专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO1997040452A1 AUTOMATED NATURAL LANGUAGE TRANSLATION 审中-公开
标题翻译：自动语言翻译
公开(公告)号：WO1997040452A1
公开(公告)日：1997-10-30
申请号：PCT/US1996005567
申请日：1996-04-23
申请人： LANGUAGE ENGINEERING CORPORATION , AKERS, Glenn, A. , KUNO, Susumu
发明人： LANGUAGE ENGINEERING CORPORATION
IPC分类号： G06F17/28
CPC分类号： G06F17/271 , G06F17/2863 , G06F17/2872 , G06F17/289
摘要： An automated natural language translation system takes source natural language textual statements (preferably in English) and translates them into a target natural language (preferably Japanese). The system also allows an operator to re-translate automatically selected portions of the source text. The system includes improvements directed: to providing more exact initial translations of writings with words having different translations in different fields; to designating certain grammar rules as controlling to eliminate undesirable translations; and to using probability values associated with some dictionary entries to eliminate undesirable translations.
摘要翻译：自动语言翻译系统采用源自然语言文本语言（最好用英语），并将其翻译成目标自然语言（最好是日语）。该系统还允许操作者自动重新翻译源文本的所选部分。该系统包括改进：提供更准确的初始翻译的文字与不同翻译在不同领域的单词; 指定某些语法规则作为控制以消除不希望的翻译; 并使用与一些字典条目相关联的概率值来消除不期望的翻译。

2. 发明申请

WO1997048058A1 AUTOMATED TRANSLATION OF ANNOTATED TEXT 审中-公开
标题翻译：自动翻译文字
公开(公告)号：WO1997048058A1
公开(公告)日：1997-12-18
申请号：PCT/US1997010005
申请日：1997-06-09
申请人： LANGUAGE ENGINEERING CORPORATION , PRINGLE, Lewis, G. , SWERDLOW, Robert, W. , WYSOKER, Alec
发明人： LANGUAGE ENGINEERING CORPORATION
IPC分类号： G06F17/28
CPC分类号： G06F17/271 , G06F17/272 , G06F17/2818 , G06F17/2872
摘要： A system and method for translating an annotated source document in a first natural language to a target document in a second natural language having corresponding annotations, includes computer storage, a computer receiving module for receiving input textual information in a first language and for storing the input textual information in the computer storage, the input textual information including annotations and a translation engine for creating a first token string including first language tokens, annotations tokens that apply to the first language tokens, and ending tokens. Prior to translation, the annotation tokens are removed from the first token string and a plurality of annotation records are created for the first language tokens, each annotation record linking one of the first language tokens to each of the annotation tokens that apply to the first language token. After the first language tokens have been translated into the second language tokens, the annotation tokens are inserted at appropriate locations in the second token string. These locations are determined using the end-of-sentence tokens and the annotation records, and a target document is produced in the second language using the second token string and annotations, thus recreating in the target document, the annotations of the source document.
摘要翻译：一种用于以第一自然语言将注释的源文档翻译成具有相应注释的第二自然语言的目标文档的系统和方法，包括计算机存储器，用于接收第一语言的输入文本信息并存储输入的计算机接收模块计算机存储器中的文本信息，包括注释的输入文本信息和用于创建包括第一语言令牌的第一令牌串，适用于第一语言令牌的注释令牌和结束令牌的翻译引擎。在翻译之前，从第一令牌字符串中移除注释令牌，并为第一语言令牌创建多个注释记录，每个注释记录将第一语言令牌中的一个连接到适用于第一语言的每个注释令牌令牌。在将第一语言令牌翻译成第二语言令牌之后，将注释令牌插入第二个令牌字符串中的适当位置。这些位置是使用结尾句子和注释记录确定的，并且使用第二个令牌字符串和注释以第二种语言生成目标文档，从而在目标文档中重新创建源文档的注释。

3. 发明申请

WO1997040453A1 AUTOMATED NATURAL LANGUAGE PROCESSING 审中-公开
标题翻译：自动语言处理
公开(公告)号：WO1997040453A1
公开(公告)日：1997-10-30
申请号：PCT/US1996010283
申请日：1996-06-14
申请人： LANGUAGE ENGINEERING CORPORATION , AKERS, Glenn, A. , KUNO, Susumu
发明人： LANGUAGE ENGINEERING CORPORATION
IPC分类号： G06F17/28
CPC分类号： G06F17/271 , G06F17/2863 , G06F17/2872 , G06F17/289
摘要： An automated natural language translation system takes source natural language text (preferably in Japanese) and translates them into a target natural language (preferably English). The system also allows an operator to re-translate automatically selected portions of the source text. The system includes an improvement directed to transforming kanas in the source text into alphabetic letters of the target language which allows the presence of a word or phrase boundary to be recognized in the middle of a kana. The system also includes an improvement involving performing concurrently on the source text both a morphological analysis and a syntactic analysis.
摘要翻译：自动语言翻译系统采用源自然语言文本（最好是日语），并将其翻译成目标自然语言（最好是英文）。该系统还允许操作者自动重新翻译源文本的所选部分。该系统包括针对将源文本中的卡纳变换为目标语言的字母字母的改进，其允许在假名中识别出单词或短语边界。该系统还包括改进，涉及同时对源文本进行形态分析和句法分析。

4. 发明申请

WO1996041281A1 MACHINE ASSISTED TRANSLATION TOOLS 审中-公开
标题翻译：机器辅助翻译工具
公开(公告)号：WO1996041281A1
公开(公告)日：1996-12-19
申请号：PCT/US1996008419
申请日：1996-06-03
申请人： INTERNATIONAL LANGUAGE ENGINEERING CORPORATION
发明人： INTERNATIONAL LANGUAGE ENGINEERING CORPORATION , HARGRAVE, James, E., III , SAVOUREL, Yves, I.
IPC分类号： G06F17/28
CPC分类号： G06F17/2827 , G06F17/2836 , Y10S707/99935
摘要： A translation memory (400) for computer assisted translation based upon an aligned file (403) having a number of source language text strings paired with target language text strings. A posting vector file (405) includes a posting vector associated with each source language text string in the aligned file. Each posting vector includes a document identification number corresponding to a selected one of the source language text strings in the aligned file and a number of entropy weight values, each of the number of weight values corresponding to a unique letter n-gram that appears in the selected source language text string. Preferably, the translation memory further includes an inverted index (409) comprising a listing of source language letter n-grams and a pointer to each of the posting vectors including an entry for the listed letter n-gram.
摘要翻译：一种用于计算机辅助翻译的翻译记忆库（400），其基于具有与目标语言文本串配对的多个源语言文本串的对准文件（403）。发布向量文件（405）包括与对齐文件中的每个源语言文本串相关联的发布向量。每个发布向量包括对应于对齐文件中的源语言文本串中的所选择的一个文档标识号和多个熵权值，每个权重值的数量对应于出现在该对应文件中的唯一字母n-gram 选择源语言文本字符串。优选地，翻译存储器还包括反向索引（409），其包括源语言字母n-gram的列表和指向每个发布向量的指针，其包括列出的字母n-gram的条目。

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