METHOD AND SYSTEM FOR TRANSLATING SOURCE SENTENCE IN FIRST LANGUAGE BY TARGET SENTENCE IN SECOND LANGUAGE Russian patent published in 2019 - IPC G06F17/28 G06N3/02 

Abstract RU 2692049 C1

FIELD: computer equipment.

SUBSTANCE: invention relates to the computer equipment. Method of translating a source sentence in a first language into a target sentence in a second language, which is implemented on a computer, includes: receiving an original sentence; generating a first translation hypothesis using a first translation model; generating a second translation hypothesis using a second translation model; assigning by first classifier a first evaluation value for first translation hypothesis, wherein the first estimate value is the probability that the first translation hypothesis corresponds to semantically illogical or logical translation into the second language and the first classifier is trained to determine a first estimate value based on analysis of the data triad: source sentence, first translation hypothesis; second translation hypothesis; designation by the second classifier of the second estimation value for the first translation hypothesis, wherein the second estimation value is a difference in the quality of the translation between the first translation hypothesis and the second translation hypothesis and the second classifier is trained to determine the second estimate value based on the data triad analysis; formation of target proposal.

EFFECT: providing source sentence translation by target request.

20 cl, 8 dwg

Similar patents RU2692049C1

Title Year Author Number
TRAINING CLASSIFIERS USED TO EXTRACT INFORMATION FROM NATURAL LANGUAGE TEXTS 2018
  • Matskevich Stepan Evgenevich
  • Bulgakov Ilya Aleksandrovich
RU2691855C1
CLASSIFIER TRAINING USED FOR EXTRACTING INFORMATION FROM TEXTS IN NATURAL LANGUAGE 2018
  • Matskevich Stepan Evgenevich
  • Bulgakov Ilya Aleksandrovich
RU2681356C1
CLASSIFICATION OF TEXTS ON NATURAL LANGUAGE BASED ON SEMANTIC SIGNS 2016
  • Kolotienko Sergej Sergeevich
  • Anisimovich Konstantin Vladimirovich
  • Myakutin Andrej Valerevich
  • Indenbom Evgenij Mikhajlovich
RU2628436C1
MULTI STAGE RECOGNITION OF THE REPRESENT ESSENTIALS IN TEXTS ON THE NATURAL LANGUAGE ON THE BASIS OF MORPHOLOGICAL AND SEMANTIC SIGNS 2016
  • Anisimovich Konstantin Vladimirovich
  • Indenbom Evgeny Mihaylovich
  • Novitskiy Valery Igorevich
RU2619193C1
NEURAL NETWORK FOR INTERPRETING NATURAL LANGUAGE SENTENCES 2018
  • Molin Mikhail Nikolaevich
  • Perskij Georgij Mikhajlovich
RU2699396C1
METHOD FOR AUTOMATED EXTRACTION OF SEMANTIC COMPONENTS FROM COMPOUND SENTENCES OF NATURAL LANGUAGE TEXTS IN MACHINE TRANSLATION SYSTEMS AND DEVICE FOR ITS IMPLEMENTATION 2021
  • Karpov Anton Gennadevich
  • Khachukaev Eduard Magomedovich
  • Khachukaeva Elina Eduardovna
RU2766060C1
METHOD AND SYSTEM FOR COMPARISON OF INITIAL LEXICAL ELEMENT OF FIRST LANGUAGE WITH TARGET LEXICAL ELEMENT OF SECOND LANGUAGE 2016
  • Zelenkov Yurij Grigorevich
RU2682002C2
METHOD OF EXTRACTING FACTS FROM TEXTS ON NATURAL LANGUAGE 2016
  • Starostin Anatolij Sergeevich
  • Smurov Ivan Mikhajlovich
  • Dzhumaev Stanislav Sergeevich
RU2637992C1
RESOLUTION OF SEMANTIC AMBIGUITY USING LANGUAGE-INDEPENDENT SEMANTIC STRUCTURE 2013
  • Zuev Konstantin Alekseevich
  • Bogdanova Daria Nikolaevna
RU2579699C2
LINGUISTICALLY INFORMED STATISTIC MODELS OF STRUCTURE OF COMPONENTS FOR ORDERING IN REALISATION OF SENTENCES FOR SYSTEM OF NATURAL LANGUAGE GENERATION 2004
  • Ringger Ehrik
  • Gejmon Majkl
  • Smets Martin
  • Korston-Oliver Sajmon
  • Mur Robert K.
RU2336552C2

RU 2 692 049 C1

Authors

Gubanov Sergey Dmitrievich

Dvorkovich Anton Aleksandrovich

Kovarsky Boris Andreevich

Nokel Mikhail Alekseevich

Noskov Aleksey Anatolievich

Frolov Anton Viktorovich

Dates

2019-06-19Published

2017-12-29Filed