FIELD: computer engineering.
SUBSTANCE: invention relates to computer engineering. Computer-aided method of verifying the content of a snippet from a plurality of snippets includes determining, for the snippet in question, at least one other snippet from the plurality of snippets providing a context for the snippet in question; formation of target vector for the considered snippet; generating for at least one other context vector snippet; providing a target vector and a context vector of a natural language processing model to determine a probability value indicating whether the content of at least one other snippet confirms the accuracy of the content of the snippet in question; determining by the server that the content facts of the considered snippet are accurate if the probability value is not less than the probability threshold value.
EFFECT: providing more reliable cards of search objects.
20 cl, 7 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD AND SERVER FOR TEACHING A NEURAL NETWORK TO FORM A TEXT OUTPUT SEQUENCE | 2020 |
|
RU2798362C2 |
METHOD AND SYSTEM FOR RECOGNIZING USER'S SPEECH FRAGMENT | 2021 |
|
RU2808582C2 |
METHOD OF ESTABLISHING TRAINING OBJECT FOR TRAINING MACHINE TRAINING ALGORITHM | 2016 |
|
RU2637883C1 |
METHOD AND SERVER FOR REPEATED TRAINING OF MACHINE LEARNING ALGORITHM | 2019 |
|
RU2743932C2 |
METHOD AND SYSTEM FOR GENERATING AN OBJECT CARD | 2018 |
|
RU2739554C1 |
METHOD AND SYSTEM FOR STORING MULTIPLE DOCUMENTS | 2018 |
|
RU2744028C2 |
SYSTEM AND METHOD OF FORMING TRAINING SET FOR MACHINE LEARNING ALGORITHM | 2018 |
|
RU2744029C1 |
METHOD AND SYSTEM FOR TRAINING CHATBOT SYSTEM | 2023 |
|
RU2820264C1 |
METHOD AND A COMPUTER DEVICE FOR SELECTING A CURRENT CONTEXT-DEPENDENT RESPONSE FOR THE CURRENT USER REQUEST | 2017 |
|
RU2693332C1 |
TRAINING METHOD OF RATING MODULE USING THE TRAINING SELECTION WITH THE INTERFERENCE LABELS | 2016 |
|
RU2632143C1 |
Authors
Dates
2024-03-25—Published
2022-07-05—Filed