公开(公告)号：US20140172411A1

公开(公告)日：2014-06-19

申请号：US14040036

申请日：2013-09-27

Applicant: Electronics and Telecommunications Research Institute

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。

公开(公告)号：US10332033B2

公开(公告)日：2019-06-25

申请号：US15405425

申请日：2017-01-13

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Oh Woog Kwon ,  Young Kil Kim ,  Yun Keun Lee

IPC: G10L15/01 ,  G10L15/22 ,  G06N20/00 ,  G10L15/18 ,  G06F17/24 ,  G06F17/27

Abstract: An incremental self-learning based dialogue apparatus for dialogue knowledge includes a dialogue processing unit configured to determine a intention of a user utterance by using a knowledge base and perform processing or a response suitable for the user intention, a dialogue establishment unit configured to automatically learn a user intention stored in a intention annotated learning corpus, store information about the learned user intention in the knowledge base, and edit and manage the knowledge base and the intention annotated learning corpus, and a self-knowledge augmentation unit configured to store a log of a dialogue performed by the dialogue processing unit, detect and classify an error in the stored dialogue log, automatically tag a user intention for the detected and classified error, and store the tagged user intention in the intention annotated learning corpus.

公开(公告)号：US09230544B2

公开(公告)日：2016-01-05

申请号：US13849853

申请日：2013-03-25

Applicant: Electronics and Telecommunications Research Institute

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

IPC: G10L15/00 ,  G10L15/22 ,  H04M3/493 ,  G06F3/16

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。