CN113836947B - Method, device, equipment and storage medium for translating terms after machine translation - Google Patents
Method, device, equipment and storage medium for translating terms after machine translation Download PDFInfo
- Publication number
- CN113836947B CN113836947B CN202110938432.7A CN202110938432A CN113836947B CN 113836947 B CN113836947 B CN 113836947B CN 202110938432 A CN202110938432 A CN 202110938432A CN 113836947 B CN113836947 B CN 113836947B
- Authority
- CN
- China
- Prior art keywords
- term
- translation
- text
- original text
- original
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013519 translation Methods 0.000 title claims abstract description 350
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000014616 translation Effects 0.000 claims abstract description 349
- 238000012545 processing Methods 0.000 claims description 29
- 230000015654 memory Effects 0.000 claims description 15
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 9
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
- G06F40/45—Example-based machine translation; Alignment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The present disclosure provides a method of translating terms after machine translation, comprising the steps of: creating a first term library and a second term library for the original text; the method comprises the steps of storing terms with one-to-one original translation relation in an original text into a first term library, and storing terms with one-to-many original translation relation in the original text into a second term library; performing machine translation on the original text to generate translated text and original translation alignment information; based on the original translation alignment information, replacing one-to-one term translations in the translated text with term translations in the first term library by using the first term library; based on the original translation alignment information and based on a first operation instruction of a user, at least one-to-many term original text in the original text is indicated by using a second term library, and indication information is generated. The disclosure also provides a machine translated term translation device, an electronic device and a storage medium.
Description
Technical Field
The disclosure relates to a method, a device, equipment and a storage medium for translating terms after machine translation, and belongs to the technical field of translation.
Background
Although the machine translation quality of the neural network is greatly improved compared with the rules and the statistical machine translation quality, the manual translation intervention correction is still needed when translating the content with high precision requirements, especially the content in the professional field and the like.
The machine translation post-editing gradually becomes an important translation mode, so that the translation efficiency is greatly improved, and the translation accuracy is ensured. However, the content edited after translation generally has high requirements, and accurate translation is required, and particularly, how to translate the terms in the translated content accurately and efficiently is always an important problem in the field of translation.
There are two kinds of term translation in the prior art, one is based on machine translation, and in the process of purely automatic machine translation of text and documents, a term library is designated in advance, so that terms in a translation result are output according to the interpretation in the term library. The other is that in the editor interface of the auxiliary translation software, when translating the corresponding sentence, the hit term in the sentence and the term table is actively or automatically queried and prompted to the translator.
Based on the term translation of machine translation, the term replacement of a purely automatic translation process can be realized, but the term cannot be added again in the auxiliary translation or post-translation editing process.
Based on the term prompt of the auxiliary translation software, when the translator translates to related content, related terms in the term library can be automatically queried and prompted, but the related terms cannot be automatically replaced, and the translator needs to manually select and execute replacement operation. In the case of a large number of terms, there is a problem of inefficiency in translating a large number of terms.
In the term library, there are often cases that one term original corresponds to a plurality of term translations, and when a term is replaced, there are cases that it cannot be judged which term translation the replacement is, because only one term can be reserved, and there may be cases that a replacement error occurs, so that the translation is inaccurate. Under the condition of multi-person collaboration, terms added by the collaboration members cannot be mutually referred to, so that the version of the term translation contributed by the collaboration members is lost and resources are wasted.
Disclosure of Invention
To solve at least one of the above technical problems, the present disclosure provides a machine translated term translation method, apparatus, device, and storage medium.
The method, the device, the equipment and the storage medium for translating the translated terms through the machine are realized through the following technical schemes.
According to one aspect of the present disclosure, there is provided a machine translated term translation method including the steps of: s1, creating a first term library and a second term library for original text; s2, storing the terms with one-to-one original translation relations in the original text into the first term library, and storing the terms with one-to-many original translation relations in the original text into the second term library; s3, performing machine translation on the original text to generate translated text and original text translation alignment information; s4, replacing one-to-one term translations in the translated text with term translations in the first term library by using the first term library based on the original term translation alignment information; and based on the original translation alignment information, indicating at least one-to-many term original text in the original text by using the second term library, and generating indication information. Preferably, the second term library is used for indicating the one-to-many term original text in the original text, indicating the term translation in the machine translation text and generating prompt information of the one-to-many term translation based on the original translation alignment information. Exemplary operating scenario: automatically indicating (e.g., highlighting, changing color, etc.) all of the one-to-many term originals in the original text, the term translations in the machine translation to which all of the one-to-many term originals correspond are also indicated (e.g., highlighting, changing color, etc.), and also generating: and prompting information of the one-to-many term translations corresponding to all the one-to-many term originals (for example, a plurality of term translations in the second term library corresponding to each term origin are prompted in a prompting frame mode, and one term origin and a plurality of term translations are displayed in the prompting frame).
Preferably, when the term translation method is used for the text after the machine translation is cooperatively processed by a plurality of translators, the identity information of each translator is also acquired, the identity information of each translator comprises a translation level, the translator above the threshold level can add and modify the term pairs of the first term base and the second term base, the translator below the threshold level cannot modify the term pairs of the first term base but can add the term pairs, and when the translator below the threshold level tries to modify the term pairs in the first term base, the target term pairs which are tried to be modified are automatically backed up to the second term base.
The machine translated term translation method according to at least one embodiment of the present disclosure, alternatively, step S4 is: based on the original translation alignment information, replacing one-to-one term translations in the translated text with term translations in the first term library by using the first term library; and based on the original text translation alignment information and a first operation instruction of a user, indicating the one-to-many term original text in the original text by using the second term library, and generating indication information. Preferably, the second term library is used for indicating the one-to-many term original text in the original text, indicating the term translation in the machine translation text and generating prompt information of the one-to-many term translation based on the original translation alignment information. Exemplary operating scenario: when the user's cursor is positioned on a paragraph in the text of the text, all of the one-to-many term text within the paragraph is indicated (e.g., highlighted, discoloured, etc.), the term translation in the machine translation paragraph that is aligned with the paragraph is also indicated (e.g., highlighted, discoloured, etc.), and also generates: the prompt information of the one-to-many term translations corresponding to the indicated one-to-many term origin (for example, the multiple term translations in the second term library corresponding to each term origin are prompted in a prompt box manner, and one term origin and multiple term translations are displayed in the prompt box).
According to the machine translated term translation method of at least one embodiment of the present disclosure, in step S1, a first term library and a second term library are created for an original text, including: a first term library and a second term library are created for the textual text using the corpus.
According to the machine translated term translation method of at least one embodiment of the present disclosure, the first term library is converted into a first dictionary and the second term library is converted into a second dictionary before step S4.
According to the machine translated term translation method of at least one embodiment of the present disclosure, the first operation instruction of the user is a cursor position instruction.
The machine translated term translation method according to at least one embodiment of the present disclosure further includes: s5, receiving a second operation instruction of a user, storing a target word original text in an original text operated by the second operation instruction and a target word translation corresponding to the target word original text into the first term library or the second term library, and updating the first term library or the second term library; and S6, searching all target word originals in the original text based on the target word originals stored in the first term library, and replacing word translations aligned with the target word originals in the translated text by using the target word translations based on the original translation alignment information.
The machine translated term translation method according to at least one embodiment of the present disclosure, alternatively, step S6 is: and searching all target word originals in the original text based on the target word originals stored in the first term library, generating prompt information, and replacing the word translations aligned to the target word originals in the translated text by the target word translations based on the prompt information.
According to the machine translated term translation method of at least one embodiment of the present disclosure, in step S5, the target term originals in the original text operated by the second operation instruction stored in the first term library and the target term translations corresponding to the target term originals are also stored in the second term library and the second term library is updated.
The second operation instruction is a selected instruction according to a machine translated term translation method of at least one embodiment of the present disclosure.
According to another aspect of the present disclosure, there is provided a machine translated term translation method including the steps of: SS1, creating a first term library and a second term library for original text; SS2, storing the terms with one-to-one original translation relations in the original text into the first term library, and storing the terms with one-to-many original translation relations in the original text into the second term library; SS3, performing machine translation on the original text to generate translated text and original text translation alignment information; SS4, splitting the original text into at least two original text sub-texts, and taking each original text sub-text and each translated text aligned with the original text sub-text as an original text translated text group to be isolated; and SS5, based on the original translation alignment information, replacing one-to-one term translations in the translated sub-text with term translations in the first term library by using the first term library; and based on the original text translation alignment information, indicating at least one-to-many term original text in the original text by using the second term library, and generating indication information. Preferably, the second term library is used for indicating the one-to-many term original text in the original text, indicating the term translation in the machine translation text and generating prompt information of the one-to-many term translation based on the original translation alignment information. Exemplary operating scenario: automatically indicating (e.g., highlighting, changing color, etc.) all of the one-to-many term originals in the original text, the term translations in the machine translation to which all of the one-to-many term originals correspond are also indicated (e.g., highlighting, changing color, etc.), and also generating: and prompting information of the one-to-many term translations corresponding to all the one-to-many term originals (for example, a plurality of term translations in the second term library corresponding to each term origin are prompted in a prompting frame mode, and one term origin and a plurality of term translations are displayed in the prompting frame).
The machine translated term translation method according to at least one embodiment of the present disclosure, alternatively, step SS5 is: based on the original translation alignment information, replacing one-to-one term translations in the translated sub-text with term translations in the first term library by using the first term library; and based on the original text translation alignment information and a first operation instruction of a user, at least indicating the one-to-many term original text in the original text sub-text by using the second term library, and generating indication information. Preferably, the second term library is used for indicating the one-to-many term original text in the original text, indicating the term translation in the machine translation text and generating prompt information of the one-to-many term translation based on the original translation alignment information. Exemplary operating scenario: when the user's cursor is positioned on a paragraph in the text of the text, all of the one-to-many term text within the paragraph is indicated (e.g., highlighted, discoloured, etc.), the term translation in the machine translation paragraph that is aligned with the paragraph is also indicated (e.g., highlighted, discoloured, etc.), and also generates: the prompt information of the one-to-many term translations corresponding to the indicated one-to-many term origin (for example, the multiple term translations in the second term library corresponding to each term origin are prompted in a prompt box manner, and one term origin and multiple term translations are displayed in the prompt box).
The machine translated term translation method according to at least one embodiment of the present disclosure further includes: SS6, receiving a second operation instruction of a user, storing a target word original text in an original text sub-text operated by the second operation instruction and a target word translation corresponding to the target word original text into the first term library or the second term library, and updating the first term library or the second term library; and SS7, searching all target word originals in the original text operated by the second operation instruction based on the target word originals stored in the first term library, and replacing word translations aligned with the target word originals in the original text operated by the second operation instruction by using the target word translations based on the original translation alignment information.
The machine translated term translation method according to at least one embodiment of the present disclosure, alternatively, step SS7 is: and searching all target word originals in the original text sub-texts operated by the second operation instruction based on the target word originals stored in the first term library, generating prompt information, and enabling word translations aligned with the target word originals in the translated text sub-texts aligned with the original text sub-texts operated by the second operation instruction to be replaced by the target word translations based on the prompt information.
According to the machine translated term translation method of at least one embodiment of the present disclosure, in step SS6, the target term origin in the origin sub-text operated by the second operation instruction stored in the first term base and the target term translation corresponding to the target term origin are also stored in the second term base and the second term base is updated.
According to still another aspect of the present disclosure, there is provided a machine-translated term translation apparatus including: the term library creation module creates a first term library and a second term library for the original text, so as to store the terms with one-to-one original translation relationship in the original text into the first term library, and store the terms with one-to-many original translation relationship in the original text into the second term library; the machine translation module is used for carrying out machine translation on the original text to generate translated text; the alignment module performs word alignment on the original text and the translated text to generate original translation alignment information; the processing module uses the first term library to replace one-to-one term translations in the translated text with term translations in the first term library based on the original translation alignment information; and based on the original translation alignment information, indicating at least one-to-many term original text in the original text by using the second term library, and generating indication information.
According to the machine translated term translation device of at least one embodiment of the present disclosure, alternatively, the processing module replaces a one-to-one term translation in the translated text with a term translation in the first term library using the first term library based on the original term alignment information; and based on the original text translation alignment information and a first operation instruction of a user, at least indicating one-to-many term original text in the original text by using the second term library, and generating indication information.
The term library creation module creates a first term library and a second term library for original text according to a machine translated term translation device of at least one embodiment of the present disclosure, including: a first term library and a second term library are created for the textual text using the corpus.
The machine-translated term translation device according to at least one embodiment of the present disclosure further includes a conversion module that converts the first term library into a first dictionary and converts the second term library into a second dictionary.
The machine translated term translation device according to at least one embodiment of the present disclosure further includes: the operation instruction receiving module receives a second operation instruction of a user, and the processing module stores a target word original text in an original text operated by the second operation instruction and a target word translation corresponding to the target word original text into the first term library or the second term library and updates the first term library or the second term library; the processing module searches all target word originals in the original text based on the target word originals stored in the first term library, and replaces word translations aligned with the target word originals in the translated text with the target word translations based on the original translation alignment information.
According to the machine translated term translation device of at least one embodiment of the present disclosure, alternatively, the processing module searches all target term originals in the original text based on the target term originals stored to the first term library, and generates prompt information; based on the hint information, a word translation in the translation text that is aligned with the target word translation can be replaced with the target word translation based on a replacement instruction received by the operation instruction receiving module.
According to the machine translated term translation device of at least one embodiment of the present disclosure, the processing module further stores the target term origin in the original text operated by the second operation instruction stored in the first term base and the target term translation corresponding to the target term origin into the second term base and updates the second term base.
According to still another aspect of the present disclosure, there is provided a machine translated term translation apparatus including: the term library creation module creates a first term library and a second term library for the original text, so as to store the terms with one-to-one original translation relationship in the original text into the first term library, and store the terms with one-to-many original translation relationship in the original text into the second term library; the machine translation module is used for carrying out machine translation on the original text to generate translated text; the alignment module performs word alignment on the original text and the translated text to generate original translation alignment information; the splitting module splits the original text into at least two original text sub-texts, so that each original text sub-text and each translated text aligned with the original text sub-text are used as an original text translated text sub-text group to be isolated; the processing module uses the first term library to replace one-to-one term translations in the translated sub-text with term translations in the first term library based on the original translation alignment information; and based on the original text translation alignment information, indicating at least one-to-many term original text in the original text by using the second term library, and generating indication information.
According to the machine translated term translation device of at least one embodiment of the present disclosure, alternatively, the processing module replaces a one-to-one term translation in the translated sub-text with a term translation in the first term library using the first term library based on the original term alignment information; and based on the original text translation alignment information and a first operation instruction of a user, at least indicating the one-to-many term original text in the original text sub-text by using the second term library, and generating indication information.
The machine translated term translation device according to at least one embodiment of the present disclosure further includes: the operation instruction receiving module receives a second operation instruction of a user, and the processing module stores a target word original text in an original text sub-text operated by the second operation instruction and a target word translation corresponding to the target word original text into the first term library or the second term library and updates the first term library or the second term library; and the processing module searches all target word originals in the original text operated by the second operation instruction based on the target word originals stored in the first term base, and replaces word translations aligned with the target word originals in the original text operated by the second operation instruction based on the original translation alignment information.
According to the machine translated term translation device of at least one embodiment of the present disclosure, alternatively, the processing module searches all target term originals in the original text sub-text operated by the second operation instruction based on the target term originals stored to the first term library, generates hint information based on which a term translation aligned with the target term originals in the translated text sub-text aligned with the original text operated by the second operation instruction can be replaced by the target term translation based on a replacement instruction received by the operation instruction receiving module.
According to the machine translated term translation device of at least one embodiment of the present disclosure, the processing module further stores the target term text in the text sub-text operated by the second operation instruction stored in the first term library and the target term translation corresponding to the target term text into the second term library and updates the second term library.
According to still another aspect of the present disclosure, there is provided an electronic apparatus including: a memory storing execution instructions; and a processor executing the memory-stored execution instructions, causing the processor to perform the method of any one of the above.
According to yet another aspect of the present disclosure, there is provided a readable storage medium having stored therein execution instructions which when executed by a processor are adapted to carry out the method of any one of the above.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the disclosure and together with the description serve to explain the principles of the disclosure.
FIG. 1 is a flow diagram of a machine translated term translation method of one embodiment of the present disclosure.
Fig. 2 is a flow diagram of a machine translated term translation method according to yet another embodiment of the present disclosure.
Fig. 3 is a flow diagram of a machine translated term translation method according to yet another embodiment of the present disclosure.
Fig. 4 is a flow diagram of a machine translated term translation method according to yet another embodiment of the present disclosure.
Fig. 5 is a block diagram schematically illustrating the structure of a machine translated term translation device according to an embodiment of the present disclosure.
Fig. 6 is a block diagram schematically illustrating the structure of a machine translated term translation apparatus according to still another embodiment of the present disclosure.
Fig. 7 is a block diagram schematically illustrating the structure of a machine translated term translation apparatus according to still another embodiment of the present disclosure.
Fig. 8 is a block diagram schematically illustrating the structure of a machine translated term translation apparatus according to still another embodiment of the present disclosure.
Fig. 9 is a block diagram schematically illustrating a structure of an electronic device according to an embodiment of the present disclosure.
Description of the reference numerals
100 machine translated term translating device
101 term library creation module
102 machine translation module
103 alignment module
104 processing module
105 conversion module
106 operation instruction receiving module
107 split module
1000 communication interface
2000 memory
3000 processor.
Detailed Description
The present disclosure is described in further detail below with reference to the drawings and the embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant content and not limiting of the present disclosure. It should be further noted that, for convenience of description, only a portion relevant to the present disclosure is shown in the drawings.
In addition, embodiments of the present disclosure and features of the embodiments may be combined with each other without conflict. The technical aspects of the present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Unless otherwise indicated, the exemplary implementations/embodiments shown are to be understood as providing exemplary features of various details of some ways in which the technical concepts of the present disclosure may be practiced. Thus, unless otherwise indicated, features of the various implementations/embodiments may be additionally combined, separated, interchanged, and/or rearranged without departing from the technical concepts of the present disclosure.
The use of cross-hatching and/or shading in the drawings is typically used to clarify the boundaries between adjacent components. As such, the presence or absence of cross-hatching or shading does not convey or represent any preference or requirement for a particular material, material property, dimension, proportion, commonality between illustrated components, and/or any other characteristic, attribute, property, etc. of a component, unless indicated. In addition, in the drawings, the size and relative sizes of elements may be exaggerated for clarity and/or descriptive purposes. While the exemplary embodiments may be variously implemented, the specific process sequences may be performed in a different order than that described. For example, two consecutively described processes may be performed substantially simultaneously or in reverse order from that described. Moreover, like reference numerals designate like parts.
When an element is referred to as being "on" or "over", "connected to" or "coupled to" another element, it can be directly on, connected or coupled to the other element or intervening elements may be present. However, when an element is referred to as being "directly on," "directly connected to," or "directly coupled to" another element, there are no intervening elements present. For this reason, the term "connected" may refer to physical connections, electrical connections, and the like, with or without intermediate components.
For descriptive purposes, the present disclosure may use spatially relative terms such as "under … …," under … …, "" under … …, "" lower, "" above … …, "" upper, "" above … …, "" higher "and" side (e.g., as in "sidewall"), etc., to describe one component's relationship to another (other) component as illustrated in the figures. In addition to the orientations depicted in the drawings, the spatially relative terms are intended to encompass different orientations of the device in use, operation, and/or manufacture. For example, if the device in the figures is turned over, elements described as "under" or "beneath" other elements or features would then be oriented "over" the other elements or features. Thus, the exemplary term "below" … … can encompass both an orientation of "above" and "below". Furthermore, the device may be otherwise positioned (e.g., rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, when the terms "comprises" and/or "comprising," and variations thereof, are used in the present specification, the presence of stated features, integers, steps, operations, elements, components, and/or groups thereof is described, but the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof is not precluded. It is also noted that, as used herein, the terms "substantially," "about," and other similar terms are used as approximation terms and not as degree terms, and as such, are used to explain the inherent deviations of measured, calculated, and/or provided values that would be recognized by one of ordinary skill in the art.
FIG. 1 is a machine translated term translation method of one embodiment of the present disclosure. As shown in fig. 1, the term translation method after machine translation includes the steps of: s1, creating a first term library and a second term library for original text; s2, storing the terms with one-to-one original translation relations in the original text into a first term library, and storing the terms with one-to-many original translation relations in the original text into a second term library; s3, performing machine translation on the original text to generate translated text and original translation alignment information; s4, based on the original translation alignment information, replacing one-to-one term translations in the translated text with term translations in the first term library by using the first term library; and indicating the one-to-many term original text in the original text by using a second term library based on the original text translation alignment information, and generating indication information.
Fig. 2 is a machine translated term translation method of yet another embodiment of the present disclosure. As shown in fig. 2, the term translation method after machine translation includes the steps of: s1, creating a first term library and a second term library for original text; s2, storing the terms with one-to-one original translation relations in the original text into a first term library, and storing the terms with one-to-many original translation relations in the original text into a second term library; s3, performing machine translation on the original text to generate translated text and original translation alignment information; s4, replacing one-to-one term translations in the translated text with term translations in the first term library by using the first term library based on the original term translation alignment information; based on the original translation alignment information and based on a first operation instruction of a user, at least one-to-many term original text in the original text is indicated by using a second term library, and indication information is generated.
In each of the above embodiments, in step S1, creating a first term library and a second term library for the original text includes: a first term library and a second term library are created for the textual text using the corpus.
Wherein the corpus can be the corpus in the prior art.
In the above embodiments, before step S4, the first term library is converted into the first dictionary, and the second term library is converted into the second dictionary.
Preferably, based on the original translation alignment information, a one-to-one term translation in the translated text is replaced with a term translation in the first dictionary using the first dictionary; and indicating the one-to-many term original text in the original text by using a second dictionary based on the original text translation alignment information, and generating indication information.
Preferably, based on the original translation alignment information, a one-to-one term translation in the translated text is replaced with a term translation in the first dictionary using the first dictionary; based on the original text translation alignment information, based on a first operation instruction of a user, indicating at least one-to-many term original text in the original text by using a second dictionary, and generating indication information.
The first operation instruction of the user may be a cursor position instruction.
For the above indication information, for example, according to the cursor position of the user, whether the original text (i.e. the text to be translated) has terms in the second term library, if any, the terms in the original text may be displayed (for example, a side bar of an editor of the web page translation system is used as a term indication), or the terms may be highlighted, color-changed and so on.
Preferably, in each of the above embodiments, the method further includes: s5, receiving a second operation instruction of a user, storing a target word original text in an original text operated by the second operation instruction and a target word translation corresponding to the target word original text into a first term library or a second term library, and updating the first term library or the second term library; and S6, searching all target word origins in the original text based on the target word origins stored in the first term library, and replacing word translations aligned with the target word origins in the translated text by using the target word translations based on the original translation alignment information.
Through step S5, it is possible to implement that the user adds a term translation to a term original in an original text in real time, adds the term original and the term translation to the first term library if the added term translation is one-to-one, and adds the term original and the term translations to the second term library if the added term translation is one-to-many (one term original corresponds to a plurality of term translations).
Preferably, in each of the above embodiments, alternatively, step S6 is: searching all target word originals in the original text based on the target word originals stored in the first term library, generating prompt information, and replacing the word translations aligned with the target word originals in the translated text by the target word translations based on the prompt information.
The prompt information is, for example, a popup window including a term original text frame and a term translated text frame.
Preferably, in step S5, the target term text in the text of the text operated by the second operation instruction stored in the first term library and the target term translation corresponding to the target term text are also stored in the second term library and the second term library is updated.
Preferably, in the above embodiment, the second operation instruction is a selected instruction.
FIG. 3 is a machine translated term translation method of yet another embodiment of the present disclosure, including the steps of: SS1, creating a first term library and a second term library for original text; SS2, storing the terms with one-to-one original translation relation in the original text into a first term library, and storing the terms with one-to-many original translation relation in the original text into a second term library; SS3, performing machine translation on the original text to generate translated text and original text translation alignment information; SS4, splitting the original text into at least two original text sub-texts, and taking each original text sub-text and each translated text aligned with the original text sub-text as an original text translated text group to be isolated; and SS5, based on the original translation alignment information, replacing one-to-one term translations in the translated sub-text with term translations in the first term library by using the first term library; and indicating the one-to-many term original text in the original text sub-text by using a second term library based on the original text translation alignment information, and generating indication information.
FIG. 4 is a machine translated term translation method of yet another embodiment of the present disclosure, including the steps of: SS1, creating a first term library and a second term library for original text; SS2, storing the terms with one-to-one original translation relation in the original text into a first term library, and storing the terms with one-to-many original translation relation in the original text into a second term library; SS3, performing machine translation on the original text to generate translated text and original text translation alignment information; SS4, splitting the original text into at least two original text sub-texts, and taking each original text sub-text and each translated text aligned with the original text sub-text as an original text translated text group to be isolated; step SS5, based on the original translation alignment information, replacing one-to-one term translations in the translated sub-text with term translations in the first term library by using the first term library; based on the original text translation alignment information and based on a first operation instruction of a user, at least one-to-many term original text in the original text is indicated by using a second term library, and indication information is generated.
In the above embodiment, preferably, the method further includes: SS6, receiving a second operation instruction of a user, storing a target word original text in an original text sub-text operated by the second operation instruction and a target word translation corresponding to the target word original text into a first term library or a second term library, and updating the first term library or the second term library; and SS7, searching all target word originals in the original text operated by the second operation instruction based on the target word originals stored in the first term library, and replacing word translations aligned with the target word originals in the original text operated by the second operation instruction by using the target word translations based on the original translation alignment information.
In the above embodiment, preferably, alternatively, step SS7 is: and searching all target word originals in the original text operated by the second operation instruction based on the target word originals stored in the first term library, generating prompt information, and replacing the word translations aligned with the target word originals in the translated text aligned with the original text operated by the second operation instruction by the target word translations based on the prompt information.
In the above embodiment, preferably, in step SS6, the target term text in the text sub-text operated by the second operation instruction stored in the first term library and the target term translation corresponding to the target term text are also stored in the second term library and updated in the second term library.
The above embodiment may be implemented:
when an original text is split into at least two original sub-texts (at least two co-workers make machine translated edits), if a term pair (original translated term pair) added by a certain co-worker and a term pair in a first term library exist in a case of one word multi-translation, the term pair in the first term library is replaced by a term pair added last by the co-worker according to the addition time sequence, and the replaced term pair is stored in a second term library.
When a certain collaboration member adds a term pair in a first term library, the term pair is also added in a second term library to prompt other collaboration members, so that a plurality of collaboration members can independently replace the terms in the original text with authority, and the added term pair can refer to the prompt mutually.
According to a preferred embodiment of the present disclosure, when a plurality of translators cooperatively process machine translation text, identity information of each translator is also acquired, and the identity information of each translator includes translation level information. The translation level information may be generated based on information such as certificate information, translation word number information, and translation accuracy uploaded to the system by the translator.
The translators of different translation levels are given different rights, for example, a translator above a threshold level can add and modify a term pair of a first term library, a term pair of a second term library can also be added and modified, a translator below the threshold level cannot modify a term pair of the first term library, but can add that when a translator below the threshold level tries to modify a term pair in the first term library, the target term pair that is tried to be modified is automatically backed up to the second term library. For example, the translation level includes a high-level, a medium-level and a primary, a high-level translator can add and modify a term pair of a first term base, and also add and modify a term pair of a second term base, the medium-level and primary translator cannot modify the term pair of the first term base, and when the medium-level or primary translator tries to modify the term pair of the first term base, the target term pair tried to be modified is automatically backed up to the second term base. For example, in an attempt to modify "apple-apple" in the first term library to "apple-fruit", the first term library still retains "apple-apple" and "apple-fruit" is backed up to the second term library.
Fig. 5 is a block diagram schematically illustrating the structure of a machine translated term translation device 100 according to an embodiment of the present disclosure.
As shown in fig. 5, the term translation apparatus 100 includes: the term library creation module 101, the term library creation module 101 creates a first term library and a second term library for the original text to store the one-to-one term of the original translation relationship in the original text to the first term library, and stores the one-to-many term of the original translation relationship in the original text to the second term library; the machine translation module 102, the machine translation module 102 carries out machine translation on the original text to generate translated text; the alignment module 103 performs word alignment on the original text and the translated text by the alignment module 103 to generate original translation alignment information; and a processing module 104, wherein the processing module 104 uses the first term library to replace one-to-one term translations in the translated text with term translations in the first term library based on the original translation alignment information; and indicating the one-to-many term original text in the original text by using a second term library based on the original text translation alignment information, and generating indication information.
Preferably, the processing module 104 uses the first term library to replace a one-to-one term translation in the translated text with a term translation in the first term library based on the original translation alignment information; based on the original translation alignment information and based on a first operation instruction of a user, at least one-to-many term original text in the original text is indicated by using a second term library, and indication information is generated.
Preferably, the term library creating module 101 creates a first term library and a second term library for the original text, including: a first term library and a second term library are created for the textual text using the corpus.
Fig. 6 is a block diagram schematically illustrating the structure of a machine translated term translation device 100 according to an embodiment of the present disclosure.
As shown in fig. 6, the term translation device 100 further includes a conversion module 105, and the conversion module 105 converts the first term library into a first dictionary and converts the second term library into a second dictionary.
Fig. 7 is a block diagram schematically illustrating the structure of a machine translated term translation device 100 according to an embodiment of the present disclosure.
As shown in fig. 7, the term translation device 100 further includes an operation instruction receiving module 106, where the operation instruction receiving module 106 receives a second operation instruction of a user, and the processing module 104 stores a target term original text in the original text operated by the second operation instruction and a target term translation corresponding to the target term original text into the first term library or the second term library, and updates the first term library or the second term library; the processing module 104 searches for all target term origins in the original text based on the target term origins stored to the first term library, and replaces word translations aligned with the target term origins in the translated text with the target term translations based on the original translation alignment information.
Preferably, the processing module 104 searches for all target word origins in the original text based on the target word origins stored to the first term library, and generates the prompt information; based on the hint information, the word translations in the translation text that are aligned with the target word originals can be replaced with the target word translations based on the replacement instructions received via the operating instruction receiving module 106.
Preferably, the processing module 104 further stores the target term text and the target term translation corresponding to the target term text in the text of the text operated by the second operation instruction stored in the first term library into the second term library and updates the second term library.
Fig. 8 is a block diagram schematically illustrating the structure of a machine translated term translation device 100 according to an embodiment of the present disclosure.
As shown in fig. 8, the machine-translated term translating apparatus 100 includes: the term library creation module 101, the term library creation module 101 creates a first term library and a second term library for the original text to store the one-to-one term of the original translation relationship in the original text to the first term library, and stores the one-to-many term of the original translation relationship in the original text to the second term library; the machine translation module 102, the machine translation module 102 carries out machine translation on the original text to generate translated text; the alignment module 103 performs word alignment on the original text and the translated text by the alignment module 103 to generate original translation alignment information; the splitting module 107, the splitting module 107 splits the original text into at least two original text sub-texts, so that each original text sub-text and each translated text aligned with the original text sub-text are used as an original text translated text sub-text group to be isolated; and a processing module 104, wherein the processing module 104 uses the first term library to replace one-to-one term translations in the translated sub-text with term translations in the first term library based on the original translation alignment information; and indicating the one-to-many term original text in the original text sub-text by using a second term library based on the original text translation alignment information, and generating indication information.
Preferably, the processing module 104 uses the first term library to replace the one-to-one term translation in the translated sub-text with the term translation in the first term library based on the original translation alignment information; based on the original text translation alignment information and based on a first operation instruction of a user, at least one-to-many term original text in the original text is indicated by using a second term library, and indication information is generated.
Preferably, the term translation apparatus 100 further comprises: the operation instruction receiving module 106, the operation instruction receiving module 106 receives a second operation instruction of the user, the processing module 104 stores the target word original text in the original text sub-text operated by the second operation instruction and the target word translation corresponding to the target word original text into the first term library or the second term library, and updates the first term library or the second term library; and the processing module 104 searches all target word originals in the original text operated by the second operation instruction based on the target word originals stored in the first term library, and replaces word translations aligned with the target word originals in the original text operated by the second operation instruction with the target word translations based on the original translation alignment information.
Preferably, alternatively, the processing module 104 searches all the target word originals in the original text sub-text operated by the second operation instruction based on the target word originals stored in the first term library, generates the hint information, and based on the hint information, the word translations aligned with the target word originals in the translated text sub-text aligned with the original text operated by the second operation instruction can be replaced by the target word translations based on the replacement instruction received by the operation instruction receiving module 106.
Preferably, the processing module 104 further stores the target term text stored in the text sub-text operated by the second operation instruction in the first term library and the target term translation corresponding to the target term text in the second term library and updates the second term library.
The present disclosure also provides an electronic device, as shown in fig. 9, including: a communication interface 1000, a memory 2000 and a processor 3000. The communication interface 1000 is used for communicating with external devices for data interactive transmission. A computer program executable on the processor 3000 is stored in the memory 2000. The processor 3000 implements the method in the above embodiment when executing the computer program. The number of memories 2000 and processors 3000 may be one or more.
The memory 2000 may include a high-speed RAM memory or may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory.
If the communication interface 1000, the memory 2000 and the processor 3000 are implemented independently, the communication interface 1000, the memory 2000 and the processor 3000 may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture (ISA, industry Standard Architecture) bus, a peripheral component interconnect (PCI, peripheral Component) bus, or an extended industry standard architecture (EISA, extended Industry Standard Component) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in the figure, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the communication interface 1000, the memory 2000, and the processor 3000 are integrated on a chip, the communication interface 1000, the memory 2000, and the processor 3000 may perform communication with each other through internal interfaces.
In the description of the present specification, reference to the terms "one embodiment/manner," "some embodiments/manner," "example," "specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/manner or example is included in at least one embodiment/manner or example of the present application. In this specification, the schematic representations of the above terms are not necessarily for the same embodiment/manner or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/modes or examples described in this specification and the features of the various embodiments/modes or examples can be combined and combined by persons skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" is at least two, such as two, three, etc., unless explicitly defined otherwise.
It will be appreciated by those skilled in the art that the above-described embodiments are merely for clarity of illustration of the disclosure, and are not intended to limit the scope of the disclosure. Other variations or modifications will be apparent to persons skilled in the art from the foregoing disclosure, and such variations or modifications are intended to be within the scope of the present disclosure.
Claims (5)
1. A method of machine translating translated terms comprising the steps of:
s1, creating a first term library and a second term library for original text;
s2, storing the terms with one-to-one original translation relations in the original text into the first term library, and storing the terms with one-to-many original translation relations in the original text into the second term library;
S3, performing machine translation on the original text to generate translated text and original text translation alignment information;
s4, based on the original translation alignment information, replacing one-to-one term translations in the translation text with term translations in the first term library by using the first term library; based on the original text translation alignment information and based on a first operation instruction of a user, indicating at least one-to-many term original text in the original text by using the second term library, and generating indication information;
s5, receiving a second operation instruction of a user, storing a target word original text in an original text operated by the second operation instruction and a target word translation corresponding to the target word original text into the first term library or the second term library, and updating the first term library or the second term library; and
s6, searching all target word origins in the original text based on the target word origins stored in the first term library, and replacing word translations aligned with the target word origins in the translated text by using the target word translations based on the original translation alignment information;
when the term translation method is used for the text after machine translation in a cooperative processing mode of a plurality of translators, identity information of each translator is also acquired, the identity information of each translator comprises a translation level, the translators above the threshold level can add and modify term pairs of a first term base and a second term base, the translators below the threshold level cannot modify the term pairs of the first term base but can add the term pairs, and when the translators below the threshold level try to modify the term pairs in the first term base, the target term pairs which are tried to be modified are automatically backed up to the second term base.
2. The machine-translated term translation method according to claim 1, wherein in step S5, the target term origin in the original text operated by the second operation instruction stored in the first term base and the target term translation corresponding to the target term origin are also stored in the second term base and the second term base is updated.
3. A method of machine translating translated terms comprising the steps of:
SS1, creating a first term library and a second term library for original text;
SS2, storing the terms with one-to-one original translation relations in the original text into the first term library, and storing the terms with one-to-many original translation relations in the original text into the second term library;
SS3, performing machine translation on the original text to generate translated text and original text translation alignment information;
SS4, splitting the original text into at least two original text sub-texts, and taking each original text sub-text and each translated text aligned with the original text sub-text as an original text translated text group to be isolated;
SS5, based on the original translation alignment information, replacing one-to-one term translations in the translated sub-text with term translations in the first term library by using the first term library; based on the original text translation alignment information and based on a first operation instruction of a user, indicating at least one-to-many term original text in the original text sub-text by using the second term library, and generating indication information;
SS6, receiving a second operation instruction of a user, storing a target word original text in an original text sub-text operated by the second operation instruction and a target word translation corresponding to the target word original text into the first term library or the second term library, and updating the first term library or the second term library; and
SS7, searching all target word originals in the original text operated by the second operation instruction based on the target word originals stored in the first term library, and replacing word translations aligned with the target word originals in the original text operated by the second operation instruction with the target word translations based on the original translation alignment information;
when the term translation method is used for the text after machine translation in a cooperative processing mode of a plurality of translators, identity information of each translator is also acquired, the identity information of each translator comprises a translation level, the translators above the threshold level can add and modify term pairs of a first term base and a second term base, the translators below the threshold level cannot modify the term pairs of the first term base but can add the term pairs, and when the translators below the threshold level try to modify the term pairs in the first term base, the target term pairs which are tried to be modified are automatically backed up to the second term base.
4. An electronic device, comprising:
a memory storing execution instructions; and
a processor executing the memory-stored execution instructions, causing the processor to perform the method of any one of claims 1 to 3.
5. A readable storage medium having stored therein execution instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110938432.7A CN113836947B (en) | 2020-10-14 | 2020-11-20 | Method, device, equipment and storage medium for translating terms after machine translation |
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020110981396 | 2020-10-14 | ||
| CN202011098139 | 2020-10-14 | ||
| CN202110938432.7A CN113836947B (en) | 2020-10-14 | 2020-11-20 | Method, device, equipment and storage medium for translating terms after machine translation |
| CN202011305042.8A CN112364669B (en) | 2020-10-14 | 2020-11-20 | Method, device, equipment and storage medium for translating translated terms by machine translation |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011305042.8A Division CN112364669B (en) | 2020-10-14 | 2020-11-20 | Method, device, equipment and storage medium for translating translated terms by machine translation |
Publications (3)
| Publication Number | Publication Date |
|---|---|
| CN113836947A CN113836947A (en) | 2021-12-24 |
| CN113836947A8 CN113836947A8 (en) | 2024-01-16 |
| CN113836947B true CN113836947B (en) | 2024-04-16 |
Family
ID=74532924
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011305042.8A Active CN112364669B (en) | 2020-10-14 | 2020-11-20 | Method, device, equipment and storage medium for translating translated terms by machine translation |
| CN202110938432.7A Active CN113836947B (en) | 2020-10-14 | 2020-11-20 | Method, device, equipment and storage medium for translating terms after machine translation |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011305042.8A Active CN112364669B (en) | 2020-10-14 | 2020-11-20 | Method, device, equipment and storage medium for translating translated terms by machine translation |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN112364669B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112364669B (en) * | 2020-10-14 | 2021-09-03 | 北京中科凡语科技有限公司 | Method, device, equipment and storage medium for translating translated terms by machine translation |
| CN113935339B (en) * | 2021-08-31 | 2023-05-23 | 北京百度网讯科技有限公司 | Translation method, translation device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010182261A (en) * | 2009-02-09 | 2010-08-19 | Toshiba Corp | Bilingual information forming device, mechanical translation device and program |
| CN109902314A (en) * | 2019-04-18 | 2019-06-18 | 中译语通科技股份有限公司 | A kind of interpretation method and device of term |
| CN110543644A (en) * | 2019-09-04 | 2019-12-06 | 语联网（武汉）信息技术有限公司 | Machine translation method and device containing term translation and electronic equipment |
| CN111144137A (en) * | 2019-12-17 | 2020-05-12 | 语联网（武汉）信息技术有限公司 | Method and device for generating edited model corpus after machine translation |
| CN112364669A (en) * | 2020-10-14 | 2021-02-12 | 北京中科凡语科技有限公司 | Method, device, equipment and storage medium for translating translated terms by machine translation |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7020601B1 (en) * | 1998-05-04 | 2006-03-28 | Trados Incorporated | Method and apparatus for processing source information based on source placeable elements |
| WO2011146934A2 (en) * | 2010-05-21 | 2011-11-24 | Western Standard Publishing Company, Inc. | Apparatus, system, and method for computer aided translation |
| US9405532B1 (en) * | 2013-03-06 | 2016-08-02 | NetSuite Inc. | Integrated cloud platform translation system |
| CN103455477B (en) * | 2013-09-09 | 2016-04-06 | 高晋愚 | A kind of term unified approach for supplementary translation |
| JP6226321B2 (en) * | 2013-10-23 | 2017-11-08 | 株式会社サン・フレア | Translation support system, translation support system server, translation support system client, translation support system control method, and program thereof |
| US9619464B2 (en) * | 2013-10-28 | 2017-04-11 | Smartcat Ltd. | Networked language translation system and method |
| US9817808B2 (en) * | 2014-09-29 | 2017-11-14 | International Business Machines Corporation | Translation using related term pairs |
| CN104298663B (en) * | 2014-09-30 | 2017-01-18 | 中国科学院计算技术研究所 | Method and device for translation consistency and statistical machine translation method and system |
| CN104750820A (en) * | 2015-04-24 | 2015-07-01 | 中译语通科技（北京）有限公司 | Filtering method and device for corpuses |
| US9558182B1 (en) * | 2016-01-08 | 2017-01-31 | International Business Machines Corporation | Smart terminology marker system for a language translation system |
| CN106250375A (en) * | 2016-08-09 | 2016-12-21 | 北京百度网讯科技有限公司 | Translation processing method and device |
| CN108549645A (en) * | 2018-04-17 | 2018-09-18 | 郑州航空工业管理学院 | A kind of system and method for realizing Chinese-English translation of webpage |
| CN109299480B (en) * | 2018-09-04 | 2023-11-07 | 上海传神翻译服务有限公司 | Context-based term translation method and device |
| CN110489762B (en) * | 2019-06-26 | 2023-07-04 | 中译语通科技股份有限公司 | Term translation method, storage medium and device based on neural network machine translation |
| CN110674871B (en) * | 2019-09-24 | 2023-04-07 | 北京中科凡语科技有限公司 | Translation-oriented automatic scoring method and automatic scoring system |
| CN111597826B (en) * | 2020-05-15 | 2021-10-01 | 苏州七星天专利运营管理有限责任公司 | Method for processing terms in auxiliary translation |
| CN111652006B (en) * | 2020-06-09 | 2021-02-09 | 北京中科凡语科技有限公司 | Computer-aided translation method and device |
-
2020
- 2020-11-20 CN CN202011305042.8A patent/CN112364669B/en active Active
- 2020-11-20 CN CN202110938432.7A patent/CN113836947B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010182261A (en) * | 2009-02-09 | 2010-08-19 | Toshiba Corp | Bilingual information forming device, mechanical translation device and program |
| CN109902314A (en) * | 2019-04-18 | 2019-06-18 | 中译语通科技股份有限公司 | A kind of interpretation method and device of term |
| CN110543644A (en) * | 2019-09-04 | 2019-12-06 | 语联网（武汉）信息技术有限公司 | Machine translation method and device containing term translation and electronic equipment |
| CN111144137A (en) * | 2019-12-17 | 2020-05-12 | 语联网（武汉）信息技术有限公司 | Method and device for generating edited model corpus after machine translation |
| CN112364669A (en) * | 2020-10-14 | 2021-02-12 | 北京中科凡语科技有限公司 | Method, device, equipment and storage medium for translating translated terms by machine translation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113836947A (en) | 2021-12-24 |
| CN112364669B (en) | 2021-09-03 |
| CN113836947A8 (en) | 2024-01-16 |
| CN112364669A (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP0519049B1 (en) | Machine translation and telecommunications system | |
| US5535120A (en) | Machine translation and telecommunications system using user ID data to select dictionaries | |
| US8635539B2 (en) | Web-based language translation memory compilation and application | |
| US8078650B2 (en) | Parsing unstructured resources | |
| US6920419B2 (en) | Apparatus and method for adding information to a machine translation dictionary | |
| US5373441A (en) | Automatic translating apparatus and a method thereof | |
| CN113836947B (en) | Method, device, equipment and storage medium for translating terms after machine translation | |
| CN110705237B (en) | Automatic document generation method, data processing device and storage medium | |
| US9817887B2 (en) | Universal text representation with import/export support for various document formats | |
| CN101271451A (en) | Computer aided translation method and device | |
| CN112949324A (en) | Method, system and terminal for translating and managing aircraft maintenance technical manual data | |
| JP5747698B2 (en) | Requirements management support device | |
| US20080052616A1 (en) | Document Processing Method and Device | |
| CN110968999B (en) | Annotating method and system for automatically realizing docx file fine granularity and diversification | |
| CN112199966B (en) | Translation method, translation device, electronic device and storage medium | |
| CN107577482A (en) | The automatic switching method and device of software languages | |
| EP1780645A1 (en) | Document processing method and device | |
| CN109947711B (en) | Automatic multi-language file management method in IOS project development process | |
| CN116595967A (en) | Natural language rule writing method based on text and related device | |
| CN115688690A (en) | Dynamic conversion method for converting Word document content into XML fragment conforming to S1000D standard | |
| CN111159979A (en) | Method and program for generating pdf document by integrating dynamic data | |
| CN115329782A (en) | Language translation method, device, electronic equipment and storage medium | |
| CN108628606B (en) | Method and system for generating WEB network management application program of embedded equipment | |
| CN112364632A (en) | Book checking method and device | |
| JP6565012B2 (en) | Translation support system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CI02 | Correction of invention patent application | ||
| CI02 | Correction of invention patent application |
Correction item: National priority Correct: 202011098139.6 2020.10.14 CN Number: 52-02 Page: The title page Volume: 37 Correction item: National priority Correct: 202011098139.6 2020.10.14 CN Number: 52-02 Volume: 37 |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |