Electronics and Telecommunications Research Institute

Korea Institute of Machinery & Materials

Lg Electronics Inc.

Korea Institute of Science and Technology

Korea Research Institute of Chemical Technology

Young Kil Kim

Chang Hyun Kim

Ki Young Lee

Sung Kwon Choi

Oh Woog Kwon

Seong Il Yang

Sang Kyu Park

Young Ae Seo

Yoon Hyung Roh

Eun Jin Park

Yun Su Jin

Jinxia Huang

Ying Shun Wu

Young-Ae Seo

Yoon-Hyung Roh

Changhao Yin

Cheol Ryu

Jong Hun Shin

Young-Sook Hwang

Yun Keun Lee

Kwang Hee Son

Tae Sook Jeong

Sung U Kim

Song H Bok

Hang W Lee

Kong Hoon Lee

Mun Pyo Hong

Chang-Hao Yin

Yo Han Lee

Chang Hwan Lee

Jeong Mu Heo

Chang Jae Lee

Young Hwan Lee

Jung Ho Lee

Ki-Young Lee

Byung-Ik Choi

Seong Kyun Kim

Byoung Mog Kwon

Soojong Lim

Seok Ho Yoon

Jee W Lee

Yong K Kwon

Sang Jin Park

In-Seob Park

Young Sook Hwang

Yingshun Wu

Yu Chang Kim

Eunjin Park

Sang Keun Jung

Chang Hao Yin

Seung Il Yang

Seong Ii Yang

Seung Hoon Na

Munpyo Hong

Mun-Pyo Hong

Hye K Kwon

Jihee Ryu

Jin Seong

Provided is a method of generating a language model using crossmodal information. The method includes: receiving language-based first modality information and non-language-based second modality information; converting the first modality information into a first byte sequence; converting the second modality information into a second byte sequence; converting the first and second byte sequences into a first embedding vector and a second embedding vector by applying an embedding technique for each modality; generating semantic association information between first and second modality information by inputting the first and second embedding vectors to a crossmodal transformer; and learning the language model by setting the generated semantic association information as training data.

Method and apparatus for generating language model using crossmodal information

Provided is a method of constructing a neural network translation model. The method includes generating a first neural network translation model learning a feature of source domain data used in an unspecific field, generating a second neural network translation model learning a feature of target domain data used in a specific field, generating a third neural network translation model learning a common feature of the source domain data and the target domain data; and generating a combiner combining translation results of the first to third neural network translation models.

Apparatus and method of constructing neural network translation model

Provided are a method and apparatus for constructing a compact translation model that may be installed on a terminal on the basis of a pre-built reference model, in which a pre-built reference model is miniaturized through a parameter imitation learning and is efficiently compressed through a tree search structure imitation learning without degrading the translation performance. The compact translation model provides translation accuracy and speed in a terminal environment that is limited in network, memory, and computation performance.

Method and apparatus for constructing translation model installed on a terminal on the basis of a pre-built reference model

A real-time utterance verification system according to the present invention includes a speech recognition unit configured to recognize an utterance of an utterer, a memory configured to store a program for verifying the utterance of the utterer in real time, and a processor configured to execute the program stored in the memory, wherein, upon executing the program, the processor generates and stores a list of the utterance of the utterer, performs a semantic analysis on each utterance included in the list, and generates, when the utterance is determined to be an inappropriate utterance for a listener as a result of the semantic analysis, utterance restricting information corresponding to the inappropriate utterance.

Real-time utterance verification system and method thereof

The present invention relates to a device of simultaneous interpretation based on real-time extraction of an interpretation unit, the device including a voice recognition module configured to recognize voice units as sentence units or translation units from vocalized speech that is input in real time, a real-time interpretation unit extraction module configured to form one or more of the voice units into an interpretation unit, and a real-time interpretation module configured to perform an interpretation task for each interpretation unit formed by the real-time interpretation unit extraction module.

Device and method of simultaneous interpretation based on real-time extraction of interpretation unit

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.

Self-learning based dialogue apparatus and method for incremental dialogue knowledge

The present invention relates to a cartridge-type inline heater including: a heat exchanging unit including a body part in which a mounting part is formed in a longitudinal direction, and swirl parts coiled in a spiral along the longitudinal direction of the body part, and configured to induce a flowing-in working fluid to flow along the swirl parts; and a heater inserted in a longitudinal direction of the heat exchanging part to heat the working fluid which is in contact with the heat exchanging unit. Accordingly, the cartridge-type inline heater capable of heating the working fluid so as to have improved durability and uniform temperature distribution is provided.

Cartridge-type inline heater and system for controlling working fluid temperature using the same

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.

Spoken dialog system based on dual dialog management using hierarchical dialog task library

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.

Method for establishing paraphrasing data for machine translation system

A foreign language writing service method includes: recognizing, when a mixed text of foreign language portions and mother tongue portions is entered by a learner, the mother tongue portions from the mixed text; translating the mother tongue portions; combining a mother tongue translation result with the foreign language portions of the mixed text to generate a combined text; and providing the learner with the combined text of the mother tongue translation result and the foreign language portions of the mixed text.

Foreign language writing service method and system

The apparatus for osmotic power generation and desalination using a salinity difference includes: a first osmotic membrane reactor having a first salt water position space and a third salt water position space separated by a first forward osmotic membrane; a second osmotic membrane reactor having a second salt water position space and a draw solution position space separated by a second forward osmotic membrane; a high pressure pump connected between the second salt water position space and the third salt water position space; a desalination unit obtaining fresh water by separating a draw solute from a draw solution diluted through a transmission of water in salt water of the second salt water position space by way of the draw solution position space; and a turbine driven by flow force of salt water discharged from the third salt water position space to produce electric energy.

Apparatus for osmotic power generation and desalination using salinity difference

A user-interactive automatic translation device for a mobile device, includes: a camera image controller for converting an image captured by a camera into a digital image; an image character recognition controller for user-interactively selecting a character string region to be translated from the digital image, performing a character recognition function on the selected character string region based on an optical character reader (OCR) function and character recognition information to generate a text string; and user-interactively correcting errors included in the text string. Further, the user-interactive automatic translation device includes a text transmission controller for transmitting the error-corrected text string; and an automatic translation controller for receiving the error-corrected text string from the text transmission controller, performing a morpheme analysis, tagging, a structure analysis, a structure conversion, and a vocabulary conversion on the text string to generate a translation of the text string based on a grammar of a target language.

User-interactive automatic translation device and method for mobile device

A post-editing apparatus for correcting translation errors, includes: a translation error search unit for estimating translation errors using an error-specific language model suitable for a type of error desired to be estimated from translation result obtained using a translation system, and determining an order of correction of the translation errors; and a corrected word candidate generator for sequentially generating error-corrected word candidates for respective estimated translation errors on a basis of analysis of an original text of the translation system. The post-editing apparatus further includes a corrected word selector for selecting a final corrected word from among the error-corrected word candidates by using the error-specific language model suitable for the type of error desired to be corrected, and incorporating the final corrected word in the translation result, thus correcting the translation errors.

Post-editing apparatus and method for correcting translation errors

A dual modem device includes a first processor to communicate with a first network and a second processor to communicate with a second network. The first processor includes a USB module to transceive a signal with a computer side using a universal serial bus (USB) interface, a first packet control block to determine a type of the signal transceived via the USB module and to decide a communication path, and a first function block to process a signal associated with the first network. The second processor includes a first control block to process a control signal for the first processor, a second control block to process a control signal for the second processor, and a second function block to process a signal associated with the second network.

Dual modem device and controlling method thereof

A hybrid translation apparatus includes a source language input unit for generalizing an input source language sentence for each node; a statistics-based translation knowledge database(DB) for storing learning data generalized for each node to be acquired; a first translation result generating unit for transforming the source language sentence generalized for each node into a node expression using the statistics-based translation knowledge to generate a first translation result; and a second translation result generating unit for repeatedly performing the generation of a target word for each node on the first translation result using pattern-based knowledge to generate a second translation result as target words for the respective nodes. Further, the hybrid translation apparatus includes a pattern-based translation knowledge DB for using in the pattern-based translation; and a translation result combining unit for combining the first translation result and the second translation result to output a target language sentence.

Hybrid translation apparatus and method thereof

Growing community of inventors

Daejeon, South Korea

Young Kil Kim