-
Patent Agency Ranking
公开(公告)号：US09037449B2
公开(公告)日：2015-05-19
申请号：US13664881
申请日：2012-10-31
Inventor： Chang Hyun Kim , Young-Ae Seo , Seong Il Yang , Jinxia Huang , Jong Hun Shin , Young Kil Kim , Sang Kyu Park
CPC classification number: G06F17/2818 , G06F17/2827
Abstract: A method for establishing paraphrasing data for a machine translation system includes selecting a paraphrasing target sentence through application of an object language model to a translated sentence that is obtained by machine-translating a source language sentence, extracting paraphrasing candidates that can be paraphrased with the paraphrasing target sentence from a source language corpus DB, performing machine translation with respect to the paraphrasing candidates, selecting a final paraphrasing candidate by applying the object language model to the result of the machine translation with respect to the paraphrasing candidates, and confirming the paraphrasing target sentence and the final paraphrasing candidate as paraphrasing lexical patterns using a bilingual corpus and storing the paraphrasing lexical patterns in a paraphrasing DB. According to the present invention, the consistent paraphrasing data can be established since the paraphrasing data is automatically established.
Abstract translation: 一种用于建立机器翻译系统的释义数据的方法包括通过将对象语言模型应用于通过机器翻译源语言句子获得的翻译句子来选择释义目标句子，提取可以用释义改写的替换候选者 来自源语言语料库DB的目标句子，对释义候选者进行机器翻译，通过将对象语言模型应用于机器翻译的结果，对于释义候选者来选择最终释义候选者，并且确认释义目标句子 和最后的释义候选人作为使用双语语料库的释义词汇模式，并将释义词汇模式存储在一个改写的DB中。 根据本发明，自动建立释义数据可以建立一致的释义数据。
-
2.发明授权Spoken dialog system based on dual dialog management using hierarchical dialog task library 有权基于双对话管理的口语对话系统，使用分层对话任务库公开(公告)号：US09230544B2
公开(公告)日：2016-01-05
申请号：US13849853
申请日：2013-03-25
Inventor： Oh Woog Kwon , Yoon Hyung Roh , Seong Il Yang , Ki Young Lee , Sang Keun Jung , Sung Kwon Choi , Eun Jin Park , Jinxia Huang , Young Kil Kim , Chang Hyun Kim , Seung Hoon Na , Young Ae Seo , Yun Jin , Jong Hun Shin , Sang Kyu Park
CPC classification number: G10L15/22 , G06F3/167 , G10L2015/225 , H04M3/4938
Abstract: The present invention relates to a spoken dialog system and method based on dual dialog management using a hierarchical dialog task library that may increase reutilization of dialog knowledge by constructing and packaging the dialog knowledge based on a task unit having a hierarchical structure, and may construct and process the dialog knowledge using a dialog plan scheme about relationship therebetween by classifying the dialog knowledge based on a task unit to make design of a dialog service convenient, which is different from an existing spoken dialog system in which it is difficult to reuse dialog knowledge since a large amount of construction costs and time is required.
Abstract translation: 本发明涉及一种基于双对话管理的口语对话系统和方法，其中使用层次对话任务库，其可以通过基于具有层次结构的任务单元构建和打包对话知识来增加对话知识的再利用，并且可以构建和 使用关于它们之间的关系的对话计划方案处理对话知识，通过对基于任务单元的对话知识进行分类，使对话服务的设计方便，这与现有的口语对话系统不同，其中难以重用对话知识，因为 需要大量的施工成本和时间。
-
公开(公告)号：US11301625B2
公开(公告)日：2022-04-12
申请号：US16681866
申请日：2019-11-13
Inventor： Yoon Hyung Roh , Jong Hun Shin , Young Ae Seo
IPC: G06F40/45 , G06F40/211 , G10L15/22 , G06F40/253 , G10L13/00 , G10L15/26
Abstract: A simultaneous interpretation system using a translation unit bilingual corpus includes a microphone configured to receive an utterance of a user, a memory in which a program for recognizing the utterance of the user and generating a translation result is stored, and a processor configured to execute the program stored in the memory, wherein the processor executes the program so as to convert the received utterance of the user into text, store the text in a speech recognition buffer, perform translation unit recognition with respect to the text on the basis of a learning model for translation unit recognition, and in response to the translation unit recognition being completed, generate a translation result corresponding to the translation unit on the basis of a translation model for translation performance.
-
4.发明授权公开(公告)号：US12217014B2
公开(公告)日：2025-02-04
申请号：US17570879
申请日：2022-01-07
Inventor： Jinxia Huang , Jong Hun Shin
Abstract: Provided is a method of providing an interpretation result using visual information, and the method includes: acquiring a spatial domain image including line-of-sight information of a user and gaze position information in the spatial domain image; segmenting the acquired spatial domain image into a plurality of images; detecting text areas including text for each of the segmented images; generating text blocks, each of which is a text recognition result for each of the detected text areas, and determining the text block corresponding to the gaze position information; converting a first language included in the determined text block into a second language that is a target language; and providing the user with a conversion result of the second language.
-
公开(公告)号：US20140172411A1
公开(公告)日：2014-06-19
申请号：US14040036
申请日：2013-09-27
Inventor： Chang Hyun KIM , Oh Woog Kwon , Seung Hoon Na , Yoon Hyung Roh , Young Ae Seo , Seong Il Yang , Ki Young Lee , Sang Keun Jung , Sung Kwon Choi , Yun Jin , Eun Jin Park , Jong Hun Shin , Jinxia Huang , Sang Kyu Park
IPC: G06F17/28
CPC classification number: G06F17/2854
Abstract: Provided are an apparatus and a method for verifying a context that verify an ambiguous expression of an input text through a user's intention and utilize the verified expression as a context in interpretation and translation. The apparatus includes: an ambiguous expression verifying unit verifying an ambiguous expression in a first input text or a back translation text for the first input text in accordance with user's input; a context generating unit generating the verified ambiguous expression as a context; and a context controlling unit controlling the generated context to be applied to translate or interpret the first input text or second input texts input after the first input text.
Abstract translation: 提供了一种用于验证通过用户意图验证输入文本的模糊表达的上下文的装置和方法，并且将所验证的表达式用作解释和翻译中的上下文。 该装置包括：模糊表达式验证单元，用于根据用户的输入验证第一输入文本或第一输入文本的后翻译文本中的模糊表达; 上下文生成单元，生成经验证的模糊表达作为上下文; 以及上下文控制单元，其控制要应用的生成的上下文来翻译或解释在第一输入文本之后输入的第一输入文本或第二输入文本。
-
-
-
-
Search Results
5
records
(took 0.015 seconds)
