Samsung Electronics Co., Ltd.

Sogang University Research & Commercialization Foundation

Sogang University Research Foundation

Hyundai Motor Company

Kia Motors Corporation

Sogang University Research Business Development Foundation

Kangwon National University University-industry Cooperation Foundation

Industry-university Cooperation Foundation Sogang University

Jung Yun Seo

Young Hee Park

Kwang Choon Kim

Myeong Gi Jeong

Choong Nyoung Seon

Myoung-Wan Koo

Youngmin Park

Jeong-Eom Lee

Seona Kim

Sang Woo Kang

Hark Soo Kim

Yeong Kil Song

Byoungjae Kim

Hyeok Ju Ahn

Maeng Sik Choi

A communication terminal and a method of providing a unified natural language interface to the same are disclosed. The method includes: determining, when text information containing many characters is created, whether the text information conforms to one of preset grammatical constraints; extracting, when the text information conforms to one of the grammatical constraints, tokens of one or more of characters from the text information, and extracting, when the text information does not conform to one of the grammatical constraints, one or more characters having an attribute probability higher than a reference probability as a token; and analyzing the extracted tokens to determine a function to handle the extracted tokens, and executing the determined function based on the extracted tokens.

Communication terminal and method of providing unified interface to the same

A dialogue system includes: a storage configured to store a parameter tree including at least one parameter used for performing an action; a speech input device configured to receive speech from a user; an input processor configured to apply a natural language understanding algorithm to the received speech to generate a speech recognition result; a dialogue manager configured to determine an action corresponding to the received speech based on the speech recognition result, to retrieve a parameter tree corresponding to the action from the storage, and to determine additional information needed to perform the action based on the retrieved parameter tree; and a result processor configured to generate a dialogue response for requesting the additional information.

Dialogue system and dialogue processing method

Provided is a voice conversation method using a bi-directional LSTM (Bi-LSTM) memory network. The voice conversation method includes steps of: performing bi-directional LSTM processing on history sentences to generate first sentence embedding and second sentence embedding; performing bi-directional LSTM processing on a question sentence to generate question sentence embedding; inputting the first sentence embedding and the question sentence embedding to an input memory of a memory network and inputting the second sentence embedding into an output memory of the memory network; generating a weight matrix representing relevance between the first sentence embedding of the input memory and the question sentence embedding, performing weighted sum of the weight matrix and the second sentence embedding of the output memory to generate output information, adding the output information and the question sentence embedding to obtain prediction information, and outputting the prediction information; and selecting an answer sentence by using the prediction information.

Voice conversation method and system with enhanced word features

Provided is a speech recognition method using machine learning, including: receiving a speech signal as an input, performing speech recognition to generate speech recognition result information including multiple candidate sentences and ranks of the respective candidate sentences; processing the multiple candidate sentences included in the speech recognition result information according to a machine learning model which is learned in advance and changing the ranks of the multiple candidate sentences to re-rank the multiple candidate sentences; and selecting the highest-rank candidate sentence among the re-ranked multiple candidate sentences as a speech recognition result. Particularly, the machine learning model is generated by: receiving the speech signal and a correct answer sentence as inputs; generating the speech recognition result information and a correct answer set; generating learning data by using the correct answer set; and performing the machine learning of changing the ranks of the candidate sentences.

Method for reranking speech recognition results

Growing community of inventors

Seoul, South Korea

Jung Yun Seo