Electronics and Telecommunications Research Institute

Eui Sok Chung

Jeon Gue Park

Hwa Jeon Song

Yun Keun Lee

Byung Ok Kang

Hyun Woo Kim

Ho Young Jung

Sung Joo Lee

Hoon Chung

Myung Gil Jang

Ji Hyun Wang

Jeom Ja Kang

Jong Jin Kim

Hyung Bae Jeon

Ki Young Park

Yoo Rhee Oh

Ho-Young Jung

Hyung-Bae Jeon

Ki-young Park

Yi Gyu Hwang

Ran Han

Byung Hyun Yoo

Soojung Lim

A knowledge increasing method includes calculating uncertainty of knowledge obtained from a neural network using an explicit memory, determining the insufficiency of the knowledge on the basis of the calculated uncertainty, obtaining additional data (learning data) for increasing insufficient knowledge, and training the neural network by using the additional data to autonomously increase knowledge.

Method and apparatus of increasing knowledge based on uncertainty in neural networks

Provided are sentence embedding method and apparatus based on subword embedding and skip-thoughts. To integrate skip-thought sentence embedding learning methodology with a subword embedding technique, a skip-thought sentence embedding learning method based on subword embedding and methodology for simultaneously learning subword embedding learning and skip-thought sentence embedding learning, that is, multitask learning methodology, are provided as methodology for applying intra-sentence contextual information to subword embedding in the case of subword embedding learning. This makes it possible to apply a sentence embedding approach to agglutinative languages such as Korean in a bag-of-words form. Also, skip-thought sentence embedding learning methodology is integrated with a subword embedding technique such that intra-sentence contextual information can be used in the case of subword embedding learning. A proposed model minimizes additional training parameters based on sentence embedding such that most training results may be accumulated in a subword embedding parameter.

Sentence embedding method and apparatus based on subword embedding and skip-thoughts

Provided are a neural network memory computing system and method. The neural network memory computing system includes a first processor configured to learn a sense-making process on the basis of sense-making multimodal training data stored in a database, receive multiple modalities, and output a sense-making result on the basis of results of the learning, and a second processor configured to generate a sense-making training set for the first processor to increase knowledge for learning a sense-making process and provide the generated sense-making training set to the first processor.

Neural network memory computing system and method

Provided is a method of automatically expanding input text. The method includes receiving input text composed of a plurality of documents, extracting a sentence pair that is present in different documents among the plurality of documents, setting the extracted sentence pair as an input of an encoder of a sequence-to-sequence model, setting an output of the encoder as an output of a decoder of the sequence-to-sequence model and generating a sentence corresponding to the input, and generating expanded text based on the generated sentence.

System and method for automatically expanding input text

A speech recognition apparatus based on a deep-neural-network (DNN) sound model includes a memory and a processor. As the processor executes a program stored in the memory, the processor generates sound-model state sets corresponding to a plurality of pieces of set training speech data included in multi-set training speech data, generates a multi-set state cluster from the sound-model state sets, and sets the multi-set training speech data as an input node and the multi-set state cluster as output nodes so as to learn a DNN structured parameter.

Apparatus and method for recognizing speech based on a deep-neural-network (DNN) sound model

Method of the present invention may include receiving speech feature vector converted from speech signal, performing first search by applying first language model to the received speech feature vector, and outputting word lattice and first acoustic score of the word lattice as continuous speech recognition result, outputting second acoustic score as phoneme recognition result by applying an acoustic model to the speech feature vector, comparing the first acoustic score of the continuous speech recognition result with the second acoustic score of the phoneme recognition result, outputting first language model weight when the first coustic score of the continuous speech recognition result is better than the second acoustic score of the phoneme recognition result and performing a second search by applying a second language model weight, which is the same as the output first language model, to the word lattice.

Method for estimating language model weight and system for the same

A method for separating a sound source from a mixed signal, includes Transforming a mixed signal to channel signals in frequency domain; and grouping several frequency bands for each channel signal to form frequency clusters. Further, the method for separating the sound source from the mixed signal includes separating the frequency clusters by applying a blind source separation to signals in frequency domain for each frequency cluster; and integrating the spectrums of the separated signal to restore the sound source in a time domain wherein each of the separated signals expresses one sound source.

Method for separating source signals and apparatus thereof

In a semi-automatic construction method for knowledge base of an encyclopedia question answering system, concept-oriented systematic templates are designed and important fact information related to entries is automatically extracted from summary information and body of the encyclopedia to semi-automatically construct the knowledge base of the encyclopedia question answering system. The method includes the steps of: (a) designing structure of the knowledge base with a plurality of templates for each entry and a plurality attributes related to each of the templates; (b) extracting structured information including the entry, an attribute name and attribute values from summary information of the encyclopedia; (c) extracting unstructured information including an attribute name and attribute values of the entry from a body of the encyclopedia; and (d) storing the structured information and the unstructured information in corresponding template and attribute of the knowledge base according to the entry.

Semi-automatic construction method for knowledge base of encyclopedia question answering system

An apparatus and a hybrid method for recognizing answer type are disclosed. The apparatus includes: a morpheme analyzer for analyzing morphemes of an input text; a syllabic answer type recognizer for extracting a predetermined size syllable from a morpheme list and recognizing an answer type based on the extracted syllable; a vocabulary feature recognizer for allocating feature to each morpheme and recognizing the feature; a vocabulary feature disambiguation unit for disambiguating vocabulary feature ambiguity of morphemes having more than one feature; a pattern rule answer type recognizer for recognizing an answer type by comparing a consecutive sequence of the morphemes and a consecutive sequence of constitutional features connected to the morphemes with a pre-constructed pattern rules; a statistic answer type recognizer for recognizing an answer type by implementing a statistic model; and an answer type sub-category recognizer for recognizing a sub-category of the recognized answer type classified to general category.

Growing community of inventors

Daejeon, South Korea

Eui Sok Chung