# US 2020/0401771 A1 · Method and system of translating a source phrase in a first language into a target phrase in a second language > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401771 A1 - Document ID: US20200401771A1 - Status: Published application - Kind: A1 - Application number: 16/884,920 - Filed: 2020-05-27 - Published: 2020-12-24 - Earliest claimed: 2019-06-19 - Assignees: Yandex Europe AG - Applicants: Yandex Europe AG - Inventors: Anton Aleksandrovich DVORKOVICH; Ekaterina Vladimirovna ENIKEEVA - Web page: https://patentgrep.com/patent/US20200401771A1 ## CPC - G06F 40/45: Example-based machine translation; Alignment - G06F 40/58: Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation - G06F 40/30: Semantic analysis - G06F 40/47: Machine-assisted translation, e.g. using translation memory - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract There is disclosed a method and system for translating a source phrase in a first language into a second language. The method being executable by a device configured to access an index comprising a set of source sentences in the first language, and a set of target sentences in the second language, each of the target sentence corresponding to a translation of a given source sentence. The method comprises: acquiring the source phrase; generating by a translation algorithm, one or more target phrases, each of the one or more target phrases having a different semantic meaning within the second language; retrieving, from the index, a respective target sentence for each of the one or more target phrases, the respective target sentence comprising one of the one or more target phrases; and selecting each of the one or more target phrase and the respective target sentences for display. ## Claims ### Claim 1 A computer-implemented method for translating a source phrase in a first language into a second language, the method executable by a computer device, the computer device configured to access: an index, the index comprising a set of source sentences in the first language, and a set of target sentences in the second language, each of the target sentence included within the set of target sentences corresponding to a translation of a given source sentence within the set of source sentences; the method comprising: acquiring the source phrase; generating by a translation algorithm, one or more target phrases, each of the one or more target phrases having a different semantic meaning within the second language; retrieving, from the index, a respective target sentence for each of the one or more target phrases, the respective target sentence comprising one of the one or more target phrases; and selecting each of the one or more target phrase and the respective target sentences for display. ### Claim 2 (depends on 1) The method of claim 1, further comprising: retrieving, from the index, one or more source sentences in the first language, each of the one or more source sentences corresponding to the translation of each respective target sentences; and selecting, the one or more source sentences for display. ### Claim 3 (depends on 1) The method of claim 1, wherein the one or more target phrases comprises a first target phrase; the plurality of target sentences comprises a first sentence and a second sentence that includes the first target phrase; and wherein the retrieving the one or more target sentences comprises retrieving one of the first sentence and the second sentence. ### Claim 4 (depends on 3) The method of claim 3, wherein the retrieving one of the first sentence and the second sentence comprises: ranking, the first sentence and the second sentence; retrieving a highest ranked one of the first sentence and the second sentence as one of the one or more target sentences. ### Claim 5 (depends on 4) The method of claim 4, wherein the ranking the first sentence and the second sentence comprises: determining a first set of features associated with the first sentence, the first set of features being representative of a pertinence of the first sentence; determining a second set of features associated with the second sentence, the second set of features being representative of the pertinence of the second sentence; ranking the first sentence and the second sentence based on the first set of features and the second set of features. ### Claim 6 (depends on 5) The method of claim 5, wherein the first set of features include at least one of: a source of the first sentence; a number of words included within the first sentence; and a popularity parameter associated with the source. ### Claim 7 (depends on 1) The method of claim 1, wherein the index further comprises an indication of a source for each of the plurality of target sentences, the source being one of: a book; a website; and a video. ### Claim 8 (depends on 7) The method of claim 7, wherein the selecting the one or more target sentences and the one or more target phrases for display further comprises selecting a respective indication of the source of each of the one or more target sentences for display. ### Claim 9 (depends on 1) The method of claim 1, wherein: the computer device is a server coupled to a client device via a communication network; the acquiring the source phrase comprises receiving the source phrase from the client device; and wherein the selecting the one or more target sentences and the one or more target phrases for display comprises: transmitting the one or more target sentences and the one or more target phrases to the client device for display. ### Claim 10 A computer device for translating a source phrase in a first language into a second language, the computer device being configured to access: an index, the index comprising a set of source sentences in the first language, and a set of target sentences in the second language, each of the target sentence included within the set of target sentences corresponding to a translation of a given source sentence within the set of source sentences; the computer device comprising a processor configured to: acquire the source phrase; generate by a translation algorithm, one or more target phrases, each of the one or more target phrases having a different semantic meaning within the second language; retrieve, from the index, a respective target sentence for each of the one or more target phrases, the respective target sentence comprising one of the one or more target phrases; and select each of the one or more target phrase and the respective target sentences for display. ### Claim 11 (depends on 10) The computer device of claim 10, the processor being further configured to: retrieve, from the index, one or more source sentences in the first language, each of the one or more source sentences corresponding to the translation of each respective target sentences; and select, the one or more source sentences for display. ### Claim 12 (depends on 10) The computer device of claim 10, wherein the one or more target phrases comprises a first target phrase; the plurality of target sentences comprises a first sentence and a second sentence that includes the first target phrase; and wherein to retrieve the one or more target sentences, the processor is configured to retrieve one of the first sentence and the second sentence. ### Claim 13 (depends on 12) The computer device of claim 12, wherein to retrieve the one of the first sentence and the second sentence, the processor is configured to: rank, the first sentence and the second sentence; and retrieve a highest ranked one of the first sentence and the second sentence as one of the one or more target sentences. ### Claim 14 (depends on 13) The computer device of claim 13, wherein to rank the first sentence and the second sentence, the processor is configured to: determine a first set of features associated with the first sentence, the first set of features being representative of a pertinence of the first sentence; determine a second set of features associated with the second sentence, the second set of features being representative of the pertinence of the second sentence; rank the first sentence and the second sentence based on the first set of features and the second set of features. ### Claim 15 (depends on 14) The computer device of claim 14, wherein the first set of features include at least one of: a source of the first sentence; a number of words included within the first sentence; and a popularity parameter associated with the source. ### Claim 16 (depends on 10) The computer device of claim 10, wherein the index further comprises an indication of a source for each of the plurality of target sentences, the source being one of: a book; a website; and a video. ### Claim 17 (depends on 16) The computer device of claim 16, wherein to select the one or more target sentences and the one or more target phrases for display, the processor is further configured to select a respective indication of the source of each of the one or more target sentences for display. ### Claim 18 (depends on 10) The computer device of claim 10, wherein: the computer device is a server coupled to a client device via a communication network; to acquire the source phrase the processor is configured to receive the source phrase from the client device; and wherein to select the one or more target sentences and the one or more target phrases for display, the processor is configured to: transmit the one or more target sentences and the one or more target phrases to the client device for display.