公开(公告)号：US08645289B2

公开(公告)日：2014-02-04

申请号：US12970879

申请日：2010-12-16

申请人： Paul Nathan Bennett ,  Jianfeng Gao ,  Jagadeesh Jagarlamudi ,  Kristen Patricia Parton

发明人： Paul Nathan Bennett ,  Jianfeng Gao ,  Jagadeesh Jagarlamudi ,  Kristen Patricia Parton

IPC分类号： G06F15/18

CPC分类号： G06F17/30669 ,  G06F17/30675

摘要： A “Cross-Lingual Unified Relevance Model” provides a feedback model that improves a machine-learned ranker for a language with few training resources, using feedback from a more complete ranker for a language that has more training resources. The model focuses on linguistically non-local queries, such as “world cup” (English language/U.S. market) and “copa mundial” (Spanish language/Mexican market), that have similar user intent in different languages and markets or regions, thus allowing the low-resource ranker to receive direct relevance feedback from the high-resource ranker. Among other things, the Cross-Lingual Unified Relevance Model differs from conventional relevancy-based techniques by incorporating both query- and document-level features. More specifically, the Cross-Lingual Unified Relevance Model generalizes existing cross-lingual feedback models, incorporating both query expansion and document re-ranking to further amplify the signal from the high-resource ranker to enable a learning to rank approach based on appropriately labeled training data.

摘要翻译： “跨语言统一相关性模型”提供了一种反馈模型，可以为少数培训资源的语言改进机器学习游戏者，使用更完整的游戏者的反馈来获得具有更多培训资源的语言。 该模式侧重于语言上的非本地查询，例如“世界杯”（英语/美国市场）和“复合世界”（西班牙语/墨西哥市场），在不同语言和市场或区域具有类似的用户意图，因此 允许低资源游击队员接收来自高资源队员的直接相关反馈。 其中，跨语言统一相关性模型与传统的相关性技术不同，包括查询和文档级功能。 更具体地说，跨语言统一相关性模型概括了现有的跨语言反馈模型，其中包括查询扩展和文档重新排序，以进一步放大来自高资源游戏者的信号，以使学习能够基于适当标记的训练进行排名 数据。

公开(公告)号：US20120158621A1

公开(公告)日：2012-06-21

申请号：US12970879

申请日：2010-12-16

申请人： Paul Nathan Bennett ,  Jianfeng Gao ,  Jagadeesh Jagarlamudi ,  Kristen Patricia Parton

发明人： Paul Nathan Bennett ,  Jianfeng Gao ,  Jagadeesh Jagarlamudi ,  Kristen Patricia Parton

IPC分类号： G06F15/18

CPC分类号： G06F17/30669 ,  G06F17/30675

摘要： A “Cross-Lingual Unified Relevance Model” provides a feedback model that improves a machine-learned ranker for a language with few training resources, using feedback from a more complete ranker for a language that has more training resources. The model focuses on linguistically non-local queries, such as “world cup” (English language/U.S. market) and “copa mundial” (Spanish language/Mexican market), that have similar user intent in different languages and markets or regions, thus allowing the low-resource ranker to receive direct relevance feedback from the high-resource ranker. Among other things, the Cross-Lingual Unified Relevance Model differs from conventional relevancy-based techniques by incorporating both query- and document-level features. More specifically, the Cross-Lingual Unified Relevance Model generalizes existing cross-lingual feedback models, incorporating both query expansion and document re-ranking to further amplify the signal from the high-resource ranker to enable a learning to rank approach based on appropriately labeled training data.

摘要翻译： “跨语言统一相关性模型”提供了一种反馈模型，可以为少数培训资源的语言改进机器学习游戏者，使用更完整的游戏者的反馈来获得具有更多培训资源的语言。 该模式侧重于语言上的非本地查询，例如“世界杯”（英语/美国市场）和“复合世界”（西班牙语/墨西哥市场），在不同语言和市场或区域具有类似的用户意图，因此 允许低资源游击队员接收来自高资源队员的直接相关反馈。 其中，跨语言统一相关性模型与传统的相关性技术不同，包括查询和文档级功能。 更具体地说，跨语言统一相关性模型概括了现有的跨语言反馈模型，其中包括查询扩展和文档重新排序，以进一步放大来自高资源游戏者的信号，以使学习能够基于适当标记的训练进行排名 数据。

公开(公告)号：US20120254218A1

公开(公告)日：2012-10-04

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。

公开(公告)号：US20120131031A1

公开(公告)日：2012-05-24

申请号：US12951068

申请日：2010-11-22

申请人： Shasha Xie ,  Xiaodong He ,  Jianfeng Gao

发明人： Shasha Xie ,  Xiaodong He ,  Jianfeng Gao

IPC分类号： G06F17/30

CPC分类号： G06F17/30967 ,  G06F17/30672

摘要： An alteration candidate for a query can be scored. The scoring may include computing one or more query-dependent feature scores and/or one or more intra-candidate dependent feature scores. The computation of the query-dependent feature score(s) can be based on dependencies to multiple query terms from each of one or more alteration terms (i.e., for each of the one or more alteration terms, there can be dependencies to multiple query terms that form at least a portion of the basis for the query-dependent feature score(s)). The computation of the intra-candidate dependent feature score(s) can be based on dependencies between different terms in the alteration candidate. A candidate score can be computed using the query dependent feature score(s) and/or the intra-candidate dependent feature score(s). Additionally, the candidate score can be used in determining whether to select the candidate to expand the query. If selected, the candidate can be used to expand the query.

摘要翻译： 可以对查询的变更候选进行评分。 评分可以包括计算一个或多个依赖于查询的特征得分和/或一个或多个候选内相关特征得分。 依赖于查询的特征得分的计算可以基于来自一个或多个改变项中的每一个的多个查询词的依赖性（即，对于一个或多个改变术语中的每一个，可以依赖于多个查询术语 其形成用于查询相关特征得分的基础的至少一部分）。 候选者相关特征得分的计算可以基于变更候选者中不同术语之间的依赖关系。 可以使用查询相关特征得分和/或候选内相关特征得分来计算候选分数。 此外，可以使用候选分数来确定是否选择候选来扩展查询。 如果选择，候选人可以用来扩展查询。

公开(公告)号：US08060358B2

公开(公告)日：2011-11-15

申请号：US12147807

申请日：2008-06-27

申请人： Xiaodong He ,  Mei Yang ,  Jianfeng Gao ,  Patrick Nguyen

发明人： Xiaodong He ,  Mei Yang ,  Jianfeng Gao ,  Patrick Nguyen

IPC分类号： G06F17/28

CPC分类号： G06F17/2827 ,  G06F17/2818

摘要： A computing system configured to produce an optimized translation hypothesis of text input into the computing system. The computing system includes a plurality of translation machines. Each of the translation machines is configured to produce their own translation hypothesis from the same text. An optimization machine is connected to the plurality of translation machines. The optimization machine is configured to receive the translation hypotheses from the translation machines. The optimization machine is further configured to align, word-to-word, the hypotheses in the plurality of hypotheses by using a hidden Markov model.

摘要翻译： 一种计算系统，被配置为产生文本输入到所述计算系统中的优化翻译假说。 计算系统包括多个翻译机。 每个翻译机被配置为从相同的文本产生他们自己的翻译假设。 优化机连接到多台翻译机。 优化机被配置为从翻译机接收翻译假说。 优化机还被配置为通过使用隐马尔科夫模型来对齐单词到多个假设中的假设。

公开(公告)号：US07974963B2

公开(公告)日：2011-07-05

申请号：US11187567

申请日：2005-07-22

申请人： Ming Zhou ,  Hua Wu ,  Yue Zhang ,  Jianfeng Gao ,  Chang-Ning Huang

发明人： Ming Zhou ,  Hua Wu ,  Yue Zhang ,  Jianfeng Gao ,  Chang-Ning Huang

IPC分类号： G06F17/00

CPC分类号： G06F17/3069 ,  Y10S707/99933

摘要： A method, computer readable medium and system are provided which retrieve confirming sentences from a sentence database in response to a query. A search engine retrieves confirming sentences from the sentence database in response to the query. IN retrieving the confirming sentences, the search engine defines indexing units based upon the query, with the indexing units including both lemma from the query and extended indexing units associated with the query. The search engine then retrieves a plurality of sentences from the sentence database using the defined indexing units as search parameters. A similarity between each of the plurality of retrieved sentences and the query is determined by the search engine, wherein each similarity is determined as a function of a linguistic weight of a term in the query. The search engine then ranks the plurality of retrieved sentences based upon the determined similarities.

摘要翻译： 提供了一种方法，计算机可读介质和系统，其响应于查询从句子数据库中检索确认句子。 搜索引擎响应于查询从句子数据库中检索确认句子。 在检索确认语句中，搜索引擎基于查询来定义索引单元，索引单元包括来自查询的引理和与查询相关联的扩展索引单元。 然后，搜索引擎使用定义的索引单元作为搜索参数从句子数据库中检索多个句子。 由搜索引擎确定多个检索到的句子和查询中的每一个之间的相似度，其中每个相似度被确定为查询中的术语的语言权重的函数。 然后，搜索引擎基于所确定的相似度对多个检索到的句子进行排序。

公开(公告)号：US20100153315A1

公开(公告)日：2010-06-17

申请号：US12337623

申请日：2008-12-17

申请人： Jianfeng Gao ,  Yi Su ,  Qiang Wu ,  Chris J.C. Burges ,  Krysta Svore ,  Elbio Renato Torres Abib

发明人： Jianfeng Gao ,  Yi Su ,  Qiang Wu ,  Chris J.C. Burges ,  Krysta Svore ,  Elbio Renato Torres Abib

IPC分类号： G06F15/18 ,  G06F17/30

CPC分类号： G06F17/3053

摘要： Model adaptation may be performed to take a general model trained with a set of training data (possibly large), and adapt the model using a set of domain-specific training data (possibly small). The parameters, structure, or configuration of a model trained in one domain (called the background domain) may be adapted to a different domain (called the adaptation domain), for which there may be a limited amount of training data. The adaption may be performed using the Boosting Algorithm to select an optimal basis function that optimizes a measure of error of the model as it is being iteratively refined, i.e., adapted.

摘要翻译： 可以执行模型适配以采用用一组训练数据（可能较大）训练的通用模型，并且使用一组特定领域的训练数据（可能小）来适配模型。 在一个域（称为背景域）中训练的模型的参数，结构或配置可以适应于可能存在有限量的训练数据的不同域（称为适配域）。 可以使用升压算法来执行自适应，以选择最优基函数，该优化基函数优化模型的误差量度，因为其被迭代地改进，即适应。

公开(公告)号：US20100048685A1

公开(公告)日：2010-02-25

申请号：US12440942

申请日：2006-10-13

申请人： Yong Ren ,  Jianfeng Gao ,  Shuqin Yu ,  Ling Wu

发明人： Yong Ren ,  Jianfeng Gao ,  Shuqin Yu ,  Ling Wu

IPC分类号： A61K31/337 ,  A61P35/00

CPC分类号： A61K47/48969 ,  A61K9/0019 ,  A61K31/337 ,  A61K47/6951 ,  B82Y5/00

摘要： A docetaxel inclusion complex having improved water-solubility (up to 15 mg/ml) and stability (stability constant Ka=2056M−1-13051M−1), comprises docetaxel and hydroxypropyl-beta-cyclodextrin and/or sulfobutyl-beta-cyclodextrin in a ratio of 1:10-150. The method includes steps as follows: docetaxel dissolved in ethanol is added into water solution of cyclodextrin via stirring, until docetaxel is completely dissolved; said solution is filtered in 0.2-04 μm microporous membrane then ethanol is removed through reduced pressure to obtain the inclusion complex in a liquid form; or ethanol, followed by water is removed through reduced pressure, then dried to obtain the inclusion complex in a solid form.

摘要翻译： 具有改善的水溶性（高达15mg / ml）和稳定性（稳定性常数Ka = 2056M-1-13051M-1）的多西紫杉醇包合物包含多西紫杉醇和羟丙基-β-环糊精和/或磺丁基β-环糊精 比例为1：10-150。 该方法包括以下步骤：通过搅拌将溶于乙醇的多西紫杉醇加入到环糊精的水溶液中，直至多西紫杉醇完全溶解; 将所述溶液在0.2-04μm微孔膜中过滤，然后通过减压除去乙醇，得到液体形式的包合络合物; 或乙醇，随后通过减压除去水，然后干燥，得到固体形式的包合络合物。

公开(公告)号：US20090276414A1

公开(公告)日：2009-11-05

申请号：US12112826

申请日：2008-04-30

申请人： Jianfeng Gao ,  Qiang Wu ,  Jiangyun Song ,  Junyan Chen ,  Steven Yao

发明人： Jianfeng Gao ,  Qiang Wu ,  Jiangyun Song ,  Junyan Chen ,  Steven Yao

IPC分类号： G06F17/30

CPC分类号： G06F16/9535

摘要： Search results provided by a search engine (e.g., for the Internet) are improved and/or made more accurate by addressing the limited availability of human labeled training data for certain domains (e.g., languages other than English, within certain date ranges, corresponding to queries over a certain length, etc.). More particularly, a ranking model trained on in-domain data, for which a small amount of human labeled training data (e.g., query/URL pairs) is available (e.g., languages other than English) is adjusted based upon out-domain data, for which a large amount of human labeled training data (e.g., query/URL pairs) is available (e.g., English). Thus, even though the resulting adapted in-domain ranking model is used in the context of in-domain data (e.g., non-English) to provide search results, the search results are improved because they are influenced by an abundance of, albeit out-domain, human labeled training data.

摘要翻译： 搜索引擎提供的搜索结果（例如，对于互联网）进行改进和/或更准确地解决某些域名（例如，英语以外的语言，某些日期范围内的对应于 查询一定长度等）。 更具体地，针对域内数据进行训练的排名模型，基于域外数据来调整少量人类标记的训练数据（例如，查询/ URL对）可用（例如，除英语以外的语言） 为此，可以使用大量的人类标记的训练数据（例如，查询/ URL对）（例如，英语）。 因此，即使在域内数据（例如，非英语）的上下文中使用所产生的适应的域内排名模型来提供搜索结果，搜索结果被改进，因为它们受到丰富的影响，尽管 域名，人标签训练数据。

公开(公告)号：US07536293B2

公开(公告)日：2009-05-19

申请号：US10462459

申请日：2003-06-16

申请人： Ming Zhuo ,  Jianfeng Gao

发明人： Ming Zhuo ,  Jianfeng Gao

IPC分类号： G06F17/28 ,  G06F17/20

CPC分类号： G06F17/289

摘要： A translation service is disclosed, the service being provided to a wireless mobile device through a selective downloading of information from a server. The downloaded information includes a translation architecture having a language independent translation engine and at least one language dependent translation database. The language dependent translation database includes translation templates and a translation dictionary. A specialized database for a selected city or cities in the world can also be downloaded. Translation between languages is realized by applying the language dependent translation database, and optionally the city specific translation database, to the translation engine. The translation engine implements a user-driven term replacement scheme for simplifying the translation process.

摘要翻译： 公开了翻译服务，该服务通过从服务器的信息的选择性下载而被提供给无线移动设备。 下载的信息包括具有语言无关的翻译引擎和至少一个与语言相关的翻译数据库的翻译架构。 语言相关的翻译数据库包括翻译模板和翻译字典。 也可以下载世界上某个城市或城市的专门数据库。 语言之间的翻译是通过将语言相关的翻译数据库和可选的城市特定翻译数据库应用于翻译引擎来实现的。 翻译引擎实现用户驱动的术语替换方案，以简化翻译过程。