公开(公告)号：EP4009193A1

公开(公告)日：2022-06-08

申请号：EP20214578.5

申请日：2020-12-16

申请人： 42Maru Inc.

发明人： KIM, Dong Hwan ,  KIM, Han Su ,  JEONG, Woo Tae ,  LEE, Seung Hyeon ,  LIM, Chang Hyeon

IPC分类号： G06F16/34

摘要： The invention relates to a method and a system for improving performance of text summarization and has an object of improving performance of a technique for generating a summary from a given paragraph. According to the invention to achieve the object, a method for improving performance of text summarization includes: an a step of generating an embedding vector by vectorizing a natural language-based context; a b step of generating a graph by using the embedding vector; a c step of assigning a weight depending on whether or not a keyword corresponding to at least one node included in the graph is present in the context; and a d step of selecting a path having a highest likelihood in the graph and generating a summary based on the path.

公开(公告)号：EP4350532A1

公开(公告)日：2024-04-10

申请号：EP22204225.1

申请日：2022-10-27

申请人： 42Maru Inc.

发明人： KIM, Dong Hwan ,  JEONG, Woo Tae ,  KIM, Hyun Ok ,  PARK, Ju Shick ,  CHANG, Hyung Jin ,  SOHN, Ah Rim

IPC分类号： G06F16/383 ,  G06F16/34 ,  G06F16/93

摘要： According to an embodiment of the present application, a method of summarizing a document includes: extracting a summary target document based on a user search query; acquiring a trained document summary model; and inputting the summary target document to the trained document summary model, acquiring a first summary vector through a first output layer of the trained document summary model, and acquiring a summary sentence based on a generated summary based on the first summary vector, in which the document summary model is trained based on a training data set including an original document and generated summary correct answer information, acquires the original document through an input layer, and is trained to output output data approximating the generated summary correct answer information based on a difference between the output data output through the first output layer of the document summary model and the generated summary correct answer information.

公开(公告)号：EP4009250A1

公开(公告)日：2022-06-08

申请号：EP20213257.7

申请日：2020-12-11

申请人： 42Maru Inc.

发明人： KIM, Dong Hwan ,  KIM, Han Su ,  JEONG, Woo Tae ,  SUNG, Ki Bong ,  KIM, Hyeon Dey

IPC分类号： G06N20/00

摘要： The present invention relates to a method for reinforcing a multiple-choice QA model based on adversarial learning techniques, wherein incorrect answers are further generated based on a data set used in the process of training the multiple-choice QA model to enrich data which are learnable by the multiple-choice QA model. To achieve this object, the method includes step A of an incorrect answer generation model encoding a text based on natural language text and a question, generating a second incorrect answer based on the text and the question, and transmitting the second incorrect answer to an incorrect answer test model, step B of the incorrect answer test model encoding the text, the question, a first correct answer corresponding to the text and the question, a first incorrect answer and the second incorrect answer, and selecting a second correct answer based on results of the encoding, step C of the incorrect answer test model generating a feedback by determining whether the first correct answer is identical to the second correct answer, and step D of the incorrect answer generation model and the incorrect answer test model performing self-learning based on the feedback.