KR20170061064A - Translation method based on selective language recognition processing - Google Patents

Description

TECHNICAL FIELD [0001] The present invention relates to a translating method based on selective language recognition processing,

The present invention relates to a translation method based on selective language recognition processing. More specifically, the present invention allows the user to directly select the meaning of a homonym or a synonym included in the original text, which is the object of machine translation, thereby enhancing the accuracy of the translation and effectively transmitting the nuance of the original text to the translation, thereby improving the overall quality of the translation The present invention relates to a translation method based on selective language recognition processing.

The conventional machine translation method has a problem in that the quality of the translation is low because the user takes a method of automatically translating the original text without the intervention of the user after the user inputs the original text to be translated. Especially, when the original text entered by the user includes homonyms or synonyms, the translation quality is further degraded.

For example, if the original text is "Access is restricted to a radius of 10 km, then a conventional machine translation engine will translate the text into" This approach was prohibited by accident 10 km. Although the original "earth" means a district, it has to be translated into "district" in actual machine translation, meaning "earth".

On the other hand, if the Korean language is a source language and the target language is a language other than English, then English is an intermediate language. In this case, the wrong translation of the intermediate language is directly translated into the target language, resulting in a significant drop in translation quality.

For example, if the original text is "Access restricted to 10 km radius of the earth", then the conventional machine translation engine will translate the text into English translations of "This approach was prohibited by accident Earth radius 10 km." , Translates this translation into a French translation of "Cette approche limite imposee par l'accident rayon de la Terre 10 km." This French translation shows that "this access restriction is enforced by the 10 km radius of the planet earth" shows that the intended intention is misinterpreted and that pure machine translation does not provide the communication function properly.

According to Dong-rae's machine translation method, similar problems arise in relation to synonyms. In particular, if the original text contains synonyms such as 语 (语), abbreviations, abbreviations, acronyms, .

For example, if the original text is "Oh, but nizolla is so cool," then the conventional machine translation engine translates this text into "Oh Dang Zola but I ㅇ ㅋ ㅋㅋ". As can be seen from this translation example, according to the conventional translation engine, it can be seen that almost no meaningful translation is generated when it is not a standard language.

Thus, if the original text entered by the user includes homonyms or synonyms, it is necessary to reflect the true meaning and nuance of the homonyms or synonyms in the translation to improve the translation quality.

Korean Patent Laid-Open Publication No. 10-2014-0098822 (public date: August 08, 2014, name: provision of translation support in application localization) Korean Patent Laid-Open Publication No. 10-2004-0111188 (date of publication: December 31, 2004, name: Adaptive Machine Translation)

An object of the present invention is to provide a translation method based on selective language recognition processing capable of improving the quality of translation by allowing the user to directly select the meaning of the homonym or synonym included in the original text which is the object of machine translation.

It is another object of the present invention to provide a translation method based on an optional language recognition process capable of improving the accuracy of translation by allowing the user to select the true meaning of the homonym word when the original word includes the homonym word .

Another object of the present invention is to provide a translation method based on selective language recognition processing that allows a user to directly select a vocabulary to be applied to a translation when synonyms are included in the original text, .

A translation method based on the selective language recognition process according to the present invention includes a source text input step of inputting a source text expressed in a source language, and a step of, if the source text includes a homonym or a synonym, And displaying the translation created by translating the original text into the target language according to the meaning of the synonym or the synonym selected by the user.

In the translation method based on the selective language recognition process according to the present invention, the semantic selection request step may include determining whether the homonym or the synonym is included in the original text by referring to a homonym / synonym database, And displaying a semantic selection menu for selecting the homonym or the meaning of the synonym by referring to the homonym / synonym database if it is determined that the homonym or the synonym is included in the homonym / synonym database, do.

In the translation method based on the selective language recognition process according to the present invention, the selection of the homonym or the meaning of the synonym is performed through an intermediate language which is a third language other than the source language and the target language, Is performed.

In the translation method based on the selective language recognition process according to the present invention, the intermediate language is one of English, Chinese, Japanese, French, Spanish, and German.

In the translation method based on the selective language recognition process according to the present invention, when the selection of the homonym or the meaning of the synonym is performed through the intermediate language, the translation creation / Generating an optional language recognition processing statement by replacing the meaning of a word or a synonym with the intermediate language; generating an intermediate translation by translating the selective language recognition processing statement into the intermediate language; And generating the translation, and displaying the translation.

In the translation method based on the selective language recognition process according to the present invention, in the case where the selection of the homonym or the meaning of the synonym is performed through the target language, the translation creation / Or a synonym is replaced with the target language to generate a selective language recognition processing statement; generating the translation by translating the selective language recognition processing statement into the target language; and displaying the translation .

The method according to the present invention is characterized by further comprising the step of recording the selected history information on the homonym or the meaning of the synonym in the selected history information database.

In the translation method based on the selective language recognition process according to the present invention, the selection history information database is constructed in a storage medium provided in the user terminal or in a remote server.

In the translation method based on the selective language recognition process according to the present invention, when the automatic language recognition automatic processing mode is selected by the user, the selection history information recorded in the selection history information database is referred to to determine whether the homonym or the synonym And automatically selects a meaning to generate the translation.

In a preferred embodiment of the present invention, there is provided a translation method based on a selective language recognition process, comprising the steps of: when a user selects an automatic language recognition automatic processing mode, the user terminal transmits a text input by a user to the server; Generating the translation by automatically selecting the homonym or the meaning of the synonym referring to the selection history information recorded in the selection history information database, and transmitting the translation to the user terminal .

In the translating method based on the selective language recognition process according to the present invention, in the case where the original sentence includes a homonym or a synonym, the semantic selection request step may include a step of displaying a sticker corresponding to the homonym or the meaning of the synonym, An emoticon selection is requested.

In the translation method based on the selective language recognition process according to the present invention, in the translation creation step, a translation including a homonym or a sticker or an emoticon corresponding to the meaning of the synonym selected by the user is generated .

In the translation method based on the selective language recognition process according to the present invention, the step of inputting the original text, the step of requesting the meaning selection, and the step of generating / displaying the translation are performed in a user terminal in which a messenger program is executed do.

In the translation method based on the selective language recognition process according to the present invention, the original text input step and the semantic selection request step are performed in a user terminal in which a messenger program is executed, The process of generating the translation is performed by the server requested to be translated from the user terminal, and the process of displaying the translation included in the translation creation / display step is performed by the user terminal that has received the translation from the server .

According to the present invention, by allowing the user to directly select the meaning of the homonym or synonym included in the original text which is the object of machine translation, it is possible to improve the accuracy of the translation and effectively transmit the nuance of the original text to the translation, There is an effect.

In addition, when the original sentence includes a homonym, the translation method based on the selective language recognition process, which can improve the accuracy of translation, is provided by allowing the user to select the true meaning of the homonym word.

In addition, when a synonym is included in the original text, the translation method based on the selective language recognition process is provided that allows the user to directly select the vocabulary to be applied to the translation, thereby allowing the nuance of the original text to be directly transferred to the translation.

1 is a diagram illustrating a translation method based on selective language recognition processing according to an embodiment of the present invention,
2 is a diagram illustrating an example of a configuration of a device in which a translation method based on selective language recognition processing is performed according to an embodiment of the present invention,
FIGS. 3 and 4 are views showing examples of the configuration of the translation generating / displaying unit of FIG. 2,
5 is a diagram illustrating an example of a configuration of a semantic selection request step in an embodiment of the present invention,
6 is a diagram illustrating an example of a configuration of a translation / creation step in a case where selection of a homonym or a meaning of a synonym is performed through an intermediate language in an embodiment of the present invention,
FIG. 7 is a diagram illustrating an example of a configuration of a translation / creation step in a case where selection of a homonym or a meaning of a synonym is performed through a target language in an embodiment of the present invention,
8 is a diagram illustrating an example of a configuration of a selection history information database constructed in a storage medium provided in a user terminal according to an exemplary embodiment of the present invention,
9 is a diagram showing an example of a configuration of a selection history information database constructed in a remote server in an embodiment of the present invention,
10 is a diagram for explaining an example of a processing operation performed in the selective language recognition automatic processing mode in an embodiment of the present invention,
11 is a view for explaining another example of a processing operation performed in the selective language recognition automatic processing mode in an embodiment of the present invention.

It is to be understood that the specific structural or functional description of embodiments of the present invention disclosed herein is for illustrative purposes only and is not intended to limit the scope of the inventive concept But may be embodied in many different forms and is not limited to the embodiments set forth herein.

The embodiments according to the concept of the present invention can make various changes and can take various forms, so that the embodiments are illustrated in the drawings and described in detail herein. It should be understood, however, that it is not intended to limit the embodiments according to the concepts of the present invention to the particular forms disclosed, but includes all modifications, equivalents, or alternatives falling within the spirit and scope of the invention.

The terms first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms may be named for the purpose of distinguishing one element from another, for example, without departing from the scope of the right according to the concept of the present invention, the first element may be referred to as a second element, The component may also be referred to as a first component.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, the terms "comprises" or "having" and the like are used to specify that there are features, numbers, steps, operations, elements, parts or combinations thereof described herein, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, parts, or combinations thereof.

Unless otherwise defined, 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 meaning of the context in the relevant art and, unless explicitly defined herein, are to be interpreted as ideal or overly formal Do not.

Before explaining the preferred embodiments of the present invention, the basic principle of the present invention will be described.

As described above, the conventional machine translation method does not correctly recognize the homonyms because the translation engine automatically translates the words or phrases when the user enters them. In other words, the conventional translation engine recognizes homonyms according to the context up to a certain level, but basically there is a problem in reflecting human intention. Table 1 below shows the results of translating a sentence containing a homonym or homonym into the conventional translation engine.

Original Translation  Fat  Fat  Local people  Fat People  Local people  Local People  Oysters of the local people  Oyster local people  Oyster style of local people  Oysters form of local people

The present invention aims at improving the accuracy of translation by intervening in the intention of the person in the machine translation process and obtaining the translation result as shown in the following Table 2. For example,

Original Translation  Fat  country  Local people  country people  Local people  country people's  Oysters of the local people  country people's oyster  Oyster style of local people  country people's oyster farming

In the conventional machine translation process, there is no process of asking a person's intention. On the other hand, the translation method based on the selective language recognition processing according to the present invention inquires of the person who requested the translation and translates based on the doctor's request.

For example, when a language (source language) is translated into a language other than English (target language), the conventional method and the method according to the present invention are compared as follows.

The conventional approach translates the source language into an intermediate language (usually English) and translates the intermediate language into the target language.

On the other hand, the method according to the present invention converts a source language into a selective language recognition processing sentence, translates an optional language recognition processing statement into an intermediate language (English), translates an intermediate language into a target language do. Selective language recognition processing is generated through the following process. First, a homonym or a synonym is recognized in a text input by a user, a user is requested to select a meaning of the homonym or a synonym, and an optional language (English) is substituted for a homonym or a synonym according to the meaning selected by the user, A recognition processing statement is generated.

The principle of the present invention is summarized as follows.

The present invention proposes a database in which a vocabulary to be recognized as a homonym or a synonym is previously made into a database, and when the homonym or synonym is included in the original text input by the user, a menu that allows the user to select the meaning of the homonym or the synonym do. E.g. For the "earth", you can ask to select one of the planets and the earth. In the database, the earth, which means a planet, is registered as Earth, and the district, which means region, is registered as district. When the user selects a region that represents a region, the translation engine according to the present invention translates the word "district" into "district ". Likewise, "thinking" is also classified as thinking and accident, allowing the user to select the meaning.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a diagram illustrating a translation method based on selective language recognition processing according to an embodiment of the present invention. FIG. 2 is a diagram illustrating an example of an apparatus configuration in which a translation method based on selective language recognition processing according to an embodiment of the present invention is performed. Fig.

1 and 2, a translation method based on the selective language recognition process according to an embodiment of the present invention includes a source text input step S10, a semantic selection request step S20, a translation creation / display step S30, And a selection history information recording step S40.

For example, the translation method based on the selective language recognition process according to an embodiment of the present invention can be performed on a messenger program or a translation-only program executed in a user terminal. The user terminal may be a mobile terminal including a wired or wireless terminal, a general computer used in a certain place, or the like. Hereinafter, a case where a translation method based on selective language recognition processing according to an embodiment of the present invention is performed on a messenger program of a user terminal will be described as an example. In this case, the input unit 10, the meaning selection request unit 20, the translation generation / display unit 30, and the selection history information recording unit 40, which will be described later, may be functional modules implemented in the user terminal, (100) and the selection history information database (200) may be built in a storage medium built in or connected to a user terminal or may be built in a remote server. For example, when translating Korean sentences into English sentences, Korean is the source language and English is the target language. Also, when translating Korean sentences into French sentences, Korean is the source language, French is the target language, and the third language that is not Korean and French is the intermediate language. The medium is preferably a commonly used language, and may be, for example, English, but is not limited thereto.

In the original text input step S10, a process of receiving the original text expressed in the source language through the input unit 10 is performed. For example, if the user is a Korean, the source language may be Korean.

In the meaning selection request step S20, when the semantic selection request unit 20 includes a homonym or a synonym in the original text, a process of requesting the user to select a homonym or a meaning of a synonym is performed.

For example, referring additionally to FIG. 5, the semantic selection request step S20 may be configured to include steps S22 and S24.

In step S22, a process of determining whether the homonym / synonym determination unit 22 includes a homonym or a synonym in the original text is performed by referring to the homonym / synonym database 100.

In step S24, when it is determined that the meaning selection menu display section 24 includes a homonym or a synonym in the original text, the meaning selection section 24 refers to the homonym / synonym database 100 and selects a meaning for selecting the meaning of the homonym or synonym A process of displaying a menu is performed. The semantic selection menu can be divided into a homonym choice menu and a synonym selection menu. The user can directly select a vocabulary having the meaning intended by the homonym selection menu or the synonym selection menu, Can be reflected in the process.

In one example, the choice of the meaning of a homonym or a synonym may be configured to be performed via an intermediate language, which is a third language other than the source language and the target language. For example, the intermediate language may be one of English, Chinese, Japanese, French, Spanish, and German. This configuration method is suitable when the source language and the target language are not commonly used languages. For example, if the source language is Korean and the target language is French, the intermediate language may be English .

As another example, the choice of the meaning of a homonym or synonym may be configured to be performed via the target language. This configuration is appropriate when the target language itself is a popular language. For example, when Korean is a source language and English is a target language, user selection for the meaning of a homonym or a synonym may be performed through a target language, i.e., English, rather than a third language, an intermediate language.

For example, when the original sentence contains a homonym or a synonym, the semantic selection request step requests the user to select a sticker or an emoticon corresponding to the meaning of the homonym or the synonym, And to generate a translation containing a sticker or emoticon corresponding to the meaning of the homonym or the synonym selected by the user.

In the translation creation / display step (S30), the translation creation / display unit 30 translates the original text into the target language according to the meaning of the homonym or the synonym selected by the user, generates a translation, and displays the translation do.

The translation creation / display step S30 can be performed in the following two ways depending on whether the selection of the homonym or the meaning of the synonym is performed through the intermediate language.

3 and 6, when the selection of the meaning of the homonym or synonym is performed through the intermediate language, the translation creation / display step S31 includes steps S312, S314, S316, Step S318.

In step S312, the selective language recognition processing statement generation unit 312 generates a selective language recognition processing sentence by replacing the meaning of the homonym or the synonym included in the original text with an intermediate language selected by the user Process is performed.

In step S314, the intermediate translation generating unit 314 performs a process of translating the selective language recognition processing statement into the intermediate language to generate the intermediate translation.

In step S316, the translation table generation unit 316 translates the intermediate translation into the target language and generates a translation.

In step S318, the process of displaying the translation by the translation display section 318 is performed.

Table 3 below shows an example of a source text including a homonym, an optional language recognition processing, an intermediate translation, and a translation when the source language is Korean, the target language is French, and the intermediate language is English.

division Contents Original  Access to the 10km radius of the accident district was restricted. Selective language recognition processing statement  There is a limit of access to the 10 km radius of the accident district. An intermediate translation  This approach limits 10 km. Translation  It is 10 km away from the hotel. Interpret translation  This access restriction is carried out in the accident zone of 10 km.

In the example described in Table 3, for accidents of homonyms, the user selected accident through the semantic selection menu, and for districts of homonyms, the user selected district through the semantic selection menu. The selective language recognition processing statement generating unit 312 generates an optional language recognition processing statement by reflecting accident and district selected by the user in the original text and the intermediate translation generating unit 314 translates the selective language recognition processing word into English And the translation creation unit 316 translates the intermediate translation into French and creates a translation.

As another example, referring additionally to FIGS. 4 and 7, if selection of the meaning of the homonym or synonym is performed through the target language, the translation creation / display step S32 includes steps S322, S324, and S316 .

In step S322, the process of generating the selective language recognition processing statement by replacing the meaning of the homonym or synonym included in the original text with the target language selected by the user is performed by the selective language recognition processing statement generation unit 322. [

In step S324, the translation-text generation unit 324 translates the selective language recognition processing sentence into the target language and generates a translation.

In step S316, the process of displaying the translated text by the translated text display unit 326 is performed.

Table 4 below shows an example of a source text including a homonym, an optional language recognition processing statement, and a translation when the source language is Korean and the target language is English, that is, when there is no separate intermediate language.

division Contents Original  Access to the 10km radius of the accident district was restricted. Selective language recognition processing statement  There is a limit of access to the 10 km radius of the accident district. Translation  This approach limits 10 km. Interpret translation  This access restriction is carried out in the accident zone of 10 km.

In the example shown in Table 4, for an accident with a homonym, the user selected accident through the semantic selection menu and the user selected district through the semantic selection menu for the homonym. The selective language recognition processing statement generating unit 322 generates an optional language recognition processing statement by reflecting accident and district selected by the user in the original text, and the mediating unit 324 translates the selective language recognition processing statement into English Create a translation.

Meanwhile, the present invention can be applied to synonyms in addition to homonyms. It can be applied to the language (语言), the slang language (abbreviated slang), abbreviation, gore, spoken language, dialect, etc., and the selection procedure may be omitted. For example, when a selection procedure for a profanity is included, it may be selected whether to translate the profanity into a profanity or a standard language.

The following table 5 is a colloquial example when translating Korean into English, and the machine translation engine is a google translator.

division Contents Original  Oh, but it's nice to have you. Translation  Oh Dang Zola but I ㅇㅋ ㅋㅋ

Referring to Table 5, according to the conventional translation engine, it can be seen that meaningless translation is generated when the word is not a standard word.

For example, according to the present invention, oki and okay can be selected from oki and okay, and it is possible to choose between fucking and really about zola, and annoying without choosing for the elderly, and lol and lola about kola. .

For example, if a user wishes to translate the meaning of profanity, oki, fucking, and lol can be selected respectively, and the original text, the selective language recognition processing statement, and the translation thereof are shown in Table 6 below.

division Contents Original  Oh, but it's nice to have you. Selective language recognition processing statement  oh oki your fucking annoying lol Translation  But you fucking annoying lol oh oki

Referring to Table 6, it can be seen that English translation effectively conveys the meaning and nuance of Korean.

For example, if the user wants to convey the meaning only in the standard language, it is possible to select okay, really, :), and the text, selective language recognition processing and translation are shown in Table 7 below.

division Contents Original  Oh, but it's nice to have you. Selective language recognition processing statement  oh okay but you really annoying :) Translation  oh okay but you really annoying :)

The translations in Tables 6 and 7 are all the results of the user's selection of synonyms of profanity, and both confirm that almost complete communication is possible.

In the selection history information recording step S40, a process of recording the selection history information on the meaning of the homonym or synonym in the selection history information recording unit 40 to the selection history information database 200 is performed. As will be described later, this selection history information can be used to support an automatic selection function for the meaning of a homonym or a synonym.

For example, the selection history information database 200 may be built on a storage medium provided in a user terminal or may be constructed on a remote server. The storage medium included in the user terminal may be an internal storage medium embedded in the user terminal, or an external storage medium connected in a wired or wireless manner.

FIG. 8 is a diagram illustrating an example of a configuration of a selection history information database 200 constructed in a storage medium provided in a user terminal according to an exemplary embodiment of the present invention. In FIG. 10, FIG. 8 is a diagram for explaining an example of a processing operation performed in the selective language-aware automatic processing mode; FIG.

8, a specific user uses the homonym of rice five times in the meaning of meal, once in the meaning of the name of person Bob, and uses the homonym of the earth as the planet Earth, It was used once in the meaning and 7 times in the meaning of district. Such selection history information can be used as information for estimating the meaning of the homonyms input by a specific user, and the reliability of the estimation is increased in proportion to the cumulative number of choices for meaning. For example, when a specific user inputs an unambiguous term such as rice or district, the meal and district having a large number of selections are automatically selected so that the convenience of the user can be improved. An example of the operation of the selective language recognition automatic processing mode using the semantic estimation will be described below.

10, in step S110, a process of the user selecting the automatic language recognition automatic processing mode on the interface screen is performed. The selective language recognition automatic processing mode is a processing mode for automatically selecting an homonym or synonym by referring to the selection history information accumulated in the selection history information database 200 without directly selecting the homonym or synonym every time by the user.

In step S120, a process of inputting the original text desired by the user for translation is performed. The processing sequence of steps S110 and S120 may be changed.

In step S130, the process of automatically selecting the meaning of the homonym is performed by referring to the selection history information recorded in the selection history information database 200. [ For example, this step may be configured to select the meaning with the greatest number of selections. The same applies to synonyms.

In step S140, a process of translating the original text into the target language according to the meaning of the automatically selected homonym, and displaying the generated translation is performed. For example, the step S140 may be configured to include the above-described steps S312, S314, S316, and S318, or may be configured to include the steps S322, S324, and S326.

FIG. 9 is a diagram illustrating an example of a configuration of a selection history information database 200 constructed in a remote server according to an exemplary embodiment of the present invention. FIG. Fig. 8 is a diagram for explaining another example of the processing operation performed in the processing mode.

9, in the selection history information database 200 built in the remote server, all the selection history information is stored for each user. More specifically, user A used the homonym of rice five times in the meaning of meal, used once in the meaning of the name of the person Bob, and used the word homonym of the earth in the sense of the planet Earth (Earth) And was used 7 times in the meaning of district. In addition, user B uses the homonym of rice once in the meaning of meal, ten times in the meaning of the name of the person Bob, and uses the homonym of the earth in the sense of the planet earth (earth) 12 times And 7 times in the meaning of district. Such selection history information can be used as information for estimating the meaning of the homonyms input by a specific user, and the reliability of the estimation is increased in proportion to the cumulative number of choices for meaning. For example, when the user A inputs a disambiguation term such as Bob or Earth, the meal and district having a large number of selections are automatically selected as the meaning thereof. When the user B inputs an unambiguous term such as Bob or Earth, Bob , And Earth are automatically selected so that user convenience related to meaning selection can be improved. An example of the operation of the selective language recognition automatic processing mode using the semantic estimation will be described below.

11, in step S210, a process of the user selecting the automatic language recognition automatic processing mode on the interface screen is performed. The selective language recognition automatic processing mode is a processing mode for automatically selecting an homonym or synonym by referring to the selection history information accumulated in the selection history information database 200 without directly selecting the homonym or synonym every time by the user.

In step S220, a process of inputting the original text desired by the user for translation is performed. The processing sequence of steps S210 and S220 may be changed.

In step S230, a process is performed in which the user terminal transmits the original text input by the user to a server located at a remote location while requesting translation.

In step S240, the server refers to the selection history information recorded in the selection history information database 200, and performs a process of automatically selecting the meaning of the homonym. For example, this step may be configured to select the meaning with the greatest number of selections. The same applies to synonyms.

In step S250, a process of translating the original text into the target language and generating a translation according to the meaning of the automatically selected homonym is performed. For example, the step S250 may be configured to include the above-described steps S312, S314, and S316, or may be configured to include the steps S322 and S324.

In step S260, the server transmits the generated translation to the user terminal.

As an example, the above-described text input step S10, the meaning selection request step S20, and the translation creation / display step S30 are performed in a messenger program or a user terminal in which a translation-only program is executed .

As another example, the process of inputting the original text (S10) and requesting the meaning selection (S20) is performed in the user terminal where the messenger program or the translation-only program is executed and the translation included in the translation creation / display step S30 The process of performing translation at the server requested by the user terminal and displaying the translation included in the translation creation / display step S30 may be performed at the user terminal that has received the translation from the server.

As described above in detail, according to the present invention, by allowing the user to directly select the meaning of the homonym or synonym included in the original text, which is the object of machine translation, the accuracy of the translation can be enhanced and the nuance of the original text can be effectively transmitted to the translation So that the overall quality can be improved.

In addition, when the original sentence includes a homonym, the translation method based on the selective language recognition process, which can improve the accuracy of translation, is provided by allowing the user to select the true meaning of the homonym word.

In addition, when a synonym is included in the original text, the translation method based on the selective language recognition process is provided that allows the user to directly select the vocabulary to be applied to the translation, thereby allowing the nuance of the original text to be directly transferred to the translation.

10: Input unit
20: Meaning selection request unit
22: homophone / synonym judge
24: Meaning selection menu display
30, 31, 32: translation / display unit
40: selection history information recording section
100: Homonym surrogate / synonym database
200: selection history information database
312, 322: an optional language recognition processing statement generating unit
314:
316, 324:
318, 326:
S10: Inputting the original text
S20: Meaning selection step
S30, S31, S32: Create / Display Translation
S40: Selection history information recording step

Claims (14)

A source text input step of inputting a source text expressed in a source language;
A semantic selection request step of requesting the user to select the homonym or the meaning of the synonym if the original text includes a homonym or a synonym; And
And displaying and displaying the translation created by translating the original text into the target language according to the homonym or the meaning of the synonym selected by the user. The method according to claim 1,
The semantic selection request step
Determining whether the homonym or the synonym is included in the original text by referring to a homonym / synonym database; And
And displaying a semantic selection menu for selecting the homonym or the meaning of the synonym by referring to the homonym / synonym database if it is determined that the homonym or the synonym is included in the original text Wherein the translation is based on an optional language recognition process. The method according to claim 1,
Wherein the selection of the homonym or the meaning of the synonym is performed through an intermediate language that is a third language other than the source language and the target language or through the target language. How to translate. The method of claim 3,
Wherein the intermediate language is one of English, Chinese, Japanese, French, Spanish, and German. The method according to claim 1,
When the selection of the homonym or the meaning of the synonym is performed through the intermediate language,
The step of generating / displaying the translated text
Generating an optional language recognition processing statement by replacing the meaning of a homonym or a synonym included in the original text with the intermediate language;
Translating the selective language recognition processing statement into the intermediate language to generate an intermediate translation;
Translating the intermediate translation into the target language to generate the translation; And
And displaying the translated text based on the selected language recognition process. The method according to claim 1,
When the selection of the homonym or the meaning of the synonym is performed through the target language,
The step of generating / displaying the translated text
Generating a selective language recognition processing statement by replacing the meaning of a homonym or a synonym included in the original text with the target language;
Translating the selective language recognition processing statement into the target language to generate the translation; And
And displaying the translated text based on the selected language recognition process. The method according to claim 1,
Further comprising a selection history information recording step of recording selection history information on the homonym or the meaning of the synonym in the selection history information database. 8. The method of claim 7,
Wherein the selection history information database is constructed on a storage medium provided in the user terminal or on a server at a remote location. 8. The method of claim 7,
When the automatic language recognition automatic processing mode is selected by the user,
Wherein the translation history is generated by automatically selecting the homonym or the meaning of the synonym by referring to the selection history information recorded in the selection history information database. 8. The method of claim 7,
When the automatic language recognition automatic processing mode is selected by the user,
Transmitting the original text entered by the user terminal to the server;
The server automatically selecting the homonym or the meaning of the synonym by referring to the selected history information recorded in the selected history information database to generate the translated text; And
And the server transmitting the translation to the user terminal. ≪ RTI ID = 0.0 > 15. < / RTI > The method according to claim 1,
In the semantic selection request step,
Wherein when the original text includes a homonym or a synonym, the user is requested to select a sticker or an emoticon corresponding to the homonym or the meaning of the synonym. 12. The method of claim 11,
In the translation creating step,
And generating a translation including a sticker or an emoticon corresponding to the homonym or the meaning of the synonym selected by the user. The method according to claim 1,
Wherein the step of inputting the original text, the step of selecting the meaning, and the step of generating / displaying the translation are performed in a user terminal in which a messenger program is executed. The method according to claim 1,
The original text input step and the semantic selection request step are performed in a user terminal in which a messenger program is executed,
The step of generating the translation included in the translation creation / display step may be performed in the server requested to be translated from the user terminal,
Wherein the step of displaying the translation included in the translation creation / display step is performed by the user terminal that has received the translation from the server.

Images