公开(公告)号：US20230069935A1

公开(公告)日：2023-03-09

申请号：US17777813

申请日：2019-11-20

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Hojin CHOI ,  Kyojoong OH ,  Youngjun LEE ,  Soohwan PARK

IPC: G06F40/30 ,  G06F40/247 ,  G06F40/268 ,  G06F40/295 ,  G06F16/332

Abstract: In a method of responding based on sentence paraphrase recognition for dialog system, main keywords of a domain and patterns thereof are recognized and extracted based on a morpheme analysis result in a pre-processing process. Question domains/sub-categories/dialogue-acts are classified using the morpheme analysis result and the extracted main keywords and patterns. Learning a model is performed using classification features of the classified question domains, sub-categories, and dialogue-acts as semantic features of query sentences, and sentence semantic vectors are extracted by measuring similarity between the vectors. A language model of letters is trained and similarity in expression and structure is analyzed by extracting a sentence expression vector based on the letter. An answer to a similar question is provided by generating a vector containing semantic and expressive information about an input query sentence based on analyzed semantic and expressive similarities, and finding a similar query sentence from FAQ knowledge using a paraphrase recognition technology. In a dialog system for automatic Q&A service such as a chatbot for customer consultation, it is possible to provide related answers by exploring question-and-answer knowledge (questions) that have similar meanings and intentions of input sentences (query) through paraphrase recognition technology.

公开(公告)号：US20230029759A1

公开(公告)日：2023-02-02

申请号：US17789088

申请日：2020-02-12

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Hojin CHOI ,  Youngjun LEE

IPC: G10L15/16 ,  G10L25/63

Abstract: A method of classifying emotions of utterances in a dialogue using word-level emotion embedding based on semi-supervised learning and a long short-term memory (LSTM) model includes embedding word-level emotion by tagging an emotion for each of words in utterances of input dialogue data with reference to a word-emotion association lexicon in which basic emotions are tagged for words for learning; extracting an emotion value of the utterances input; and classifying emotions of the utterances in consideration of change of emotion in the dialogue made in a messenger client, based on the LSTM model, using extracted emotion values of the utterances as input values of the LSTM model. The present invention can appropriately classify emotions by recognizing a change in emotion in a dialogue made in natural language.