Patents by Inventor Chang-Hao Yin
Chang-Hao Yin has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10303775Abstract: The present invention relates to the use of a plurality of dependency trees in tree-based statistical machine translation and proposes a dependency forest to effectively process the plurality of dependency trees. The present invention can improve a translation capability by generating a translation rule and a dependency language model by using the dependency forest and applying the generated translation rule and dependency language model when a source language text is converted to a target language text.Type: GrantFiled: May 1, 2018Date of Patent: May 28, 2019Assignee: ELEVEN STREET CO., LTD.Inventors: Young Sook Hwang, Sang-Bum Kim, Shouxun Lin, Zhaopeng Tu, Yang Liu, Qun Liu, Chang Hao Yin
-
Patent number: 10198437Abstract: The present invention relates to statistical machine translation, and provides a machine translation device and a machine translation method that acquire a creation probability for a target language from a single corpus while extracting respective conversion probabilities by extracting syntax conversion knowledge and word translation knowledge from a parallel corpus, model a weighted translation model by allowing each of the conversion knowledge and each of the probabilities to learn using a translation model learning device, and generate a target sentence through decoding processes of a syntax converter and a word translator by applying the translation model to a source sentence input in real time, thereby resolving disadvantages of the existing phrase-based SMT and syntax-based SMT and combining advantages thereof.Type: GrantFiled: July 20, 2011Date of Patent: February 5, 2019Assignee: SK PLANET CO., LTD.Inventors: Young Sook Hwang, Sang-Bum Kim, Chang Hao Yin, Yeon Su Lee, Seong Wook Lee, Hae Chang Rim
-
Publication number: 20180314690Abstract: The present invention relates to the use of a plurality of dependency trees in tree-based statistical machine translation and proposes a dependency forest to effectively process the plurality of dependency trees. The present invention can improve a translation capability by generating a translation rule and a dependency language model by using the dependency forest and applying the generated translation rule and dependency language model when a source language text is converted to a target language text.Type: ApplicationFiled: May 1, 2018Publication date: November 1, 2018Inventors: Young Sook Hwang, Sang-Bum Kim, Shouxun Lin, Zhaopeng Tu, Yang Liu, Qun Liu, Chang Hao Yin
-
Patent number: 9971757Abstract: The present disclosure relates to a syntax parsing apparatus based on syntax preprocessing and a method thereof. In specific, the present disclosure parses syntaxes that can be parsed by rules and patterns without ambiguity by syntax parsing preprocessing, draws all possible syntax parsing results by applying syntax rules based on a result of syntax parsing preprocessing in which ambiguity is partially resolved, and resolves structural ambiguity by applying a statistic syntax parsing model learned from a syntax tree attachment learning corpus so as to reduce ambiguity in rule-based syntax parsing and to resolve ambiguity by a statistics-based scheme so that parsing correctness and processing efficiency in a syntax parsing method can be enhanced.Type: GrantFiled: February 28, 2017Date of Patent: May 15, 2018Assignee: SK PLANET CO., LTD.Inventors: Young Sook Hwang, Chang Hao Yin
-
Publication number: 20170169006Abstract: The present disclosure relates to a syntax parsing apparatus based on syntax preprocessing and a method thereof. In specific, the present disclosure parses syntaxes that can be parsed by rules and patterns without ambiguity by syntax parsing preprocessing, draws all possible syntax parsing results by applying syntax rules based on a result of syntax parsing preprocessing in which ambiguity is partially resolved, and resolves structural ambiguity by applying a statistic syntax parsing model learned from a syntax tree attachment learning corpus so as to reduce ambiguity in rule-based syntax parsing and to resolve ambiguity by a statistics-based scheme so that parsing correctness and processing efficiency in a syntax parsing method can be enhanced.Type: ApplicationFiled: February 28, 2017Publication date: June 15, 2017Inventors: Young Sook HWANG, Chang Hao YIN
-
Patent number: 9620112Abstract: The present disclosure relates to a syntax parsing apparatus based on syntax preprocessing and a method thereof. In specific, the present disclosure parses syntaxes that can be parsed by rules and patterns without ambiguity by syntax parsing preprocessing, draws all possible syntax parsing results by applying syntax rules based on a result of syntax parsing preprocessing in which ambiguity is partially resolved, and resolves structural ambiguity by applying a statistic syntax parsing model learned from a syntax tree attachment learning corpus so as to reduce ambiguity in rule-based syntax parsing and to resolve ambiguity by a statistics-based scheme so that parsing correctness and processing efficiency in a syntax parsing method can be enhanced.Type: GrantFiled: August 30, 2013Date of Patent: April 11, 2017Assignee: SK PLANET CO., LTD.Inventors: Young Sook Hwang, Chang Hao Yin
-
Publication number: 20150142443Abstract: The present disclosure relates to a syntax parsing apparatus based on syntax preprocessing and a method thereof. In specific, the present disclosure parses syntaxes that can be parsed by rules and patterns without ambiguity by syntax parsing preprocessing, draws all possible syntax parsing results by applying syntax rules based on a result of syntax parsing preprocessing in which ambiguity is partially resolved, and resolves structural ambiguity by applying a statistic syntax parsing model learned from a syntax tree attachment learning corpus so as to reduce ambiguity in rule-based syntax parsing and to resolve ambiguity by a statistics-based scheme so that parsing correctness and processing efficiency in a syntax parsing method can be enhanced.Type: ApplicationFiled: August 30, 2013Publication date: May 21, 2015Inventors: Young Sook Hwang, Chang Hao Yin
-
Publication number: 20140303955Abstract: The present disclosure relates to an apparatus and a method for recognizing an idiomatic expression using phrase alignment of a bilingual parallel corpus, and more particularly, to an apparatus and a method for recognizing an idiomatic expression using phrase alignment of a parallel corpus which extract a candidate idiomatic expression using phrase alignment information of a bilingual parallel corpus and measure an idiomatic expression index for every extracted candidate idiomatic expression to recognize the candidate idiomatic expression as an idiomatic expression to resolve errors in measuring a translational entropy of a word and extracting a representative translated word of the word and improve the accuracy of the idiomatic expression recognition.Type: ApplicationFiled: May 25, 2011Publication date: October 9, 2014Applicant: SK PLANET CO., LTD.Inventors: Sang-Bum Kim, Chang Hao Yin, Young Sook Hwang, Hae Chang Rim, Hyoung Gyu Lee
-
Patent number: 8818792Abstract: An apparatus and a method for constructing a verb phrase translation pattern using a bilingual parallel corpus. Each of the apparatus or method recognizes a predicate and an argument using a syntax analysis result and a word alignment result of a source sentence from a plurality of bilingual parallel corpus, extracts a translation pattern candidate and an occurrence frequency using the recognized predicate and argument, and then generates a basic verb phrase translation pattern by verifying the translation pattern candidate, and generalizes the generated basic verb phrase translation pattern to generate a general verb phrase pattern so as to be applied to various language pairs and minimize an error in the verb phrase translation pattern and determine an appropriate generalization level using a co-occurrence frequency of a predicate and an argument of the verb phrase translation pattern and a translation probability of the predicate.Type: GrantFiled: July 8, 2011Date of Patent: August 26, 2014Assignee: SK Planet Co., Ltd.Inventors: Young Sook Hwang, Sang-Bum Kim, Chang Hao Yin, Hae Chang Rim, Joo Young Lee
-
Publication number: 20140012564Abstract: Disclosed all an apparatus and a method for constructing a verb phrase translation pattern using a bilingual parallel corpus which recognizes a predicate and an argument using a syntax analysis result and a word alignment result of a source sentence from a plurality of bilingual parallel corpus, extracts a translation pattern candidate and an occurrence frequency using the recognized predicate and argument, and then generates a basic verb phrase translation pattern by verifying the translation pattern candidate, and generalizes the generated basic verb phrase translation pattern to generate a general verb phrase pattern so as to be applied to various language pairs and minimize an error in the verb phrase translation pattern and determine an appropriate generalization level using a co-occurrence frequency of a predicate and an argument of the verb phrase translation pattern and a translation probability of the predicate.Type: ApplicationFiled: July 8, 2011Publication date: January 9, 2014Applicant: SK PLANET CO., LTD.Inventors: Young Sook Hwang, Sang-Bum Kim, Chang Hao Yin, Hae Chang Rim, Joo Young Lee
-
Patent number: 8543376Abstract: Disclosed are a joint decoding apparatus and a joint decoding method that joins a tokenization process and a translation process. More particularly, the present disclosure can generate all available candidate tokens, reduce translation errors, and obtain an optimal translation result by jointly conducting a decoding by simultaneously conducting the tokenization process and the translation process for an input character sequence while decoding.Type: GrantFiled: May 25, 2011Date of Patent: September 24, 2013Assignee: SK Planet Co., LtdInventors: Young Sook Hwang, Sang-Bum Kim, Chang Hao Yin, Xinyan Xiao, Yang Liu, Qun Liu, Shouxun Lin
-
Publication number: 20130226556Abstract: The present invention relates to statistical machine translation, and provides a machine translation device and a machine translation method that acquire a creation probability for a target language from a single corpus while extracting respective conversion probabilities by extracting syntax conversion knowledge and word translation knowledge from a parallel corpus, model a weighted translation model by allowing each of the conversion knowledge and each of the probabilities to learn using a translation model learning device, and generate a target sentence through decoding processes of a syntax converter and a word translator by applying the translation model to a source sentence input in real time, thereby resolving disadvantages of the existing phrase-based SMT and syntax-based SMT and combining advantages thereof.Type: ApplicationFiled: July 20, 2011Publication date: August 29, 2013Applicant: SK Planet Co., Ltd.Inventors: Young Sook Hwang, Sang-Bum Kim, Chang Hao Yin, Yeon Su Lee, Seong Wook Lee, Hae Chang Rim
-
Publication number: 20130158975Abstract: The present invention relates to the use of a plurality of dependency trees in tree-based statistical machine translation and proposes a dependency forest to effectively process the plurality of dependency trees. The present invention can improve a translation capability by generating a translation rule and a dependency language model by using the dependency forest and applying the generated translation rule and dependency language model when a source language text is converted to a target language text.Type: ApplicationFiled: May 31, 2011Publication date: June 20, 2013Applicant: SK PLANET CO., LTD.Inventors: Young Sook Hwang, Sang-Bum Kim, Shouxun Lin, Zhaopeng Tu, Yang Liu, Qun Liu, Chang Hao Yin
-
Publication number: 20130132064Abstract: Disclosed are a joint decoding apparatus and a joint decoding method that joins a tokenization process and a translation process. More particularly, the present disclosure can generate all available candidate tokens, reduce translation errors, and obtain an optimal translation result by jointly conducting a decoding by simultaneously conducting the tokenization process and the translation process for an input character sequence while decoding.Type: ApplicationFiled: May 25, 2011Publication date: May 23, 2013Applicant: SK PLANET CO., LTD.Inventors: Young Sook Hwang, Sang-Bum Kim, Chang Hao Yin, Xinyan Xiao, Yang Liu, Qun Liu, Shouxun Lin
-
Publication number: 20130117010Abstract: Disclosure relates to a statistical machine translation field, and more particularly to a method and a device for filtering a translation rule and generating a target word in a hierarchical phrase-based statistical machine translation. The method and device filters a translation rule using a relaxed-well-formed dependency structure and generates a target word by referring to a head word of a source word in a hierarchical phrase-based statistical machine translation. The disclosure improves a translation performance while reducing a number of translation rules, in comparison with a hierarchical phrase-based original translation rule table.Type: ApplicationFiled: May 31, 2011Publication date: May 9, 2013Applicant: SK PLANET CO., LTD.Inventors: Young Sook Hwang, Sang-Bum Kim, Chang Hao Yin, Zhiyang Wang, Qun Liu, Yajuan Lv
-
Patent number: 8423346Abstract: Provided are a device and method for interactive machine translation. The device includes a machine translation engine having a morphological/syntactic analyzer for analyzing morphemes and sentences of an original text and generating original text analysis information, and a translation generator for generating a translation and translation generation information on the basis of the original text analysis information, and a user interface module for displaying sentence structures of the original text and the translation, and a relationship between the original text and the translation to a user on the basis of the original text analysis information and the translation generation information, and for receiving corrections to the original text or the translation from the user. The device and method provide a user interface whereby the user can effectively recognize and correct a mistranslated part and a cause of the mistranslation, and rapidly provides a re-translated result according to the correction.Type: GrantFiled: September 5, 2008Date of Patent: April 16, 2013Assignee: Electronics and Telecommunications Research InstituteInventors: Young Ae Seo, Chang Hyun Kim, Seong Il Yang, Young Sook Hwang, Chang Hao Yin, Eun Jin Park, Sung Kwon Choi, Ki Young Lee, Oh Woog Kwon, Yoon Hyung Roh, Young Kil Kim
-
Patent number: 8121829Abstract: The present invention relates to a method and apparatus for constructing translation knowledge to be used in a translator. According to the invention, a source-language sentence and a target-language sentence are converted by receiving the source-language sentence and the target-language sentence corresponding to the source-language sentence and attaching a prototype, a part-of-speech, relative position information, and syntactic information in a base phrase to each morpheme of the source-language sentence and the target-language sentence. Then, word alignment and syntactic alignment are performed in the converted source-language sentence and target-language sentence, thereby extracting translation knowledge on words and syntaxes, translation knowledge on a subcategory of a bilingual inflected-word, and translation knowledge on a bilingual sentence pattern based on the results of the word and syntactic alignment.Type: GrantFiled: May 29, 2008Date of Patent: February 21, 2012Assignee: Electronics and Telecommunications Research InstituteInventors: Young-Sook Hwang, Young Kil Kim, Sung Kwon Choi, Chang Hyun Kim, Young-Ae Seo, Ki Young Lee, Seong Il Yang, Yoon-Hyung Roh, Chang-Hao Yin, Oh Woog Kwon, Eun jin Park
-
Patent number: 8108202Abstract: Disclosed is a machine translation method for a PDF file.Type: GrantFiled: May 29, 2008Date of Patent: January 31, 2012Assignee: Electronics and Telecommunications Research InstituteInventors: Oh Woog Kwon, Sung Kwon Choi, Ki Young Lee, Yoon-Hyung Roh, Young Kil Kim, Chang Hyun Kim, Young-Ae Seo, Seong Il Yang, Young-Sook Hwang, Chang-Hao Yin, Eun jin Park
-
Publication number: 20090063128Abstract: Provided are a device and method for interactive machine translation. The device includes a machine translation engine having a morphological/syntactic analyzer for analyzing morphemes and sentences of an original text and generating original text analysis information, and a translation generator for generating a translation and translation generation information on the basis of the original text analysis information, and a user interface module for displaying sentence structures of the original text and the translation, and a relationship between the original text and the translation to a user on the basis of the original text analysis information and the translation generation information, and for receiving corrections to the original text or the translation from the user. The device and method provide a user interface whereby the user can effectively recognize and correct a mistranslated part and a cause of the mistranslation, and rapidly provides a re-translated result according to the correction.Type: ApplicationFiled: September 5, 2008Publication date: March 5, 2009Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Young Ae SEO, Chang Hyun Kim, Seong Il Yang, Young Sook Hwang, Chang Hao Yin, Eun Jin Park, Sung Kwon Choi, Ki Young Lee, Oh Woog Kwon, Yoon Hyung Roh, Young Kil Kim
-
Publication number: 20090043564Abstract: The present invention relates to a method and apparatus for constructing translation knowledge to be used in a translator. According to the invention, a source-language sentence and a target-language sentence are converted by receiving the source-language sentence and the target-language sentence corresponding to the source-language sentence and attaching a prototype, a part-of-speech, relative position information, and syntactic information in a base phrase to each morpheme of the source-language sentence and the target-language sentence. Then, word alignment and syntactic alignment are performed in the converted source-language sentence and target-language sentence, thereby extracting translation knowledge on words and syntaxes, translation knowledge on a subcategory of a bilingual inflected-word, and translation knowledge on a bilingual sentence pattern based on the results of the word and syntactic alignment.Type: ApplicationFiled: May 29, 2008Publication date: February 12, 2009Applicant: Electronics and Telecommunications Research InstituteInventors: Young-Sook Hwang, Young Kil Kim, Sung Kwon Choi, Chang Hyun Kim, Young-Ae Seo, Ki Young Lee, Seong Il Yang, Yoon-Hyung Roh, Chang-Hao Yin, Oh Woog Kwon, Eun Jin Park