Abstract: A method of retrieving a document according to an embodiment of the present application includes: acquiring a user retrieval query; calculating a user inquiry vector in a unit of sentence from the user retrieval query and acquiring a first document candidate group based on similarity between the calculated user inquiry vector and an embedding vector of a document stored in a retrieval database; acquiring a second document candidate group based on similarity between a text included in the user retrieval query and a text of the document stored in the retrieval database; and determining a summarization target document based on the first document candidate group and the second document candidate group.

Abstract: 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.

Abstract: A text data structuring apparatus according to the present invention includes: a data extraction unit which extracts text included in an image and position information of the text on the basis of OCR; a data processing unit which extracts line information included in the image by using the text, the position information, and the image; a labeling unit which labels the text as keys or values; and a relationship identification unit which acquires a mapping candidate group including first text, second text, and third text labeled on the basis of the line information, calculates a first similarity score representing meaning similarity between the first text and the third text and a second similarity score representing meaning similarity between the second text and the third text, and decides text to be mapped with the third text among of the first text and the second text.

Abstract: Aspects of the subject disclosure may include, systems and methods, for example, including receiving a user question data in a speech format or a text format, analyzing the user question data, selecting a plurality of documents from a plurality of domains corresponding to the user question data, searching for a plurality of passages including candidates for an answer value determined as being suitable for the user question data, in the plurality of documents, obtaining candidates by inputting the user question data and the plurality of passages into a plurality of MRC question and answer units, determining the answer value based on whether a reliability value of each of the candidates exceeds a threshold value, and providing the determined answer value to a user. Other embodiments are disclosed.

Abstract: Provided is an artificial intelligence (AI) answering system including a user question receiver configured to receive a user question from a user terminal; a first question extender configured to generate a question template by analyzing the user question and determine whether the user question and the generated question template match; a second question extender configured to generate a similar question template by using a natural language processing and a deep learning model when the user question and the generated question template do not match; a training data builder configured to generate training data for training the second question extender by using an neural machine translation (NMT) engine; and a question answering unit configured to transmit a user question result derived through the first question extender or the second question extender to the user terminal.

Abstract: A machine reading comprehension (MRC) question and answer providing method includes receiving a user question; analyzing the user question; selecting at least one document from at least one domain corresponding to an analyzed user question and searching for a passage, which is a candidate answer determined as being suitable for the user question, in the selected at least one document; obtaining at least one correct answer candidate value by inputting the user question and a corresponding passage into each of at least one MRC question and answer unit; and determining whether the at least one correct answer candidate value is a best answer.

Abstract: A method of generating a question-answer learning model through adversarial learning may include: sampling a latent variable based on constraints in an input passage; generating an answer based on the latent variable; generating a question based on the answer; and machine-learning the question-answer learning model using a dataset of the generated question and answer, wherein the constraints are controlled so that the latent variable is present in a data manifold while increasing a loss of the question-answer learning model.

Abstract: 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 using the embedding vector and calculating a first likelihood of each of at least one node included in the graph; a c step of generating a second likelihood by assigning a weight to the first likelihood according to a result of comparing at least one node included in the graph with the context; and a d step of calculating a third likelihood for all candidate paths present in the graph based on the second likelihood, selecting a path having a highest third likelihood, and generating a summary based on the path.

Abstract: Disclosed herein is a search method performed by a server, including: receiving a user question from a user terminal; generating a user question vector for the user question; selecting similar question candidates based on a similarity to the user question vector; generating an answer to the user question based on the similar question candidates; and transmitting the answer to the user question to the user terminal.

Abstract: An unstructured document analysis method according to an embodiment includes: operations of acquiring unstructured document data including font characteristic data and document structure data, extracting text included in the unstructured document data on the basis of the font characteristic data or the document structure data, classifying the extracted text into a pre-classified item using a trained neural network model, acquiring a content query related to the content included in the unstructured document data and associated with the pre-classified item, and generating an answer to the content query on the basis of the extracted text classified into the item.

Abstract: Provided are a device and method for converting a natural language query into a structured query language (SQL) query for a database search. The method includes an operation A of labeling natural language queries included in training data, an operation B of converting the natural language queries into second SQL queries by applying the natural language queries to an SQL conversion model, an operation C of verifying the second SQL queries, and an operation D of training the SQL conversion model by comparing the second SQL queries with third SQL queries corresponding to the natural language queries of the training data.

Abstract: Disclosed herein is a search method performed by a server, including: receiving a user question from a user terminal; generating a user question vector for the user question; selecting similar question candidates based on a similarity to the user question vector; generating an answer to the user question based on the similar question candidates; and transmitting the answer to the user question to the user terminal.

Abstract: A machine reading comprehension (MRC) question and answer providing method includes receiving a user question; analyzing the user question; selecting at least one document from at least one domain corresponding to an analyzed user question and searching for a passage, which is a candidate answer determined as being suitable for the user question, in the selected at least one document; obtaining at least one correct answer candidate value by inputting the user question and a corresponding passage into each of at least one MRC question and answer unit; and determining whether the at least one correct answer candidate value is a best answer.

Abstract: The present invention relates to an in-document search method and device for a query vector, and an object of the present invention is to improve the accuracy of a response by generating sentence data corresponding to data in a table form stored in database. The in-document search method for a query vector includes a step A of receiving a user query from a user terminal, a step B of generating a user query vector for the user query, a step C of extracting candidate table data based on the user query vector in a data storage module, a step D of searching for a response corresponding to the user query vector in the candidate table data, and a step E of providing the response to the user terminal.

Abstract: A machine reading comprehension (MRC) question and answer providing method includes receiving a user question; analyzing the user question; selecting at least one document from at least one domain corresponding to an analyzed user question and searching for a passage, which is a candidate answer determined as being suitable for the user question, in the selected at least one document; obtaining at least one correct answer candidate value by inputting the user question and a corresponding passage into each of at least one MRC question and answer unit; and determining whether the at least one correct answer candidate value is a best answer.

Abstract: Provided is an artificial intelligence (AI) answering system including a user question receiver configured to receive a user question from a user terminal; a first question extender configured to generate a question template by analyzing the user question and determine whether the user question and the generated question template match; a second question extender configured to generate a similar question template by using a natural language processing and a deep learning model when the user question and the generated question template do not match; a training data builder configured to generate training data for training the second question extender by using an neural machine translation (NMT) engine; and a question answering unit configured to transmit a user question result derived through the first question extender or the second question extender to the user terminal.

Abstract: Provided is a system for generating speech recognition training data, the system including: a speech data processing module receiving speech data from a user terminal and performing data preprocessing on the received speech data; an auto speech recognition (ASR) interfacing module transmitting the preprocessed speech data to a plurality of ASR engines and acquiring a confidence score and transcription data of the speech data from the plurality of ASR engines; an ASR result evaluating module determining whether the speech data and the transcription data match each other; and a training data managing unit generating training data as a pair of the speech data and the transcription data determined to match each other.

Abstract: Disclosed herein is a search method including: generating a user question vector for a user question using a paraphrase model learned using first learning data composed of a first pair of questions and a label indicating that the first pair of questions are similar to each other and second learning data composed of a second pair of questions and a label indicating that the second pair of questions are dissimilar to each other; selecting a similar question based on a similarity analysis result to the user question vector; and determining an answer to the similar question as an answer to the user question.

Abstract: A semantic triple-based knowledge extension system includes a data updater configured to update existing semantic triple data; a question generating module configured to generate a question by utilizing and combining entity synonyms and attribute synonyms; an actual question obtaining unit configured to obtain actual user questions based on user logs; a semantic triple extractor configured to select a relevant passage candidate group according to characteristics of the question and specify a search target, search for a passage relevant to the corresponding question, and derive a unique instant answer based on a retrieved passage and question data; and a semantic triple conversion module configured to convert a unique instant answer, which is a correct answer, and a question into the form of a semantic triple including an entity, an attribute, and an instant answer.

Abstract: A machine reading comprehension (MRC) question and answer providing method includes receiving a user question; analyzing the user question; selecting at least one document from at least one domain corresponding to an analyzed user question and searching for a passage, which is a candidate answer determined as being suitable for the user question, in the selected at least one document; obtaining at least one correct answer candidate value by inputting the user question and a corresponding passage into each of at least one MRC question and answer unit; and determining whether the at least one correct answer candidate value is a best answer.