Statistical machine translation processing
    51.
    发明申请
    Statistical machine translation processing 有权
    统计机器翻译处理

    公开(公告)号:US20090106015A1

    公开(公告)日:2009-04-23

    申请号:US11977133

    申请日:2007-10-23

    IPC分类号: G06F17/28

    CPC分类号: G06F17/2818

    摘要: 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.

    摘要翻译: 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。

    KNOWLEDGE EXTRACTION FROM ONLINE DISCUSSION FORUMS
    52.
    发明申请
    KNOWLEDGE EXTRACTION FROM ONLINE DISCUSSION FORUMS 有权
    知识从线上讨论提取

    公开(公告)号:US20080046394A1

    公开(公告)日:2008-02-21

    申请号:US11464373

    申请日:2006-08-14

    IPC分类号: G06N7/02

    摘要: Concepts presented herein relate to extracting knowledge for a chatbot knowledge base from online discussion forms. Within a thread of on online discussion form, replies are selected based on structural features and content features therein. The replies can be ranked and used in a chatbot knowledge base.

    摘要翻译: 本文提出的概念涉及从在线讨论形式提取关于chatbot知识库的知识。 在在线讨论表单的线索中,基于其中的结构特征和内容特征来选择回复。 这些回复可以在chatbot知识库中进行排名和使用。

    Method and system for retrieving hint sentences using expanded queries
    53.
    发明授权
    Method and system for retrieving hint sentences using expanded queries 有权
    使用扩展查询检索提示句的方法和系统

    公开(公告)号:US07171351B2

    公开(公告)日:2007-01-30

    申请号:US10247684

    申请日:2002-09-19

    申请人: Ming Zhou

    发明人: Ming Zhou

    IPC分类号: G06F17/27

    CPC分类号: G06F17/30672

    摘要: A method, computer readable medium and system are provided which retrieve hint sentences from a sentence database in response to a query. An input component receives the query having terms. A search engine expands the query by including synonyms of the terms to obtain expanded terms. The search engine then combines the expanded terms to form dependency triples from the expanded terms. From the formed dependency triples, dependency triples which are not found in a dependency triples database are discarded to obtain remaining dependency triples from the expanded terms. The search engine then searches the sentence database using the remaining dependency triples as search parameters.

    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提示句子。 输入组件接收具有术语的查询。 搜索引擎通过包含术语的同义词来扩展查询以获得扩展的术语。 然后,搜索引擎将扩展的术语组合成从扩展术语形成依赖三元组。 从形成的依赖性三元组中,依赖三元组数据库中找不到的依赖性三元组被丢弃以从扩展的术语获得剩余的依赖关系三元组。 搜索引擎然后使用剩余的依赖关系三元组搜索句子数据库作为搜索参数。

    Named entity translation
    54.
    发明申请
    Named entity translation 审中-公开
    命名实体翻译

    公开(公告)号:US20070011132A1

    公开(公告)日:2007-01-11

    申请号:US11155829

    申请日:2005-06-17

    申请人: Ming Zhou Long Jiang

    发明人: Ming Zhou Long Jiang

    IPC分类号: G06F17/30

    CPC分类号: G06F16/951

    摘要: Named entity translation of a named entity in a source language is translated to a target language by combining a transliteration of the named entity with data mining in the target language.

    摘要翻译: 通过将命名实体的音译与目标语言中的数据挖掘相结合,将源语言中的命名实体命名实体翻译转换为目标语言。

    Processing collocation mistakes in documents
    55.
    发明申请
    Processing collocation mistakes in documents 有权
    处理文件中的并置错误

    公开(公告)号:US20070010992A1

    公开(公告)日:2007-01-11

    申请号:US11177136

    申请日:2005-07-08

    IPC分类号: G06F17/27

    摘要: A sentence is accessed and at least one query is generated based on the sentence. At least one query can be compared to text within a collection of documents, for example using a web search engine. Collocation errors in the sentence can be detected and/or corrected based on the comparison of the at least one query and the text within the collection of documents.

    摘要翻译: 访问一个句子,并且基于该句子生成至少一个查询。 至少可以将一个查询与文档集合中的文本进行比较,例如使用Web搜索引擎。 可以基于至少一个查询与文档集合内的文本的比较来检测和/或修正该句子中的配置错误。

    Document information extraction with cascaded hybrid model
    56.
    发明申请
    Document information extraction with cascaded hybrid model 审中-公开
    使用级联混合模型的文档信息提取

    公开(公告)号:US20070005549A1

    公开(公告)日:2007-01-04

    申请号:US11149713

    申请日:2005-06-10

    申请人: Ming Zhou Kun Yu

    发明人: Ming Zhou Kun Yu

    IPC分类号: G06F17/30

    CPC分类号: G06F16/835

    摘要: General information blocks of text are extracted from a document. A label is applied to each general information block and detailed information strings of text are extracted from at least one of the general information blocks based on the corresponding label of the at least one general information block.

    摘要翻译: 从文档中提取文本的一般信息块。 将标签应用于每个一般信息块,并且基于至少一个一般信息块的相应标签从至少一个通用信息块中提取文本的详细信息串。

    Computer-aided writing system and method with cross-language writing wizard
    57.
    发明授权
    Computer-aided writing system and method with cross-language writing wizard 有权
    计算机辅助写作系统和方法与跨语言写作向导

    公开(公告)号:US07107204B1

    公开(公告)日:2006-09-12

    申请号:US09556229

    申请日:2000-04-24

    IPC分类号: G06F17/28

    摘要: A computer-aided writing system offers assistance to a user writing in a non-native language, as the user needs help, without requiring the user to divert attention away from the entry task. The writing system provides a user interface (UI) that integrates writing assistance with in-line text entry. When the user is unsure of a word's spelling or whether the word is appropriate, the user may enter a corresponding native word directly in line with the ongoing sentence. An error tolerant spelling tool accepts the native word (even if it is misspelled or mistyped) and derives the most probable non-native word for the given context. The spelling tool consults a bilingual dictionary to determine possible non-native word translation candidates, a non-native language model (e.g., a trigram language model) to generate probabilities associated with the candidates given the current sentence or phrase context, and a translation model to generate probabilities of how likely a certain native word was intended given the non-native word candidates. From these probabilities, the spelling tool determines the most probable non-native word translation and substitutes the non-native word for the native input string. If the user likes the non-native word, the user may simply continue with the sentence. On the other hand, if the user is still unsure of the non-native word, the user can invoke a sentence recommendation tool that allows the user to see the non-native word in a bilingual sentence pair to learn how the word can be used.

    摘要翻译: 计算机辅助写入系统为用户以非本地语言编写的协助,因为用户需要帮助,而不需要用户将注意力转移到入口任务之外。 写作系统提供了一种将写作辅助与内联文本输入相集成的用户界面(UI)。 当用户不确定单词的拼写或该单词是否合适时,用户可以直接输入相应的本地词,与正在进行的句子一致。 容错拼写工具接受本机字(即使是拼写错误或错误的),并为给定上下文导出最可能的非本地字。 拼写工具咨询双语字典以确定可能的非本地字翻译候选者,非本地语言模型(例如,三元语言模型),以产生与给定当前句子或短语上下文的候选者相关联的概率,以及翻译模型 以产生对非本地词候选人给定某个本地词的可能性的概率。 从这些概率中,拼写工具确定最可能的非本地字翻译,并将非本地字替换为本地输入字符串。 如果用户喜欢非母语,则用户可以简单地继续该句子。 另一方面,如果用户仍然不确定非本地字,则用户可以调用允许用户在双语句子对中看到非本地字的句子推荐工具,以了解该字可如何使用 。

    Method and system for retrieving confirming sentences
    58.
    发明申请
    Method and system for retrieving confirming sentences 有权
    检索确认句子的方法和系统

    公开(公告)号:US20050273318A1

    公开(公告)日:2005-12-08

    申请号:US11187567

    申请日:2005-07-22

    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。

    Dynamic link
    59.
    发明授权
    Dynamic link 失效
    动态链接

    公开(公告)号:US06856989B1

    公开(公告)日:2005-02-15

    申请号:US09545045

    申请日:2000-04-07

    IPC分类号: G06F17/30

    摘要: A file system for file sharing includes a web server that creates a temporary directory for each session between the web server and a client computer. When the client computer requests a file located in a file server, the web server creates a symbolic link to the file in the temporary directory and a web page including an URL to the symbolic link. The web server transmits the web page, and therefore the file, to the client computer. Client computer can also upload files to the web server. The web server saves the uploaded files to the temporary directory and then moves the files to the file server. At the end of the session, the web server deletes the temporary directory. Thus, files are not saved on the web server and therefore not accessible to others from the Internet. In this file system, file and directory names are orderly incremented in the file server to simplify the back up process of the file server. Furthermore, previously backed up directories are checked for their current size to determine if they should be backed up again. By backing up previously backed up directories that are now smaller speeds up the restoration of file serve when necessary.

    摘要翻译: 用于文件共享的文件系统包括为web服务器和客户端计算机之间的每个会话创建临时目录的web服务器。 当客户端计算机请求位于文件服务器中的文件时,Web服务器创建到临时目录中的文件的符号链接和包括符号链接的URL的网页。 Web服务器将网页(因此将文件)发送到客户端计算机。 客户端计算机也可以将文件上传到Web服务器。 Web服务器将上传的文件保存到临时目录,然后将文件移动到文件服务器。 在会话结束时,Web服务器删除临时目录。 因此,文件不会保存在Web服务器上,因此不能从Internet上的其他人访问。 在该文件系统中,文件服务器中的文件和目录名称有序增加,以简化文件服务器的备份过程。 此外,先前备份的目录将检查其当前大小,以确定是否应再次备份它们。 通过备份以前备份的目录,这些目录在加速文件恢复时需要更小的速度。

    Electronics enclosure having an interior EMI shielding and cosmetic coating
    60.
    发明授权
    Electronics enclosure having an interior EMI shielding and cosmetic coating 失效
    电子外壳具有内部EMI屏蔽和化妆品涂层

    公开(公告)号:US06809254B2

    公开(公告)日:2004-10-26

    申请号:US10175163

    申请日:2002-06-18

    IPC分类号: H05K900

    CPC分类号: H05K9/0045 H05K5/0243

    摘要: An enclosure for housing circuitry of an electronic device including at least one enclosure part, and a shielding layer on the part. The enclosure part has an exterior surface and an opposing interior surface defining a wall therebetween, and is formed of a plastic material which is generally transparent. The shielding layer is provided to cover at least a portion of the interior surface of the enclosure part. The layer is formulated to provide EMI shielding for the circuitry housed within the enclosure, and as coated or otherwise applied to the interior surface is visually perceptible through the exterior surface of the enclosure part for enhancing the cosmetic appearance of the enclosure.

    摘要翻译: 一种用于电子设备的壳体电路的外壳,包括至少一个外壳部件和该部件上的屏蔽层。 外壳部分具有外表面和在其之间限定壁的相对的内表面,并且由通常是透明的塑料材料形成。 屏蔽层设置成覆盖外壳部分的内表面的至少一部分。 该层配制成为容纳在外壳内的电路提供EMI屏蔽,并且通过外壳部分的外表面可视地感知涂覆或以其它方式施加到内表面的电磁屏蔽,以增强外壳的外观。