JP2014075005A - Information processor, information processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processor, an information processing method and a program capable of suitably converting notations into language with no long sound even in the case of a Japanese text including long sounds.SOLUTION: The information processor includes: an input part 101 for accepting the input of a text including Chinese characters and the reading KANA of the text; a long sound Chinese character determination part 107 for determining whether or not long sound Chinese characters are included in the text; a long sound KANA determination part 103 for determining whether or not long sound KANA characters are included in the reading KANA; a long sound determination part 111 for, when the long sound Chinese characters are included in the text and the long sound KANA characters are included in the reading KANA as the result of determination, and when the reading of the long sound Chinese characters is coincident with the long sound KANA characters, specifying the long sound Chinese characters and the long sound KANA characters as long sounds; and a translation part 113 for converting the reading KANA into notations in language with no long sound in accordance with whether or not long sounds are included.

Description

  Some embodiments according to the present invention relate to an information processing apparatus, an information processing method, and a program.

In recent years, devices that translate between Japanese and other languages are becoming popular. Here, there are long sounds in Japanese, but there are no long sounds in languages such as English, Korean, Thai, etc. There is a case.
In order to cope with such a problem, for example, Patent Document 1 discloses an apparatus that adds a long sound that is omitted when converting a Roman character into a kana character string.

Japanese National Patent Publication No. 2008/072734

  However, the method described in Patent Document 1 only considers the case of converting from Roman alphabet notation to kana notation character string, and does not consider any notation from Japanese notation to another language.

  Some aspects of the present invention have been made in view of the above-mentioned problems, and even a Japanese text containing a long sound can be suitably converted into a language without a long sound. An object is to provide an information processing apparatus, an information processing method, and a program.

  An information processing system according to the present invention includes an input unit that receives input of a text including a kanji and a kana for the text, and a first determination unit that determines whether or not the text includes a long kanji. The second discrimination means for discriminating whether or not the phonetic kana is included in the phonetic kana, and, as a result of the discrimination, the text contains a long kanji and the phonetic kana is contained in the kana And if the reading of the long kana matches the long kana, the means for identifying the long kanji and the long kana as a long sound, and whether the kana includes a long sound And means for converting into a notation of a language without a long sound.

  An information processing method according to the present invention includes a step of receiving a text including a kanji and a kana character of the text, a step of determining whether or not a long kanji is included in the text, A step of determining whether or not a long kana is included, and as a result of the determination, the text includes a long kanji and the kana includes a long kana, Identifying a kana kanji as a long sound when the reading matches the long kana, and converting the kana to a notation of a language without a long sound depending on whether or not a long sound is included; Is performed by the information processing apparatus.

  The program according to the present invention includes a step of receiving a text including a kanji and a kana character of the text, a step of determining whether or not the text includes a kana kanji, and a kana kana in the kana And the result of the determination is that the text includes a long kanji and the kana includes a long kana, and the long kanji is read. A step of identifying the kana kanji as a long sound when matching the kana with the long sound kana, and converting the kana to a notation of a language without a long sound depending on whether or not the kana is included It is a program for making it run.

  In the present invention, “part”, “means”, “apparatus”, and “system” do not simply mean physical means, but “part”, “means”, “apparatus”, “system”. This includes the case where the functions possessed by "are realized by software. Further, even if the functions of one “unit”, “means”, “apparatus”, and “system” are realized by two or more physical means or devices, two or more “parts” or “means”, The functions of “device” and “system” may be realized by a single physical means or device.

  According to the present invention, it is possible to provide an information processing apparatus, an information processing method, and a program capable of suitably converting a notation into a language without a long sound even if it is a Japanese text including a long sound. Can do.

It is a figure for demonstrating the process in embodiment of this invention. It is a figure which shows the structure of the information processing apparatus in embodiment of this invention. It is a figure which shows the specific example of the long sound vowel kana dictionary shown in FIG. It is a figure which shows the specific example of the long sound Chinese character dictionary shown in FIG. 3 is a flowchart for explaining a processing flow of the information processing apparatus illustrated in FIG. 2. It is a block diagram which shows the structure of the hardware which can mount the information processing apparatus shown in FIG.

  Embodiments of the present invention will be described below. In the following description and the description of the drawings to be referred to, the same or similar components are denoted by the same or similar reference numerals.

(Embodiment)
1 to 6 are diagrams for explaining the embodiment. Hereinafter, embodiments will be described along the following flow with reference to these drawings. First, an outline of processing performed by the information processing apparatus according to the embodiment is described as “1”. Then, “2” describes the system configuration of the information processing apparatus, and “3” describes the processing flow. “4” indicates a specific example of a hardware configuration capable of mounting the system. Finally, the effects and the like according to the present embodiment will be described after “1.5”.

(1 Overview)
When machine-translating Japanese text into another language, for example, when a place name, a person's name, or an address is included in the text, the part is not usually translated and only the notation is changed. However, if you try to change the notation from Japanese to English, Korean, Thai, etc., Japanese will have long sounds, but English, Korean, Thai, etc. will not have long sounds, causing problems. There is a case.

  For example, when “Tokyo” (Tokyo) or “Osaka” (Osaka) is written in English (in Roman letters), it is usually written as “Tokyo” or “Osaka” instead of “Tokyokyo” or “Oosaka”. To do. This is because some syllables followed by a vowel (a line) (eg “Tokyo” “Tou” and “Kyo”, Osaka “Oo”) are pronounced in a long sound. Because there is no long sound, it is more natural to omit the vowels.

  In order to deal with cases such as “Osaka”, it may be possible to mechanically delete the vowels connected to the vowel line in the reading kana, but such a method is also inconvenient. For example, “Nagame” and “Yu” (Yu) are treated as “Nagame” because “Aga” and “Yu” are treated as long sounds by using a method of simply deleting vowels connected to the vowel line. Indicated as “Yu”. However, considering from the notation of kanji, it should be expressed as “Nagaame” “Yuu”.

  Therefore, the information processing apparatus according to the present embodiment determines whether or not the sound is a long sound in consideration of both kanji notation and kana kana (kana notation). Hereinafter, this method will be described with reference to FIG. FIG. 1 is a diagram for explaining an outline of the long sound determination performed by the information processing apparatus according to the present embodiment.

The information processing apparatus according to the present embodiment receives two types of input: Japanese text including kanji and a Japanese kana (reading kana) of the Japanese text. In the example of FIG. 1, the Japanese text “Tokyo Sky Tree” and the phonetic name “TOKYO KASUKA DAI” are input to the information processing apparatus.
The information processing apparatus performs a long sound determination in order from the top of both the Japanese text and the phonetic kana. This will be specifically described below.

  For Japanese text, the first character “East” is first identified as a long kanji (whether or not it is a kanji whose reading can be a long sound) with reference to the long kanji dictionary. Here, the long sound kanji dictionary is a dictionary that associates kanji that can be long sound (long sound kanji) with the reading kana (long kana) at the time of the long sound. Details of the long-tone kanji dictionary will be described later with reference to FIG.

  For furigana, it is a string of 2 or more characters (usually 2 or 3 characters) that end with a vowel (a line) and may be pronounced as a long sound (long sound reading) Is determined with reference to the long vowel kana dictionary in order from the top. In the example shown in FIG. 1, the first two letters “To” are the long-tone kana. The long sound vowel kana dictionary is a dictionary for identifying long sound kana. Details of the long vowel kana dictionary will be described later with reference to FIG.

  If the long-tone kanji specified for the Japanese text (“East” in the example of FIG. 1) is the same as the long-tone kana specified for the phonetic kana, “East” to be read can be specified as a kanji for long sound reading.

  Although not shown in FIG. 1, in the case of the text “Tokyo Skytree” and the pseudonym “Toyosuka Kadari”, “Kyo” is read as “Kyo” by continuing the processing after “East” and “Toyo”. “Kyo” can also be specified as a kanji for long sound reading.

  If the long sound can be identified in this way, the information processing apparatus can convert the notation to another language in accordance with this. That is, among “Tokyo”, “Tou” and “Kyo” are long sounds, respectively. For example, when this is written in English (Roman alphabet), the information processing apparatus displays a suitable notation “Tokyo” with each vowel part dropped. Can be created.

  In the description according to the present embodiment, a case where Japanese notation is converted to English notation will be described as an example. However, the present invention is not limited to this, and any language that does not have a long sound, such as Korean or Thai. Applicable.

(2 System overview)
FIG. 2 is a diagram illustrating a schematic configuration of the information processing apparatus 100 according to the present embodiment. As described above, the information processing apparatus 100 is a device having a function of converting Japanese notation into another notation, and can be realized as, for example, a personal computer or a server. The data that the information processing apparatus 100 converts from Japanese to multilingual data includes various information such as place names, addresses, store names, station names, road names, and facility names related to map data, person names, and the like. Conceivable.

  As illustrated in FIG. 1, the information processing apparatus 100 includes an input unit 101, a long sound kana determination unit 103, a long sound vowel kana dictionary 105, a long sound kanji determination unit 107, a long sound kanji dictionary 109, a long sound determination unit 111, and a translation unit 113. Including.

  The input unit 101 receives an input of Japanese text including kanji and a kana (reading kana) of the Japanese text. Various input methods can be considered. For example, the input may be received directly from the user by an input device such as a keyboard, or may be recorded on a storage medium such as an HDD (Hard Disk Memory) or a flash memory. Reading data is also conceivable.

  The long sound kana determination unit 103 identifies a character string that can be a long sound kana included in the phonetic kana received by the input unit 101. As described above, the long sound kana is a character string of two or more characters that end with a vowel (a line) and may be pronounced as a long sound.

  At this time, the long sound kana determination unit 103 refers to the long sound vowel kana dictionary 105 and determines whether the character string included in the phonetic kana is a character string included in the long sound vowel kana dictionary 105. , Identify the long kana.

  The long sound vowel kana dictionary 105 is a dictionary for specifying the long sound kana as described above. FIG. 3 shows a specific example of the long vowel kana dictionary 105. In the long vowel kana dictionary 105 in the example of FIG. 3, a vowel is associated with a character that can be a long sound when it comes before the vowel. For example, in the case of “a”, characters such as “a”, “ka”, “sa”, “ta”, and “na” are associated. This is because "ah" "ka" "sah" "taa" "naa" etc., the strings are long kana, that is, if these strings are included in the kana, they can be long Is shown.

  The long sound kanji determination unit 107 specifies a character string that can be a long sound kanji included in the Japanese text input by the input unit 101. The long kanji is a kanji that can be read as long as described above.

  At this time, the long sound kanji determination unit 107 refers to the long sound kanji dictionary 109 and determines whether or not the character included in the Japanese text is a character included in the long sound kanji dictionary 109. Is identified.

  As described above, the long-tone kanji dictionary 109 is a dictionary for identifying long-tone kana. FIG. 4 shows a specific example of the long sound Chinese character dictionary 109. In the long-span kanji dictionary 109 in the example of FIG. 4, a kanji that can be a long sound is associated with a reading kana when it is a long sound. For example, in the example of FIG. 4, “sound” and “rice” are long kanji characters that can be long sound, and when they are long sound, they are read as “ah” or “good”, etc. Can be understood by referring to the long-tone kanji dictionary 109.

  The long sound determination unit 111 determines whether the sound is actually a long sound based on the determination results of the long sound kana determination unit 103 and the long sound kanji determination unit 107. More specifically, when the kana character determining unit 103 determines that the kana character includes a long kana character, and the long sound kanji determining unit 107 determines that a kana character character is included, the long sound kanji character is used. When the reading kana at the time of the long sound coincides with the long sound kana, the long sound determination unit 111 determines that the sound is a long sound. A specific example is as described above with reference to FIG.

  The translation unit 113 converts the notation into a predetermined language based on the determination result by the long sound determination unit 111. For example, when converting “Tokyo” into English notation, as described above, the long sound vowel from “Tokyo” is determined by the long sound determination unit 111 that “To” and “Kyou” are long sounds. Based on the “time” excluding (the character on the line), the translation unit 113 converts the notation to “Tokyo”.

(3 Process flow)
Hereinafter, the processing flow of the information processing apparatus 100 will be described with reference to FIG. FIG. 5 is a flowchart showing the flow of the long sound determination process in the information processing apparatus 100. In the example of FIG. 5, processing related to notation conversion (translation) is omitted.

Here, each processing step, which will be described later, can be executed in any order or in parallel as long as there is no contradiction in processing contents, and other steps are added between the processing steps. Also good. Further, a step described as a single step for convenience can be executed by being divided into a plurality of steps, and a step described as being divided into a plurality of steps for convenience can be executed as one step.
First, the input unit 101 receives an input of a Japanese text including kanji and a Japanese kana (reading kana) (S501).

  The long sound kana determination unit 103 extracts a character string from the beginning of the phonetic kana and compares it with the long sound vowel kana dictionary 105 (S503). In the example of FIG. 1 described above, the long vowel kana dictionary 105 is referred to for “to”, which is the first character string of the phonetic kana.

  As a result, if the extracted character string is not included in the long sound vowel kana dictionary 105 (that is, if it is not the long sound kana) (No in S505), the long sound kana determination unit 103 determines the first character of the kana from the kana After deletion (S507), if unprocessed pseudonym still remains (Yes in S509), the process returns to S503.

  If the character string extracted from the phonetic kana is a long sound kana (Yes in S505), the long sound kanji determination unit 107 targets the first character of the Japanese text ("east" in the example of FIG. 1). In addition, the long-tone kanji dictionary 109 is referred to.

  As a result, if the extracted character does not exist in the long-span kanji dictionary 109 (No in S513), it means that the character is not a long-span kanji, so the long-span kanji determination unit 107 deletes the character from the text (S515). If unprocessed text still remains (Yes in S517), the process returns to S511.

  If the character extracted from the text is a long Chinese character (S513), the long sound determination unit 111 reads the long Chinese character at the time of the long sound ("To" in the example of FIG. 1), and identifies it in S505. The long kana that has been made ("To" in the case of FIG. 1) is compared (S519). As a result, if a long-sword is included in a long-sword kanji reading of a long-sword (if there is a match), it can be determined that the long-span kanji and long-sword Kana are longs (Yes in S521). The long sound determination unit 111 transcribes the long sound kanji and the long sound kana as being a long sound (S523), and deletes the long sound kanji and the long sound kana from the original text and the kana (S525). Thereafter, if an unprocessed pseudonym still remains (Yes in S509), the process returns to S503.

  If a long kana is not included in the reading of the specified long kanji in S521, it means that the long kanji is not read (No in S521), and the long kanji is deleted from the text. (S515), if unprocessed text still remains (Yes in S517), the process returns to S511.

  As a result of repeating the processing of S503 to S517, when all of the processing of at least one of the kana or text ends (No in S509 or No in S517), all the processing related to the long sound determination ends.

(4 hardware configuration)
Hereinafter, an example of a hardware configuration when the information processing apparatus 100 described above is realized by a computer will be described with reference to FIG. Note that the functions of the information processing apparatus 100 can be realized by being divided into a plurality of apparatuses via a network.

  As illustrated in FIG. 6, the information processing apparatus 100 includes a processor 601, a memory 603, a storage device 605, an input I / F (Interface) 607, a data I / F 609, a communication I / F 611, and a display device 613.

  The processor 601 controls various processes in the information processing apparatus 100 by executing a program stored in the memory 603. For example, the input unit 101, the long sound kana determination unit 103, the long sound kanji determination unit 107, the long sound determination unit 111, and the translation unit 113 described in FIG. 2 are temporarily stored in the memory 603 and mainly on the processor 601. It can be realized as an operating program.

  The memory 603 is a storage medium such as a RAM (Random Access Memory). The memory 603 temporarily stores a program code of a program executed by the processor 601 and data necessary for executing the program. For example, in the storage area of the memory 603, a stack area necessary for program execution is secured.

  The storage device 605 is a non-volatile storage medium such as a hard disk or a flash memory. The storage device 605 includes an operating system, various programs for realizing the input unit 101, the long sound kana determination unit 103, the long sound kanji determination unit 107, the long sound determination unit 111, and the translation unit 113, the long sound vowel kana dictionary 105, and the long sound. Various data such as a database for realizing the Chinese character dictionary 109 is stored. Programs and data stored in the storage device 605 are referred to by the processor 601 by being loaded into the memory 603 as necessary.

  The input I / F 607 is a device for receiving input from the user. Specific examples of the input I / F 607 include a keyboard, a mouse, a touch panel, and various sensors. The input I / F 607 may be connected to the information processing apparatus 100 via an interface such as a USB (Universal Serial Bus).

  The data I / F 609 is a device for inputting data from outside the information processing apparatus 100. Specific examples of the data I / F 609 include a drive device for reading data stored in various storage media. The data I / F 609 may be provided outside the information processing apparatus 100. In that case, the data I / F 609 is connected to the information processing apparatus 100 via an interface such as a USB.

  The communication I / F 611 is a device for performing data communication with an external device of the information processing apparatus 100 by wire or wireless. The communication I / F 611 may be provided outside the information processing apparatus 100. In that case, the communication I / F 611 is connected to the information processing apparatus 100 via an interface such as a USB.

  The display device 613 is a device for displaying various information. For example, the text converted by the translation unit 113 may be displayed on the display device 613. Specific examples of the display device 613 include a liquid crystal display and an organic EL (Electro-Luminescence) display. The display device 613 may be provided outside the information processing apparatus 100. In that case, the display device 613 is connected to the information processing apparatus 100 via, for example, a display cable.

(5 Effects of this embodiment)
As described above, the information processing apparatus 100 according to the present embodiment checks the presence or absence of a long kanji in Japanese text and the presence or absence of a long kana for a Japanese phonetic kana, and then reads the long kanji as a long kana. If they match, the long kanji and long kana are identified as long sounds.

  That is, since both the kana notation and the kanji notation are used, it is possible to suitably specify the long sound, and as a result, it is possible to suitably convert the notation into a multilingual with no long sound. For example, when “Tokyo” or “Osaka” is written in English, “Tokyo” or “Osaka” can be written instead of “Tokyokyo” or “Oosaka”, and “long rain” or “Yu” is written in English. Can be expressed as “Nagaame” or “Yuu”.

(6 Appendix)
Note that the configurations of the above-described embodiments may be combined or some components may be replaced. The configuration of the present invention is not limited to the above-described embodiment, and various modifications may be made without departing from the scope of the present invention.

  DESCRIPTION OF SYMBOLS 100 ... Information processing apparatus, 101 ... Input part, 103 ... Long sound kana determination part, 105 ... Long sound vowel kana dictionary, 107 ... Long sound kanji determination part, 109 ... Long sound kanji dictionary, DESCRIPTION OF SYMBOLS 111 ... Long sound determination part, 113 ... Translation part, 601 ... Processor, 603 ... Memory, 605 ... Storage device, 607 ... Input interface, 609 ... Data interface, 611 ..Communication interface, 613 ... Display device

Claims (5)

An input means for receiving input including a text including kanji and a kana for the text;
First discriminating means for discriminating whether or not a long kanji character is included in the text;
Second discriminating means for discriminating whether or not the phonetic kana is included in the phonetic kana;
As a result of the determination, when the text includes a long kana and the kana includes a long kana, and the reading of the long kana matches the long kana, the long kanji and Means for identifying the long kana as a long sound;
An information processing apparatus comprising: means for converting the phonetic pseudonym into a notation of a language without a long sound depending on whether or not a long sound is included. The first determining means determines whether or not the text includes a long sound kanji character by referring to a long sound kanji dictionary that associates a long sound kanji character with a reading for the character included in the text.
The information processing apparatus according to claim 1. The second discriminating means refers to a long phonetic kana in the phonetic kana by referring to a long vowel kana dictionary related to a combination of a long vowel and another character with respect to consecutive characters included in the phonetic kana. Whether or not is included,
The information processing apparatus according to claim 1 or 2. Receiving a text containing kanji and a kana for the text;
Determining whether the text contains long kanji characters; and
Determining whether the phonetic kana is included in the phonetic kana;
As a result of the determination, if the text includes a long kana and the kana includes a long kana, and the reading of the long kana matches the long kana, the long kanji is Identifying as a long sound,
An information processing method in which an information processing apparatus performs a step of converting the phonetic name into a notation of a language without a long sound depending on whether or not a long sound is included. Receiving a text containing kanji and a kana for the text;
Determining whether the text contains long kanji characters; and
Determining whether the phonetic kana is included in the phonetic kana;
As a result of the determination, if the text includes a long kana and the kana includes a long kana, and the reading of the long kana matches the long kana, the long kanji is Identifying as a long sound,
A program for causing a computer to execute a step of converting the phonetic name into a notation of a language without a long sound depending on whether or not a long sound is included.