号： G06F17/279
摘要： An adaptive shared infrastructure that can be easily utilized to enable natural interaction between user(s) and machine system(s) is provided. Additionally, the novel innovation can provide interactive techniques that produce accurate intent-to-action mapping based upon a user input. Further, the innovation can provide novel mechanism by which assets (e.g., documents, actions) can be authored. The authoring mechanisms can enable the generation of learning models such that the system can infer a user intent based at least in part upon an analysis of a user input. In response thereto, the system can discover an asset, or group of assets based upon the inference. Moreover, the innovation can provide a natural language interface that learns and/or adapts based upon one or more user input(s), action(s), and/or state(s).
摘要翻译：提供了可以容易地利用以实现用户和机器系统之间的自然交互的自适应共享基础设施。此外，新颖的创新可以提供基于用户输入产生准确的意图 - 动作映射的交互技术。此外，创新可以提供可以创作资产（例如，文档，动作）的新颖机制。创作机制可以实现学习模型的产生，使得系统至少部分地基于对用户输入的分析来推断用户意图。作为响应，系统可以基于推论发现资产或资产组。此外，创新可以提供基于一个或多个用户输入，动作和/或状态来学习和/或适应的自然语言界面。

72. 发明申请

US20060277033A1 Discriminative training for language modeling 有权
标题翻译：语言建模歧视性培训
公开(公告)号：US20060277033A1
公开(公告)日：2006-12-07
申请号：US11142432
申请日：2005-06-01
申请人： Jianfeng Gao , Hisami Suzuki
发明人： Jianfeng Gao , Hisami Suzuki
IPC分类号： G06F17/21
CPC分类号： G10L15/063 , G10L15/197
摘要： A method of training language model parameters trains discriminative model parameters in the language model based on a performance measure having discrete values.
摘要翻译：训练语言模型参数的方法是基于具有离散值的性能度量来训练语言模型中的歧视模型参数。

73. 发明申请

US20060184341A1 Method and Apparatus for Generating and Managing a Language Model Data Structure 失效
标题翻译：用于生成和管理语言模型数据结构的方法和装置
公开(公告)号：US20060184341A1
公开(公告)日：2006-08-17
申请号：US11276292
申请日：2006-02-22
申请人： Shuo Di , Kai-Fu Lee , Lee-Feng Chien , Zheng Chen , Jianfeng Gao
发明人： Shuo Di , Kai-Fu Lee , Lee-Feng Chien , Zheng Chen , Jianfeng Gao
IPC分类号： G06F17/10
CPC分类号： G06F17/27 , G10L15/285
摘要： A method is presented comprising assigning each of a plurality of segments comprising a received corpus to a node in a data structure denoting dependencies between nodes, and calculating a transitional probability between each of the nodes in the data structure.
摘要翻译：提出了一种方法，包括将包括接收到的语料库的多个段中的每一个分配给表示节点之间的依赖关系的数据结构中的节点，以及计算数据结构中每个节点之间的过渡概率。

74. 发明申请

US20060009965A1 Method and apparatus for distribution-based language model adaptation 有权
公开(公告)号：US20060009965A1
公开(公告)日：2006-01-12
申请号：US11225543
申请日：2005-09-13
申请人： Jianfeng Gao , Mingjing Li
发明人： Jianfeng Gao , Mingjing Li
IPC分类号： G06F17/27
CPC分类号： G06F17/2715 , G10L15/065 , G10L15/1815
摘要： A method and apparatus are provided for adapting a language model to a task-specific domain. Under the method and apparatus, the relative frequency of n-grams in a small training set (i.e. task-specific training data set) and the relative frequency of n-grams in a large training set (i.e. out-of-domain training data set) are used to weight a distribution count of n-grams in the large training set. The weighted distributions are then used to form a modified language model by identifying probabilities for n-grams from the weighted distributions.

75. 发明授权

US06904402B1 System and iterative method for lexicon, segmentation and language model joint optimization 有权
标题翻译：词法，分割和语言模型联合优化的系统迭代法
公开(公告)号：US06904402B1
公开(公告)日：2005-06-07
申请号：US09609202
申请日：2000-06-30
申请人： Hai-Feng Wang , Chang-Ning Huang , Kai-Fu Lee , Shuo Di , Jianfeng Gao , Dong-Feng Cai , Lee-Feng Chien
发明人： Hai-Feng Wang , Chang-Ning Huang , Kai-Fu Lee , Shuo Di , Jianfeng Gao , Dong-Feng Cai , Lee-Feng Chien
IPC分类号： G06F17/28 , G06F17/27 , G10L15/06 , G10L15/18 , G06F17/21 , G06F17/20 , G10L15/00
CPC分类号： G06F17/274 , G10L15/197
摘要： A method for optimizing a language model is presented comprising developing an initial language model from a lexicon and segmentation derived from a received corpus using a maximum match technique, and iteratively refining the initial language model by dynamically updating the lexicon and re-segmenting the corpus according to statistical principles until a threshold of predictive capability is achieved.
摘要翻译：提出了一种用于优化语言模型的方法，其包括使用最大匹配技术从词典和从接收到的语料库导出的分割开发初始语言模型，并且通过动态地更新词典并重新分割语料库来迭代地改进初始语言模型统计原理，直到达到预测能力的阈值。

76. 发明授权

US09501759B2 Search query and document-related data translation 有权
标题翻译：搜索查询和文档相关的数据翻译
公开(公告)号：US09501759B2
公开(公告)日：2016-11-22
申请号：US13328924
申请日：2011-12-16
申请人： Jianfeng Gao , Xuedong Huang , Mei Li , Zhenghao Wang , Christopher John Brockett , William B. Dolan
发明人： Jianfeng Gao , Xuedong Huang , Mei Li , Zhenghao Wang , Christopher John Brockett , William B. Dolan
IPC分类号： G06F17/30 , G06F7/00 , G06Q10/10 , G06Q30/02
CPC分类号： G06Q10/10 , G06F17/30687 , G06Q30/0241
摘要： The subject disclosure is directed towards developing a translation model for mapping search query terms to document-related data. By processing user logs comprising search histories into word-aligned query-document pairs, the translation model may be trained using data, such as probabilities, corresponding to the word-aligned query-document pairs. After incorporating the translation model into model data for a search engine, the translation model is used may used as features for producing relevance scores for current search queries and ranking documents/advertisements according to relevance.
摘要翻译：本发明旨在开发用于将搜索查询词语映射到文档相关数据的翻译模型。通过将包括搜索历史的用户日志处理成字对齐的查询 - 文档对，可以使用对应于字对齐的查询 - 文档对的诸如概率的数据来训练翻译模型。在将翻译模型合并到搜索引擎的模型数据中之后，使用翻译模型可以用作根据相关性产生当前搜索查询和排序文档/广告的相关性分数的特征。

77. 发明授权

US08838433B2 Selection of domain-adapted translation subcorpora 有权
标题翻译：选择领域适应翻译子公司
公开(公告)号：US08838433B2
公开(公告)日：2014-09-16
申请号：US13022633
申请日：2011-02-08
申请人： Amittai Axelrod , Jianfeng Gao , Xiaodong He
发明人： Amittai Axelrod , Jianfeng Gao , Xiaodong He
IPC分类号： G06F17/28
CPC分类号： G06F17/2809
摘要： An architecture is discussed that provides the capability to subselect the most relevant data from an out-domain corpus to use either in isolation or in combination conjunction with in-domain data. The architecture is a domain adaptation for machine translation that selects the most relevant sentences from a larger general-domain corpus of parallel translated sentences. The methods for selecting the data include monolingual cross-entropy measure, monolingual cross-entropy difference, bilingual cross entropy, and bilingual cross-entropy difference. A translation model is trained on both the in-domain data and an out-domain subset, and the models can be interpolated together to boost performance on in-domain translation tasks.
摘要翻译：讨论了一种架构，其提供了从外域语料库中选择最相关的数据的能力，以隔离或与域内数据组合使用。该架构是机器翻译的域适应，从较大的平行翻译句子的一般领域语料库中选择最相关的句子。选择数据的方法包括单语交叉熵测度，单语交叉熵差，双语交叉熵和双语交叉熵差。对域内数据和外域子集进行翻译模型的训练，并将这些模型插值到一起，以提升域内翻译任务的性能。

78. 发明授权

US08738356B2 Universal text input 有权
标题翻译：通用文本输入
公开(公告)号：US08738356B2
公开(公告)日：2014-05-27
申请号：US13110484
申请日：2011-05-18
申请人： Hisami Suzuki , Vikram Dendi , Christopher Brian Quirk , Pallavi Choudhury , Jianfeng Gao , Achraf Chalabi
发明人： Hisami Suzuki , Vikram Dendi , Christopher Brian Quirk , Pallavi Choudhury , Jianfeng Gao , Achraf Chalabi
IPC分类号： G06F17/28
CPC分类号： G06F17/27
摘要： The universal text input technique described herein addresses the difficulties of typing text in various languages and scripts, and offers a unified solution, which combines character conversion, next word prediction, spelling correction and automatic script switching to make it extremely simple to type any language from any device. The technique provides a rich and seamless input experience in any language through a universal IME (input method editor). It allows a user to type in any script for any language using a regular qwerty keyboard via phonetic input and at the same time allows for auto-completion and spelling correction of words and phrases while typing. The technique also provides a modeless input that automatically turns on and off an input mode that changes between different types of script.
摘要翻译：本文描述的通用文本输入技术解决了以各种语言和脚本输入文本的困难，并提供了一种统一的解决方案，它将字符转换，下一个字预测，拼写校正和自动脚本切换相结合，使其非常简单，任何设备。该技术通过通用IME（输入法编辑器）为任何语言提供了丰富且无缝的输入体验。它允许用户使用普通qwerty键盘通过语音输入为任何语言输入任何脚本，同时允许在打字时自动完成和拼写校正单词和短语。该技术还提供了无模式输入，可自动打开和关闭在不同类型脚本之间进行更改的输入模式。

79. 发明授权

US08732151B2 Enhanced query rewriting through statistical machine translation 有权
标题翻译：通过统计机器翻译增强查询重写
公开(公告)号：US08732151B2
公开(公告)日：2014-05-20
申请号：US13078648
申请日：2011-04-01
申请人： Alnur Ali , Jianfeng Gao , Xiaodong He , Bodo von Billerbeck , Sanaz Ahari
发明人： Alnur Ali , Jianfeng Gao , Xiaodong He , Bodo von Billerbeck , Sanaz Ahari
IPC分类号： G06F17/30
CPC分类号： G06F17/30672
摘要： Systems, methods, and computer media for identifying query rewriting replacement terms are provided. A list of related string pairs each comprising a first string and second string is received. The first string of each related string pair is a user search query extracted from user click log data. For one or more of the related string pairs, the string pair is provided as inputs to a statistical machine translation model. The model identifies one or more pairs of corresponding terms, each pair of corresponding terms including a first term from the first string and a second term from the second string. The model also calculates a probability of relatedness for each of the one or more pairs of corresponding terms. Term pairs whose calculated probability of relatedness exceeds a threshold are characterized as query term replacements and incorporated, along with the probability of relatedness, into a query rewriting candidate database.
摘要翻译：提供了用于识别查询重写替换术语的系统，方法和计算机媒体。接收包括第一串和第二串的相关字符串对的列表。每个相关字符串对的第一个字符串是从用户点击日志数据中提取的用户搜索查询。对于一个或多个相关字符串对，字符串对作为统计机器翻译模型的输入提供。该模型识别一对或多对对应的术语，每对对应的术语包括来自第一个字符串的第一项和来自第二个字符串的第二个项。该模型还计算一对或多对相应项中的每一对的相关概率。其相关性概率超过阈值的术语对被表征为查询词替换，并将其与相关性的概率一起并入查询重写候选数据库中。

80. 发明申请

US20130103493A1 Search Query and Document-Related Data Translation 有权
标题翻译：搜索查询和文档相关数据翻译
公开(公告)号：US20130103493A1
公开(公告)日：2013-04-25
申请号：US13328924
申请日：2011-12-16
申请人： Jianfeng Gao , Xuedong Huang , Mei Li , Zhenghao Wang , Christopher John Brockett , William B. Dolan
发明人： Jianfeng Gao , Xuedong Huang , Mei Li , Zhenghao Wang , Christopher John Brockett , William B. Dolan
IPC分类号： G06Q30/02 , G06F17/30
CPC分类号： G06Q10/10 , G06F17/30687 , G06Q30/0241
摘要： The subject disclosure is directed towards developing a translation model for mapping search query terms to document-related data. By processing user logs comprising search histories into word-aligned query-document pairs, the translation model may be trained using data, such as probabilities, corresponding to the word-aligned query-document pairs. After incorporating the translation model into model data for a search engine, the translation model is used may used as features for producing relevance scores for current search queries and ranking documents/advertisements according to relevance.
摘要翻译：本发明旨在开发用于将搜索查询词语映射到文档相关数据的翻译模型。通过将包括搜索历史的用户日志处理成字对齐的查询 - 文档对，可以使用对应于字对齐的查询 - 文档对的诸如概率的数据来训练翻译模型。在将翻译模型合并到搜索引擎的模型数据中之后，使用翻译模型可以用作根据相关性产生当前搜索查询和排序文档/广告的相关性分数的特征。

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