FIELD: physics.
SUBSTANCE: invention relates to machine translation, in particular to a method and a server for performing problem-oriented translation. Method for performing machine problem-oriented translation of sentences from a first language into a second language, performed by a server running a neural network (NN), wherein the server has access to a problem-oriented dictionary containing problem-oriented translations of words from a first language into a second language. Method includes generating, by a server, an augmented sequence of input tokens based on an input sentence in a first language and a recommendation inserted into the input sentence; iterative formation using a neural network of a sequence of output tokens based on an augmented sequence of input tokens; generating a second sentence in a second language containing a problem-oriented translation of the input word using a sequence of output tokens.
EFFECT: providing execution of problem-oriented machine translation with proper quality and reduction of costs of computational resources.
18 cl, 10 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD AND SERVER FOR PERFORMING CONTEXT-SENSITIVE TRANSLATION | 2021 |
|
RU2812301C2 |
METHOD AND SERVER FOR PROCESSING TEXT SEQUENCE IN MACHINE PROCESSING TASK | 2020 |
|
RU2775820C2 |
METHOD AND SERVER FOR TRAINING MACHINE LEARNING ALGORITHM FOR TRANSLATION | 2020 |
|
RU2789796C2 |
METHOD AND SYSTEM FOR RECOGNIZING USER'S SPEECH FRAGMENT | 2021 |
|
RU2808582C2 |
MULTISTAGE TRAINING OF MACHINE LEARNING MODELS FOR RANKING SEARCH RESULTS | 2021 |
|
RU2824338C2 |
METHODS AND ELECTRONIC DEVICES FOR PACKAGING REQUESTS INTENDED FOR PROCESSING BY PROCESSING UNIT | 2021 |
|
RU2810916C2 |
METHOD AND SYSTEM FOR TRAINING CHATBOT SYSTEM | 2023 |
|
RU2820264C1 |
METHOD OF TRAINED RECURRENT NEURAL NETWORK DEBUGGING | 2019 |
|
RU2715024C1 |
SYSTEM AND METHOD FOR AUGMENTATION OF THE TRAINING SAMPLE FOR MACHINE LEARNING ALGORITHMS | 2020 |
|
RU2758683C2 |
METHOD AND SYSTEM FOR RANKING SET OF DOCUMENTS FROM SEARCH RESULT | 2021 |
|
RU2821294C2 |
Authors
Dates
2024-06-13—Published
2021-12-02—Filed