KR20180057923A - User database construction system for auto interpreting and translating system, auto interpreting and translating system using the same, and method thereof - Google Patents
User database construction system for auto interpreting and translating system, auto interpreting and translating system using the same, and method thereof Download PDFInfo
- Publication number
- KR20180057923A KR20180057923A KR1020160156394A KR20160156394A KR20180057923A KR 20180057923 A KR20180057923 A KR 20180057923A KR 1020160156394 A KR1020160156394 A KR 1020160156394A KR 20160156394 A KR20160156394 A KR 20160156394A KR 20180057923 A KR20180057923 A KR 20180057923A
- Authority
- KR
- South Korea
- Prior art keywords
- external information
- vocabulary
- information
- unit
- input
- Prior art date
Links
Images
Classifications
-
- G06F17/2809—
Landscapes
- Machine Translation (AREA)
Abstract
A system for constructing a user database for an automatic translation and interpretation system according to an embodiment of the present invention includes a vocabulary extraction unit for extracting vocabularies in input external information; A semantic generation unit for generating semantics for the external information; And a mapping unit for mapping the vocabulary extracted by the vocabulary extraction unit and the meaning generated by the semantic generation unit to generate mapping information of a (vocabulary, semantic) type, storing the generated mapping information in a database, .
Description
TECHNICAL FIELD The present invention relates to an automatic translation and interpretation technology, and more particularly, to an automatic translation and interpretation system capable of improving the quality of an automatic translation and interpretation service by using not only its own knowledge but also external information, And an automatic translation and interpretation system using the same and a method thereof.
One of the problems encountered when using the existing automatic translation and interpretation system is that the automatic translation and interpretation system is used when there are special proper nouns related to the area (name, building, trade name, transit name such as train / subway / Sometimes the translator does not perform the translation properly, or the proper noun is mis-translated.
Due to the failure of correct translation of such an automatic translation and interpretation system, it often occurs that the user fails to accurately convey his / her intention.
The conventional automatic translation and interpretation system carries out translation using knowledge it possesses. Translation using this knowledge of self-holding applies equally to Rule Based Machine Translation (RBMT), statistical machine translation, or Neural machine translation, which is referred to as the latest technology.
As described above, since the conventional automatic translation and interpretation system carries out the translation in the knowledge it has, it can not output the correct codeword for the vocabulary to be classified in the unregistered language, .
In addition, when visiting a place using a language such as a word-of-mouth language, even if an alphabet is used in English, if the locally used language (that is, the band language) is not English, I sometimes do not understand the English notation included.
For example, when a foreigner visits Korea and inquires how to find a National Folk Museum using the National Palace Museum of Korea, which is the official name of the National Folk Museum, Museum of Korea 'does not know where it is called, and sometimes it is not able to give guidance to foreigners.
As another example, when a person in another language visits China and asks for directions using the English language on the road sign instead of asking for proper nouns using Simlified Chinese, It may not be possible to understand the correct position of the sensor.
Due to the problems described above, when you visit a country that normally uses another language, you can write your local language, on paper, print it out, show your intended location, name, and other proper nouns, In many cases, they ask local people while photographing and showing photographs of signs and instructions written.
One of these techniques is to take a picture and perform the optical character recognition (OCR) on the character in the picture, recognize it as a digitized character, and translate it.
However, there is a limitation in that it does not allow accurate translation of proper nouns, and even when the user knows the meaning, there is a problem that the user can not communicate with the local person using the vocabulary.
It is therefore an object of the present invention to improve the quality of an automatic translation and interpretation service by using it to translate external information as well as its own knowledge And an automatic translation and interpretation system using the same, and a method thereof.
According to another aspect of the present invention, there is provided a system for constructing a user database for an automatic translation and interpretation system, the system including: a vocabulary extracting unit for extracting vocabularies in input external information; A semantic generation unit for generating semantics for the external information; And a mapping unit for mapping the vocabulary extracted by the vocabulary extraction unit and the meaning generated by the semantic generation unit to generate mapping information of a (vocabulary, semantic) type, storing the generated mapping information in a database, .
Wherein the vocabulary extraction unit comprises: an information type discrimination unit for discriminating whether the external information is unstructured external information or formal external information; A character recognition unit for recognizing characters in the non-fixed external information provided from the type discrimination unit; A vocabulary determination unit for determining a vocabulary included in the external information provided from the information discrimination unit and for identifying the vocabulary by identifying a character provided from the character recognition unit; And an input / output interface for outputting a determination result provided by the lexical decision unit rotor and providing information input from the outside to the lexical decision unit.
The lexical judgment unit provides the determined vocabulary to the input / output interface when the lexical judgment is successful, and provides the lexical judgment failure status to the input / output interface when the lexical judgment fails.
The vocabulary determination unit provides a vocabulary determination result to the input / output interface, and then outputs a vocabulary according to information provided from the input / output interface.
The vocabulary determination unit outputs a vocabulary provided from the input / output interface when the vocabulary is provided from the input / output interface, and outputs the determined vocabulary when receiving the application signal from the input / output interface.
Wherein the semantic generation unit comprises: an information type discrimination unit for discriminating whether the external information is unstructured external information or external external information; An object recognition unit for performing object recognition on the atypical external information provided from the information type discrimination unit and generating object information; A semantic judging unit for judging the meaning of the formal external information provided from the information type judging unit and judging the meaning of the object information provided from the object recognizing unit; And an input / output interface that outputs a determination result provided from the semantic determination unit and provides information input from the outside to the semantic determination unit.
The semantic determination unit provides the determined semantic to the input / output interface when the semantic determination is successful, and provides the semantic determination failure status to the input / output interface when the semantic determination fails.
The semantic determiner outputs semantics according to information provided from the input / output interface after providing a semantic determination result to the input / output interface.
The semantic determination unit outputs a meaning provided from the input / output interface when receiving the meaning from the input / output interface, and outputs the determined meaning when receiving the application signal from the input / output interface.
An automatic translation and interpretation system according to an embodiment of the present invention includes a system database, which is implemented at the time of establishing an automatic translation and interpretation system, and stores information for translation and interpretation; A user database in which external information is stored in a form of a pair (lexical, meaning) of a word in the external information input by the user and a meaning of the external information after the automatic translation and interpretation system is constructed; A translating / translating unit for translating and interpreting the input sentence; And a text input device for generating a sentence composed of text expressed only in a source language according to a request of a user and providing the sentence to the interpretation section or providing a sentence having a combination of a source language and a target language to the interpretation section.
The text input device may include a text input unit configured with a text input button and outputting text corresponding to a user's instruction; An external information reference button for outputting an external information reference signal corresponding to the user's instruction; An external information display unit for displaying information provided from outside; A completion button for outputting a completion signal corresponding to a user instruction; And a text input through the text input unit to create a sentence composed of a text input through the text input unit and external information selected from external information stored in the user database, And a control section for providing an interpretation section.
Upon receiving the external information reference signal, the control unit extracts external information stored in the user database, displays the extracted external information on the external information display unit, and creates a sentence using external information selected from the displayed external information.
Wherein the control unit provides the text to the interpretation station when the text input unit receives the completion signal, or the text input through the text input unit and the external information selected from the external information stored in the user database To the interpretation and distribution section.
According to an embodiment of the present invention, there is provided an automatic translation and interpretation method comprising: displaying a text input through a text input unit on a text display unit; Extracting external information from the user database and displaying external information selected from the extracted external information on the text display unit when there is an external information reference request; And translating a sentence consisting of text input through the text input unit when there is a completion request or translating a sentence having a combination of text input through the text input unit and external information selected from external information stored in the user database .
The step of displaying the external information on the text display unit may include extracting external information from the user database when the external information reference request is received, displaying the extracted external information on the external information display unit, On the text display unit.
The step of displaying the text on the text display unit and the step of displaying the external information on the text display unit are alternately repeated.
The external information stored in the user database is stored in a form of a pair (lexical meaning) in the form of a pair of the words in the external information and the meaning of the external information inputted by the user after the automatic translation and interpretation system is constructed.
The external information stored in the user database may be stored in a form of a pair (lexical or semantic) of a vocabulary in the unstructured external information and a meaning of the unstructured external information, The meanings are stored in pairs (vocabulary, meaning).
If the external information stored in the user database is generated based on the unstructured external information, the external information stored in the user database recognizes the character in the unstructured external information, To generate the object information, to identify the recognized character to judge the vocabulary, to judge the meaning of the generated object information, and to generate based on the determined vocabulary and meaning.
Wherein if the external information stored in the user database is generated based on the external external information, the external information stored in the user database is used to determine a vocabulary in the external external information, And is based on the determined vocabulary and meaning.
According to the embodiment of the present invention, the knowledge of the vocabulary of the difficult language to be input or the proper noun not included in the existing automatic translation and translation engine is received from the external information, the vocabulary is provided in a kind of user defined dictionary format, The quality of the resultant product can be improved.
In addition, through the application of the present invention, the user can conveniently input a sentence intended by the user without using input method environments for inputting vocabulary.
1 is a diagram illustrating an example of a system for constructing a user database of an automatic translation and interpretation system according to a preferred embodiment of the present invention.
2 is a diagram showing an example of a configuration of a lexical value extracting unit of the user database construction system of FIG.
3 is a diagram showing an example of a configuration of a meaning generation unit of the user database construction system of FIG.
4 is a flowchart illustrating an operation of a system for constructing a user database for an automatic translation and interpretation system according to an embodiment of the present invention.
FIG. 5 is a flow chart specifically illustrating a word extraction process and a meaning generation process in step S410 shown in FIG.
6 is a diagram showing an example of the configuration of an automatic translation and interpretation system according to a preferred embodiment of the present invention.
7 is a detailed configuration diagram of the text input device of Fig.
8 is a flowchart illustrating an operation of an automatic translation and interpretation system according to an exemplary embodiment of the present invention.
For specific embodiments of the invention disclosed herein, specific structural and functional descriptions are set forth for the purpose of describing an embodiment of the invention only, and it is to be understood that the embodiments of the invention may be embodied in various forms, And should not be construed as limited to the embodiments described.
The present invention is capable of various modifications and various forms, and specific embodiments are illustrated in the drawings and described in detail in the text. It should be understood, however, that the invention is not intended to be limited to the particular forms disclosed, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.
It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between. Other expressions that describe the relationship between components, such as "between" and "between" or "neighboring to" and "directly adjacent to" should be interpreted as well.
The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms " comprising ", or " having ", and the like, are intended to specify the presence of stated features, integers, But do not preclude the presence or addition of steps, operations, elements, parts, or combinations thereof.
Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.
On the other hand, if an embodiment is otherwise feasible, the functions or operations specified in a particular block may occur differently from the order specified in the flowchart. For example, two consecutive blocks may actually be performed at substantially the same time, and depending on the associated function or operation, the blocks may be performed backwards.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an automatic translation and interpretation system proposed by the present invention, a method thereof, and a user database construction system therefor will be described in detail with reference to the accompanying drawings.
1 is a diagram illustrating an example of a system for constructing a user database of an automatic translation and interpretation system according to a preferred embodiment of the present invention.
Referring to FIG. 1, a
To this end, the
Specifically, the
Here, the external information may be unstructured external information or may be external external information. The external external information may be a photograph taken by a camera (ex, a photograph of a sign), and the external external information may be computer readable Information stored in a recording medium, and information that can be acquired using an electronic device.
Examples of the external information include a digitalized subway station name guidance map, a digitized bus station name map, and the like.
At this time, since the external information is input to each of the
The
The
The detailed configuration of the
Meanwhile, the
2 is a diagram showing an example of a configuration of a lexical value extracting unit of the user database construction system of FIG.
Referring to FIG. 2, the
For this, the
Specifically, the
The information
If the input external information is unstructured external information, the information
The
For example, when a road sign such as' Taesanro ',' Jangpyeongro 'and' Alpanro 'is photographed and input, the
The
The lexical
For example, when a user confirms a subway route map using a smart phone and inputs the subway route map as external information, the station name of the subway route map is digitized information, Is not required.
That is, since the vocabulary in the unstructured external information can not be immediately recognized by the
The
In addition, if the lexical
The input /
In addition, the input /
That is, the user can determine whether the displayed vocabulary is appropriate through the input /
If the lexical judgment is not correctly performed, the user can directly input the vocabulary through the input /
Further, when the lexical judgment is made correctly, the user can input the application for using the currently determined vocabulary.
The
3 is a diagram showing an example of a configuration of a meaning generation unit of the user database construction system of FIG.
Referring to FIG. 3, the
For this purpose, the
The
The information
If the inputted external information is unstructured external information, the information
The entity information data face 320 stores entity information necessary for the
The
For example, when the photographed application sign image is input, the
The
The
For example, if 'place name' is defined as the meaning of the object information 'sign' in the
The
At this time, the fixed external information is digitized information, and the entity information for the corresponding information can be automatically recognized. Therefore, since the recognition of the object is not required for the formal external information, it is input to the meaning
For example, when a user confirms a subway route map using a smartphone and inputs a subway route map as external information, since the inputted external information includes entity information called a 'subway route map' It is not necessary.
The
In addition, when the
The input /
In addition, the input /
That is, the user can determine whether the meaning displayed through the input /
In this way, if the semantics are not correctly determined, semantics can be input directly through the input /
In addition, when the semantic determination is performed correctly, the user can input an application for using the currently determined semantic.
The
The configuration and configuration of the user database construction system for constructing the user database used in the automatic translation and interpretation system according to the embodiment of the present invention have been described. Hereinafter, an operation of the system for constructing a user database for an automatic translation and interpretation system according to an embodiment of the present invention will be described in detail.
4 is a flowchart illustrating an operation of a system for constructing a user database for an automatic translation and interpretation system according to an embodiment of the present invention.
4 may be performed by the user
The vocabulary extraction process and the meaning generation process in step S410 will be described later with reference to FIG.
Thereafter, the
Then, the
FIG. 5 is a flow chart specifically illustrating a word extraction process and a meaning generation process in step S410 shown in FIG.
Referring to FIG. 5, the
If it is determined in step S411 that the external information is unstructured external information (S411: Yes), the
Thereafter, the
After step S414, the
Specifically, the
If the semantic determination is successful, the
After displaying the determination result, the
Then, after displaying the determination result, the
If it is determined in step S411 that the external information is not the unfixed external information (S411: No), that is, if the external information is the external external information, the
Thereafter, the
Specifically, the
If the semantic determination is successful, the
After displaying the determination result, the
After displaying the determination result, the
The configuration and operation of the system for constructing a user database for an automatic translation and interpretation system according to an embodiment of the present invention have been described with reference to FIGS. Hereinafter, an automatic translation and interpretation system for performing translation and interpretation using a user database constructed by the user database construction system described with reference to FIGS. 1 to 5 will be described.
FIG. 6 is a diagram illustrating an example of the configuration of an automatic translation and interpretation system according to a preferred embodiment of the present invention, and FIG. 7 is a detailed configuration diagram of the text input device of FIG.
The automatic translation and
To this end, the automatic translation and
Specifically, the automatic translation and
The
The interpretation / translating
In particular, the interpretation /
The
The
That is, the
Since the process of storing external information in the
Meanwhile, the
In this case, the external information stored in the
If the external information provided to the
However, if the external information provided to the
Accordingly, the
The
Specifically, the
The
At this time, the text input through the
The
The external information reference button 643 outputs a signal corresponding to the user's instruction to the
For example, when the user presses or touches the external information reference button 643, the external information reference button 643 may output an external information reference signal to the
The external
The
For example, when the user is pressed or touched, the
The
Upon receiving the signal (external information reference signal) provided from the external information reference button 643, the
At this time, the external information extracted from the
The
When the
The configuration and function of the automatic translation and interpretation system according to the preferred embodiment of the present invention have been described above. Hereinafter, the operation of the automatic translation and interpretation system of the present invention will be described.
8 is a flowchart illustrating an operation of an automatic translation and interpretation system according to an exemplary embodiment of the present invention.
8 can be performed by the automatic translation and
At this time, the text input through the
When the external information reference button 643 is pressed or touched by the external information reference button 643, that is, when there is an external information reference request, The external information is extracted from the
In this case, after the automatic translation and
The external information stored in the
The process of storing external information in the
Thereafter, the automatic translation and
On the other hand, depending on the case, the steps S800 and S810 (including S810-1 and S810-2) may be reversed in sequence or alternately. Also, in some cases, step S810 may not be performed.
If the completion signal is generated from the
That is, the automatic translation and
For example, suppose that a user uses his / her automatic translation and
Then, it is assumed that the word 'Korean Electronics and Telecommunications Research Institute' is stored in the
For example, a user whose native language is English can select a location (or a building) in a map displayed on the screen, and select the lexical information (here, Korea Electronics and Telecommunications Research Institute) and the semantic information (here, name). In the worst case, the English native speaker knows that this is a place name or company name, and finally, the name of the company (or place name), which is the semantic information corresponding to the word 'Korea Electronics and Telecommunications Research Institute' tuple) and can be inserted into the
The user inputs 'Please go to the' using the
Accordingly, the automatic translation and
When the user selects 'Korean Electronics and Telecommunications Research Institute' among the external information displayed in the external
That is, finally, the completed text is displayed on the
'Please, go to the Korea Electronics and Telecommunications Research Institute'
Next, when the user presses or touches the
1 to 3 showing a system for constructing a user database according to an embodiment of the present invention, and blocks of FIGS. 6 and 7 showing an automatic translation and interpretation system according to an embodiment of the present invention, It should be understood as an example embodied in a functional perspective.
Similarly, the operations depicted in FIGS. 4, 5, and 8 are representative of various processes that may be substantially represented on a computer-readable medium and executed by a computer or processor, whether or not the computer or processor is explicitly shown .
Also, the explicit use of terms such as processor, control, or similar concepts should not be interpreted exclusively as hardware capable of executing the software, and may include, without limitation, digital signal processor (DSP) hardware, ROM), random access memory (RAM), and non-volatile memory. Other hardware, of course, may also be included.
As described above, the automatic translation and interpretation system, the method, and the user database construction system for the automatic translation and interpretation system according to the present invention have been described by way of examples. However, the scope of the present invention is not limited to the specific examples. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Therefore, the embodiments described in the present invention and the accompanying drawings are intended to illustrate rather than limit the technical spirit of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments and accompanying drawings . The scope of protection of the present invention should be construed according to the claims, and all technical ideas within the scope of equivalents should be interpreted as being included in the scope of the present invention.
100: user
120, 300: Meaning generation unit 130:
140: user database 210: information type discrimination unit
220: character recognition unit 230: lexical information database
240: lexical decision unit 250: input / output interface
310: information type discrimination unit 320: object information database
330: entity recognition unit 340: semantic information database
350: Meaning judgment part 360: Input / output interface
600: Automatic translation and interpretation system 610: System database
620: Translating and translating unit 630: User database
640: Text input device 641: Text input part
642: text display section 643: external information reference button
644: External information display part 645: Completion button
646:
Claims (1)
A vocabulary extraction unit for extracting a vocabulary in the inputted external information;
A semantic generation unit for generating semantics for the external information; And
(Vocabulary, semantic) type mapping information by mapping the vocabulary extracted by the vocabulary extraction unit and the meaning generated by the meaning generation unit, and storing the generated mapping information in a database to construct a user database Including a mapping unit
User Database Construction System for Automatic Translation and Interpretation System.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160156394A KR20180057923A (en) | 2016-11-23 | 2016-11-23 | User database construction system for auto interpreting and translating system, auto interpreting and translating system using the same, and method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160156394A KR20180057923A (en) | 2016-11-23 | 2016-11-23 | User database construction system for auto interpreting and translating system, auto interpreting and translating system using the same, and method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20180057923A true KR20180057923A (en) | 2018-05-31 |
Family
ID=62454509
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020160156394A KR20180057923A (en) | 2016-11-23 | 2016-11-23 | User database construction system for auto interpreting and translating system, auto interpreting and translating system using the same, and method thereof |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR20180057923A (en) |
-
2016
- 2016-11-23 KR KR1020160156394A patent/KR20180057923A/en unknown
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8060359B2 (en) | Apparatus, method and computer program product for optimum translation based on semantic relation between words | |
TWI437449B (en) | Multi-mode input method and input method editor system | |
TWI443551B (en) | Method and system for an input method editor and computer program product | |
US9805718B2 (en) | Clarifying natural language input using targeted questions | |
US9047268B2 (en) | Character and word level language models for out-of-vocabulary text input | |
US9484034B2 (en) | Voice conversation support apparatus, voice conversation support method, and computer readable medium | |
US20090222257A1 (en) | Speech translation apparatus and computer program product | |
US20140320413A1 (en) | Multimodal text input by a keyboard/camera text input module replacing a conventional keyboard text input module on a mobile device | |
KR102204888B1 (en) | Automatic translation by keyboard | |
JPWO2018055983A1 (en) | Translation apparatus, translation system, and evaluation server | |
US11227116B2 (en) | Translation device, translation method, and program | |
CN111160333A (en) | AR glasses, text translation method and device thereof, and computer-readable storage medium | |
JP5558284B2 (en) | Speech recognition system, speech recognition method, and speech recognition program | |
CN114092949A (en) | Method and device for training class prediction model and identifying interface element class | |
US20210233522A1 (en) | Voice context-aware content manipulation | |
US20170083499A1 (en) | Identifying and modifying specific user input | |
JP2010134922A (en) | Similar word determination method and system | |
CN111709431B (en) | Instant translation method and device, computer equipment and storage medium | |
JP7481999B2 (en) | Dictionary editing device, dictionary editing method, and dictionary editing program | |
US20220198157A1 (en) | Multilingual Model Training Using Parallel Corpora, Crowdsourcing, and Accurate Monolingual Models | |
JP2019159814A (en) | Information processing device, information processing method, and program | |
WO2023163767A1 (en) | Multilingual support for natural language processing applications | |
KR20180057923A (en) | User database construction system for auto interpreting and translating system, auto interpreting and translating system using the same, and method thereof | |
US11501762B2 (en) | Compounding corrective actions and learning in mixed mode dictation | |
CN114663886A (en) | Text recognition method, model training method and device |