RU2285951C2 - System for controlling language translation - Google Patents

Abstract

FIELD: computer engineering.

SUBSTANCE: system contains processor with memory, in which software executed on processor is stored for comparing terms of text with terms of both common and specialized dictionary, while matches of terms being compared are shown on display and it is possible to insert translation of matching terms into text being translated. Processor is used for assigning priorities by means of graphic user interface to several dictionaries, as a result of which terms are offered on display on basis of assigned priorities, and for showing on display the longest translations of matching terms from text and terms from common or specialized dictionary.

EFFECT: increased speed and precision of translation, simplification of complicated translations.

2 cl, 10 dwg

Description

The invention relates to computer technology and can be used for automated translation of text from one language to another.

At the moment, in the field of computer-assisted translation from a foreign language, machine translation tools and translation tools using translation memories are known. When using machine translation tools, a block of text or a sentence is translated by sequentially searching for a translation of the words of each sentence of the text. Thus, a direct search for each translated word is carried out in the dictionary database. The machine translation program then collects these translations into a sentence that makes sense. When using translation memory, a block of text is translated directly sentence by sentence or segment by segment. That is, a search is made for the translation of each sentence or segment in a previously compiled database of phrases and sentences of the language.

Previously, various methods have been developed that allow documents to be translated exclusively by computer. For example, Carbonell et al. US Pat. No. 6,173,785 describes an interactive text editor that imposes lexical and grammatical restrictions on a subset of the natural language used by the author to create the original text. These limitations help resolve text ambiguity in order to improve translation capabilities. In addition, Motoyama in US Pat. No. 6,208,956 describes a method for encoding documents using tags of a standard generalized markup language (SGML) and using translation resources depending on the tags. Tags can indicate the types of documents or parts of a document that are being translated. By coding a document in this way, a more accurate machine translation can be achieved without imposing excessive restrictive rules on the words and phrases of the document to be translated.

Other methods are known for imposing restrictions and structuring grammar and vocabulary. Various methods for processing semantic and idiomatic words and phrases, as well as methods for processing multi-valued words using statistical analysis, are being developed and improved. In addition, to simplify the work of users, modern translation systems may include the function of parallel display of the original text and its translation. Additionally, these systems can enable users to choose which parts of machine translation to accept and which to refuse.

The problem solved by the present invention is improving the quality of translation.

The technical result that can be obtained by implementing the claimed system is to increase the accuracy and speed of translation, as well as simplify complex translations.

To solve the problem with the achievement of the specified technical result, the language translation management system comprises a processor with memory, a display, software stored in the memory and executed on the processor for comparing text terms with terms found in at least one of the dictionaries, and at least one of the many specialized dictionaries has been entered into the system, and the processor is configured to show matches between text terms and dictionary and specialist terms on the display according to the invention, the processor is configured to prioritize through at least one of the dictionaries and at least one of the many specialized dictionaries, the processor made by providing through the graphical user interface the presentation on the display based on the assigned priorities of the matching text terms with the terms s specialized dictionary or dictionaries, as well as the chance by the GUI on the display presenting the longest matching translation text terms and specialized terms dictionary or vocabulary.

An additional embodiment of the system is possible, in which it is advisable that before inserting the translations the processor should be able to bring the terms to a standard form, providing the definition of their root components.

Other features and advantages of the present invention will be apparent from the following description and the appended claims.

Figure 1 shows a typical computer system on which at least one embodiment of the present invention may be implemented;

figure 2 - a typical graphical user interface (GUI) in accordance with at least one embodiment of the present invention;

figure 3 is an enlarged view of a part of a typical graphical user interface (GUI) shown in figure 2;

4 is a dictionary search window in accordance with at least one embodiment of the present invention;

5 is a typical options window in accordance with at least one embodiment of the present invention;

6 is a window for installing an active dictionary in accordance with at least one embodiment of the present invention;

7 is a flowchart describing a process in accordance with at least one embodiment of the present invention;

Fig. 8 is a flowchart describing an exemplary method for processing a second match in accordance with at least one embodiment of the present invention;

Fig.9 is a view of a typical resulting document after comparing in accordance with at least one embodiment of the present invention;

10 is a typical translation window in accordance with at least one embodiment of the present invention.

The following is a detailed description of specific embodiments of the present invention with reference to the accompanying drawings. In order to maintain compliance in different drawings, the same elements are indicated by the same reference numbers.

In order to provide a more accurate understanding of the invention, numerous specific details are set forth in the following detailed description of the invention. However, it will be understood by those skilled in the art that the invention may be practiced without these specific details. In other cases, a detailed description of well-known functions, on the contrary, is not given in order to avoid creating uncertainty for understanding the essence of the invention.

The present invention relates to methods and devices for translation from a foreign language using Universe translation tools. Universe translation tools are tools that provide translation assistance. Universe translation tools analyze sentences and provide additional definitive information based on words and phrases found. Based on the words and phrases found in this sentence, these words and phrases are searched in a specific dictionary in order to provide additional definitive information. Special dictionaries contain definition phrases in the source and target language and are specifically designed to work within the framework of these specific topics. Special dictionaries are documents compiled specifically for working with a given project and / or topic, and have a narrower focus than a regular dictionary, contain one or more translations of a given word or phrase. Conventional dictionaries, as a rule, are detailed documents covering all possible interpretations and corresponding translations of a word or phrase. Further, Universe translation tools work with any language pair, for example, when translating in both directions for language pairs English-French, English-Spanish, English-Russian, etc.

The present invention can be implemented on virtually any type of computer, regardless of the platform used. For example, as shown in figure 1, a typical computer (10) has a processor (12) associated with a memory (14), an information storage device (16), and a number of other elements and functional units typical of a modern computer (not shown). The computer (10) is equipped with associated information input means, such as a keyboard (18) and a mouse (20), although, depending on the configuration, these means, water can take other forms. The computer (10) is also connected to output devices, such as a display (22), which can also take other forms depending on the configuration available. The computer (10) can be connected to a network or other resources (24).

As shown in Figure 2, the Universe translation tool is memory-resident, and the graphical user interface (GUI) has window controls selectable at the user's discretion, for example, buttons in the toolbar of the Microsoft Word® editor. The GUI is part of the application software that interacts with the user through a graphic display. The GUI receives input from the user through various means of access, such as a mouse or a combination pad, or through a keyboard. The visual output of the GUI is routinely output to a display device, such as a computer monitor screen, and contains controls that allow the user to interact with the GUI. Examples of controls are windows, titles, buttons, labels, menu bars, toolbars, dialog boxes, menus, icons, etc. The controls may also be applications that can be launched by the user, or a cursor icon showing the position of the mouse.

An example of the visual output of the GUI is shown in figures 2, 3. As can be seen from the figures, the Microsoft Word® editor is displayed in the window (30) along with the open document. The buttons of the Universe translation tool are included in fixed toolbars, for example, toolbars (32), (34), and floating toolbars, for example, a toolbar (36). These toolbars (32), (34) and (36) correspond to various functions of the Universe translation program. Specialists in this field should understand how to create and perform dynamic positioning of controls of this type. Therefore, a detailed description of this process is not given in this document.

The various toolbar buttons (32), (34) and (36) activate the various functions of the Universe translation program. In particular, the fixed toolbar (32) contains the “Merge translation” button (40), which inserts translations of known terms into the text of the document.

The fixed toolbar (34) has six buttons, namely the scan button (42), the translate button (44), the auto button (46), the lookup button (dictionary search) (48), the "clear" button (50) and the "options ..." button (options ...) (52). These buttons include various functions. The scan button (42) includes scanning the active document for the search for known terms, as well as the identification of the found terms. The translation button (44) activates the translation command of known terms in the active document. This translation process is similar to spell checking. Known terms are displayed along with their translation, and the user can, at his discretion, insert one translation or insert all translations. The “auto” button (46) includes a command to search for known terms in a document and automatically insert translations of all found known terms. The search button in the dictionary (48) starts the search for the highlighted term in active dictionaries or, in the absence of highlighted text, displays a search window in the dictionary. The clear button (50) deletes all marks associated with known terms from the active document. The "options ..." button (52) displays the dictionary options window.

In the floating toolbar (36) there are icons corresponding to the search command in the dictionary, i.e. an icon button (54), and a command for viewing a set of active dictionaries, i.e. pictogram button (56). The icon button (54) enables the search for the highlighted term in active dictionaries or, in the absence of a highlighted term, displays a search box in dictionaries. This allows users to search for known terms in defined dictionaries. Button (56) displays a list of active dictionaries. In this window, the user has the ability to change the set of active dictionaries, as well as set the priorities of active dictionaries. Specialists in this field should be clear that the labels and icons used, as well as the placement and organization of the buttons described above are just an example and can be changed in various ways without deviating from the essence of the present invention.

Figure 4 shows a search box in a dictionary according to one embodiment of the present invention. The search window in the dictionary (80) is displayed when you press the button (48) or the icon button (54). Search windows in the dictionary (80) contain a text window (82) for entering the search keyword and a drop-down menu (84) of terms found in the dictionary. The user can select the language indicators with the buttons (86) and (88). For example, the buttons of the Russian language and English are shown.

The control buttons (90), (92), (94), (96), (98) allow you to search for the selected term in a special dictionary, view and change the set of active special dictionaries, view and change the contents of the clipboard, perform the copy function, and also perform a return function, respectively. The search box in the special dictionary also includes menu items that allow you to perform various functions. The menu item "glossary" (dictionary) (100) allows you to display a set of active special dictionaries. In the window of the set of active special dictionaries, the user can select a dictionary, as well as add, delete and prioritize special dictionaries of the active set. The menu option "options" (102) allows you to display the options window of a special dictionary. In the options window of the special dictionary, the user can modify the parameters of the Universe translation program related to the search in documents, the source language of the document in which the search is performed, as well as the method for identifying the terms found in the document. Finally, the “help” menu item (104) displays a help window. The help window displays the documentation for the program.

Figure 5 shows the dictionary options window (60). The dictionary options window (60) is displayed when you press the options button (52). In the dictionary options window (60), the user has the opportunity to modify the parameters of the Universe translation program related to the search in documents, the source language of the document in which the search is performed, as well as the method for identifying the terms found in the document.

As an example, selective buttons (62) and (64) are used, allowing the user to choose between searching for terms only in the current dictionary or in the active set of dictionaries, respectively. Selective buttons (66) and (68) are used to allow the user to choose between identifying only the first longest match or all the longest matches, respectively. The drop-down menu (70) is used to select the source document language. Finally, the color change buttons (72), (74) and (76) allow the user to choose which color to display the terms found and identify the translation text, respectively. In addition, the clear memory button (78) deletes all marks related to known terms and translations from the active document in the same way as the clear button (50). Finally, there are OK and cancel buttons that work the same way as in other standard windows.

Figure 6 shows a window of a set of active dictionaries in accordance with one embodiment of the present invention. A set of active dictionaries (110) is displayed on the screen by pressing the icon button (56) or selecting the dictionary item (100) in the dictionary search window (80). In the window of the set of active dictionaries, the user has the opportunity to select a dictionary and add, remove and prioritize dictionaries of the active set. All available dictionaries are listed either in the window of the active set (112) or in the window (114) of dictionaries that are not included in the active set. Dictionaries can be added or excluded from the active set using the buttons (116) and (118), respectively, having previously selected the desired dictionary in the corresponding window.

Special dictionaries included in the active set are assigned priority from top to bottom. The dictionary priority is changed by the priority button (120) after highlighting the desired dictionary. In the example shown, one single priority button is used, which operates on the principle of increasing priority, i.e. Each time you press the button, the priority of the selected dictionary rises to the next higher level. Specialists in this field should be clear that there are a variety of options for this function, which are not beyond the scope of the present invention. Finally, the "OK" and "cancel" buttons are used, which work in the same way as in other standard windows.

7 is a flowchart describing a process in accordance with one embodiment of the present invention. When the user selects one of the translation activation buttons described above (step 200), the open document is analyzed for known terms (step 202). Before analysis, the selected terms are reduced to the standard form (step 201). Reducing to a standard form is a process that is used to bring words to their root component in order to compare with the words in this special dictionary. For the English language, reduction to the standard form consists in searching for plural nouns and verbs in the past tense and converting them, respectively, into the singular and the present tense. Specialists in this field should be clear that in other languages, the reduction to a standard form may include a more complex process of determining the root component of a particular word.

The analysis of the document may include comparing the terms contained in the active special dictionary and the set of active special dictionaries with the text of the document in order to find matches. During the comparison process, if no matches are found in the text of the document for the known term (step 204), the system checks whether the comparison was performed for all known terms, and then the process ends (step 206).

If so, the process stops. Otherwise, the system continues to compare known terms with the text of the document (step 202).

If a match is found for a known term (step 204), the system determines whether the detected known term is part of another known term (step 208). If not, the known term is presented as such (step 210) and the system determines whether the process is completed (step 206). If the known term is part of another term (step 208), then one of several comparisons may be made, depending on the options selected by the user and the particular embodiment of the present invention. As an example, a method for processing a second match is described below with reference to FIG. 8 (step 212). After returning from processing the second match (step 212), the system determines whether the process is completed (step 206).

According to figure 8, the system first determines whether the use of a set of active dictionaries is selected, or whether a single dictionary is used (step 214). If there is an active set (step 214), the system determines whether the priority of the detected second match is higher or lower than the priority of the existing match of which it is a part (step 216). If the priority of the second match is lower than the priority of the existing match (step 216), the system checks whether it is necessary to return all the longest matches (step 218). As described above, whether to return all the longest matches or only one longest match is an option set by the user.

If it is necessary to return all the longest matches (step 218), then the second match is returned as the second term found (step 220), and the process goes to the beginning (step 212). On the other hand, if you want to return only one longest match (step 218), the system compares the second match with the existing match to determine if the second match is the longest (step 222). If not, the process returns to the beginning (step 212). If so, the second match is presented as the longest match, and the existing match is no longer presented (step 224). Then the process goes to the beginning (step 212).

If the priority of the second match is higher than the priority of the existing match (step 216), the system again determines whether to return all the longest matches (step 226). If so, the second match is presented as the primary match, and the existing match is presented as the secondary match in accordance with priority (step 228). Then the process goes to the beginning (step 212). Otherwise, the system determines whether the second match is longer than the existing match (step 230). If so, the second match is presented as the longest match, and the existing match is no longer presented (step 224), as already described above. However, if the second match is not the longest match (step 230), both the second match and the existing match are returned, since the existing match is the longest and the second match is the match with a higher priority (step 228). Then the process returns to the beginning (step 212).

Specialists in this field should be clear that in a particular embodiment, the number of steps described above may be more or less, or steps may appear in a sequence different from that described without going beyond the scope of the present invention.

In figures 9, 10 shows a document obtained as a result of the above comparison. A document (240) is a text completely similar to the original document, however, as you can see, labels are placed throughout the text to indicate which terms are known. Further, different colors are used to highlight primary and secondary known terms. Based on these notations, translators will be able to quickly determine which terms are special technical terms and which are commonly used (at least from the point of view of the selected dictionary). Having looked at a document with known terms indicated, the user can select with a marker words or a phrase designated as known, for example, the word "tanks" (252) and press the search button in the dictionary (48) or the icon button (54) to view the corresponding translation (250).

Advantages of one embodiment of the present invention may include one or more of the following. In one embodiment, the present invention simplifies the translation of words, sentences and phrases by marking terms found in a document that correspond to technical or other significant words, sentences and phrases stored in special dictionaries. It can be set in which dictionaries to search, as well as the priority of matches found. In the presence of plug-in dictionaries of terms, the translations performed by various specialist translators will be uniform. Technical terms that have a certain meaning in a technical context and a completely different meaning in ordinary use will be translated correctly. Terms that are not difficult to translate can be proposed or fully reserved for translation by a specialist translator.

An automatic translation of the most complex terminology specific to a specific project can be performed. During the translation process, automatic and full use of the dictionary database is possible. Absolute compliance with the terminology approved for a given project, as well as full compliance of translated materials with approved dictionaries of special terms, can be effectively implemented. A faster, more consistent and accurate translation can be provided. It is possible to issue documents that have undergone preliminary processing to freelance translators. Simplified modernization and operational control, as well as database management. Specialists in this field should be clear that the present invention may include other advantages and features.

Despite the fact that the invention has been described by the example of a limited number of embodiments, those skilled in the art having read this description should understand that other embodiments may be offered without departing from the scope of the invention described in this application. Thus, the scope of the invention should be limited only by the attached claims.

The most successfully claimed technical solution is industrially applicable in computer technology for the automatic translation of the most complex terminology specific to a specific project.

Claims (2)

1. A system for managing a language translation comprising a processor with memory, a display, software stored in memory and executed on a processor to compare text terms with terms in at least one of the dictionaries, and at least one of many specialized dictionaries, and the processor is designed to present on the display matches between the terms of the text and the terms of the dictionary and the specialized dictionary and insert translations of matching text terms and dictionary terms and a specialized dictionary into text, characterized in that the processor is designed to assign priorities through a graphical interface to a user of at least one of the dictionaries and at least one of the many specialized dictionaries, the processor is designed to be presented on the display via a graphical user interface, based on the assigned priorities, matching terms of the text with the terms of a dictionary or a specialized dictionary, as well as for presentation on the display by means of graphic th user interface longest matching text translations of terms and terminology dictionary or a specialized dictionary. 2. The system according to claim 1, characterized in that before inserting the translations, the processor is designed to bring the terms to a standard form, providing a definition of their root components.

Images