公开(公告)号：US20150199332A1

公开(公告)日：2015-07-16

申请号：US14423950

申请日：2012-08-31

Applicant: Mu Li ,  Xi Chen

Inventor： Mu Li ,  Xi Chen

IPC: G06F17/27 ,  G06F17/30 ,  H04L29/08

CPC classification number: G06F16/9574 ,  G06F3/018 ,  G06F3/0237 ,  G06F17/276 ,  H04L67/2857

Abstract: Some examples may include generating a browsing history language model based on browsing history information. Further, some implementations may include predicting and presenting a non-Latin character string based at least in part on the browsing history language model, such as in response to receiving a Latin character string via an input method editor interface.

Abstract translation: 一些示例可以包括基于浏览历史信息生成浏览历史语言模型。 此外，一些实现可以包括至少部分地基于浏览历史语言模型来预测和呈现非拉丁字符串，诸如响应于经由输入方法编辑器界面接收拉丁字符串。

公开(公告)号：US20120022850A1

公开(公告)日：2012-01-26

申请号：US13250417

申请日：2011-09-30

Applicant: Chi-Ho Li ,  Mu Li ,  Dongdong Zhang ,  Ming Zhou

Inventor： Chi-Ho Li ,  Mu Li ,  Dongdong Zhang ,  Ming Zhou

IPC: G06F17/28

CPC classification number: G06F17/2818

Abstract: A method of statistical machine translation (SMT) is provided. The method comprises generating reordering knowledge based on the syntax of a source language (SL) and a number of alignment matrices that map sample SL sentences with sample target language (TL) sentences. The method further comprises receiving a SL word string and parsing the SL word string into a parse tree that represents the syntactic properties of the SL word string. The nodes on the parse tree are reordered based on the generated reordering knowledge in order to provide reordered word strings. The method further comprises translating a number of reordered word strings to create a number of TL word strings, and identifying a statistically preferred TL word string as a preferred translation of the SL word string.

Abstract translation: 提供了统计机器翻译（SMT）的方法。 该方法包括基于源语言（SL）的语法和将样本SL语句与样本目标语言（TL）语句对齐的多个对齐矩阵来生成重排序知识。 该方法还包括接收SL字串并将SL字串解析成表示SL字串的句法属性的解析树。 基于所生成的重新排序知识来重新排序解析树上的节点，以提供重新排序的字串。 该方法还包括翻译多个重新排序的字串以创建多个TL字串，并且将统计上优选的TL字串识别为SL字串的优选翻译。

公开(公告)号：US08046211B2

公开(公告)日：2011-10-25

申请号：US11977133

申请日：2007-10-23

Applicant: Chi-Ho Li ,  Mu Li ,  Dongdong Zhang ,  Ming Lester Alexander Zhou

Inventor： Chi-Ho Li ,  Mu Li ,  Dongdong Zhang ,  Ming Lester Alexander Zhou

IPC: G06F17/20 ,  G10L21/00

CPC classification number: G06F17/2818

Abstract: A method of statistical machine translation (SMT) is provided. The method comprises generating reordering knowledge based on the syntax of a source language (SL) and a number of alignment matrices that map sample SL sentences with sample target language (TL) sentences. The method further comprises receiving a SL word string and parsing the SL word string into a parse tree that represents the syntactic properties of the SL word string. The nodes on the parse tree are reordered based on the generated reordering knowledge in order to provide reordered word strings. The method further comprises translating a number of reordered word strings to create a number of TL word strings, and identifying a statistically preferred TL word string as a preferred translation of the SL word string.

Abstract translation: 提供了统计机器翻译（SMT）的方法。 该方法包括基于源语言（SL）的语法和将样本SL语句与样本目标语言（TL）语句对齐的多个对齐矩阵来生成重排序知识。 该方法还包括接收SL字串并将SL字串解析成表示SL字串的句法属性的解析树。 基于所生成的重新排序知识来重新排序解析树上的节点，以提供重新排序的字串。 该方法还包括翻译多个重新排序的字串以创建多个TL字串，并且将统计上优选的TL字串识别为SL字串的优选翻译。

公开(公告)号：US07818332B2

公开(公告)日：2010-10-19

申请号：US11465023

申请日：2006-08-16

Applicant: Elliott K. Olds ,  Gregory N. Hullender ,  Haoyong Zhang ,  Janine R. Crumb ,  Jianfeng Gao ,  Ming Zhou ,  Mu Li ,  Yajuan Lv

Inventor： Elliott K. Olds ,  Gregory N. Hullender ,  Haoyong Zhang ,  Janine R. Crumb ,  Jianfeng Gao ,  Ming Zhou ,  Mu Li ,  Yajuan Lv

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F17/3064

Abstract: Candidate suggestions for correcting misspelled query terms input into a search application are automatically generated. A score for each candidate suggestion can be generated using a first decoding pass and paths through the suggestions can be ranked in a second decoding pass. Candidate suggestions can be generated based on typographical errors, phonetic mistakes and/or compounding mistakes. Furthermore, a ranking model can be developed to rank candidate suggestions to be presented to a user.

Abstract translation: 自动生成用于纠正输入到搜索应用程序中的拼错查询条件的候选建议。 可以使用第一解码通道来生成每个候选建议的得分，并且通过建议的路径可以被排列在第二解码通行证中。 可以根据印刷错误，语音错误和/或复合错误生成候选建议。 此外，可以开发排名模型来排列要呈现给用户的候选建议。

公开(公告)号：US20100059203A1

公开(公告)日：2010-03-11

申请号：US12399030

申请日：2009-03-06

Applicant: Ching-Hung Chu ,  Chang-Mu Li

Inventor： Ching-Hung Chu ,  Chang-Mu Li

IPC: F28F13/00

CPC classification number: H01L23/3672 ,  G06F1/20 ,  H01L23/4093 ,  H01L2924/0002 ,  H01L2924/00

Abstract: A heat dissipation device for an electronic component includes a heat sink thermally contacting the electronic component and a label member fixed on the heat sink for providing information. The heat sink includes a base and a plurality of fins extending upwardly from a top surface of the base. Two engaging portions protrude from two spaced fins, towards each other. Two flanges angle outwardly from two opposite lateral sides of the label member and clasp the two engaging portions of the heat sink, respectively.

Abstract translation: 一种用于电子部件的散热装置包括热接触电子部件的散热器和固定在散热器上的用于提供信息的标签部件。 散热器包括基部和从基部的顶表面向上延伸的多个翅片。 两个接合部分从两个隔开的翅片彼此朝向彼此突出。 两个法兰从标签构件的两个相对的侧面向外侧倾斜并分别扣住散热器的两个接合部分。

公开(公告)号：US07590626B2

公开(公告)日：2009-09-15

申请号：US11589557

申请日：2006-10-30

Applicant: Mu Li ,  Ming Zhou

Inventor： Mu Li ,  Ming Zhou

IPC: G06F17/30

CPC classification number: G06F17/3069 ,  G06F17/30672 ,  G06F17/30687 ,  G06Q10/063 ,  Y10S707/99933 ,  Y10S707/99934 ,  Y10S707/99935

Abstract: A distributional similarity between a word of a search query and a term of a candidate word sequences is used to determine an error model probability that describes the probability of the search query given the candidate word sequence. The error model probability is used to determine a probability of the candidate word sequence given the search query. The probability of the candidate word sequence given the search query is used to select a candidate word sequence as a corrected word sequence for the search query. Distributional similarity is also used to build features that are applied in maximum entropy model to compute the probability of the candidate word sequence given the search query.

Abstract translation: 使用搜索查询的词和候选词序列的词之间的分布相似度来确定描述候选词序列的搜索查询的概率的误差模型概率。 误差模型概率用于确定给定搜索查询的候选词序列的概率。 使用给出搜索查询的候选词序列的概率用于选择候选词序列作为搜索查询的校正单词序列。 分布相似性也用于构建在最大熵模型中应用的特征，以计算给定搜索查询的候选词序列的概率。

公开(公告)号：US20090106015A1

公开(公告)日：2009-04-23

申请号：US11977133

申请日：2007-10-23

Applicant: Chi-Ho Li ,  Mu Li ,  Dongdong Zhang ,  Ming Zhou

Inventor： Chi-Ho Li ,  Mu Li ,  Dongdong Zhang ,  Ming Zhou

IPC: G06F17/28

CPC classification number: G06F17/2818

Abstract: A method of statistical machine translation (SMT) is provided. The method comprises generating reordering knowledge based on the syntax of a source language (SL) and a number of alignment matrices that map sample SL sentences with sample target language (TL) sentences. The method further comprises receiving a SL word string and parsing the SL word string into a parse tree that represents the syntactic properties of the SL word string. The nodes on the parse tree are reordered based on the generated reordering knowledge in order to provide reordered word strings. The method further comprises translating a number of reordered word strings to create a number of TL word strings, and identifying a statistically preferred TL word string as a preferred translation of the SL word string.

Abstract translation: 提供了统计机器翻译（SMT）的方法。 该方法包括基于源语言（SL）的语法和将样本SL语句与样本目标语言（TL）语句对齐的多个对齐矩阵来生成重新排序知识。 该方法还包括接收SL字串并将SL字串解析成表示SL字串的句法属性的解析树。 基于所生成的重新排序知识来重新排序解析树上的节点，以提供重新排序的字串。 该方法还包括翻译多个重新排序的字串以创建多个TL字串，并且将统计上优选的TL字串识别为SL字串的优选翻译。

公开(公告)号：US20090083255A1

公开(公告)日：2009-03-26

申请号：US11903591

申请日：2007-09-24

Applicant: Mu Li

Inventor： Mu Li

IPC: G06F17/30

CPC classification number: G06F17/273 ,  G06F16/3325 ,  G06F16/951

Abstract: A technology for query spelling correction is disclosed. In one method approach, web search results generated based on a query term are received. The web search results are used as a part of determining a correction candidate for the query term if the query term is incorrectly spelt.

Abstract translation: 公开了一种用于查询拼写校正的技术。 在一种方法中，接收基于查询项生成的网络搜索结果。 如果查询项不正确拼写，则网页搜索结果被用作确定查询项的校正候选的一部分。

公开(公告)号：US07231349B2

公开(公告)日：2007-06-12

申请号：US10448498

申请日：2003-05-30

Applicant: Mu Li ,  Jianfeng Gao

Inventor： Mu Li ,  Jianfeng Gao

IPC: G01L15/06

CPC classification number: G10L15/197 ,  G06F17/277 ,  G10L15/285

Abstract: A method and data structure are provided for efficiently storing asymmetric clustering models. The models are stored by storing a first level record for a word identifier and two second level records, one for a word identifier and one for a cluster identifier. An index to the second level word record and an index to the second level cluster record are stored in the first level record. Many of the records in the data structure include both cluster sub-model parameters and word sub-model parameters.

Abstract translation: 提供了一种方法和数据结构，用于有效地存储非对称聚类模型。 通过存储用于字标识符的第一级记录和两个第二级记录来存储模型，一个用于字标识符，一个用于集群标识符。 第二级记录的索引和第二级集群记录的索引存储在第一级记录中。 数据结构中的许多记录包括集群子模型参数和单词子模型参数。

公开(公告)号：US09824085B2

公开(公告)日：2017-11-21

申请号：US14423914

申请日：2012-08-31

Applicant: Mu Li ,  Xi Chen

Inventor： Mu Li ,  Xi Chen

IPC: G06F17/28 ,  G06F17/22 ,  G06F17/27

CPC classification number: G06F17/2863 ,  G06F17/2223 ,  G06F17/276

Abstract: Some examples include generating a personal language model based on linguistic characteristics of one or more files stored at one or more locations in a file system. Further, some implementations include predicting and presenting a non-Latin character string based at least in part on the personal language model, such as in response to receiving a Latin character string via an input method editor interface.