JP2014120007A - Dictionary registration device, word division device, dictionary registration method, word division method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a dictionary for word division having a higher degree of precision than the conventional dictionary.SOLUTION: A dictionary for word division with a higher degree of precision can be obtained from a dictionary registration device which includes: a dictionary for word division which can store one or more division information composed of a set of one or more words and two or more division words; a first division result acquisition unit for acquiring a first division result from one word division device; an other division result acquisition unit for acquiring two or more other division information from two or more of other word division devices; a different portion acquisition unit for acquiring one or more different portions between the first division result and the two or more other division results; a division information acquisition unit which, if one or more different portions satisfy a predetermined condition, configures division information including a word which is a character string corresponding the different portions and two or more words which are the different portions; and a dictionary registration unit for accumulating the division information in the dictionary for word division.

Description

  The present invention relates to a dictionary registration device that registers information in a word division dictionary used by a word division device that divides a sentence into two or more words.

  Conventionally, there has been a dictionary creation system that absorbs differences in the description format of various input data and registers them in common in each dictionary item (see Patent Document 1).

  In addition, there is a machine learning system that can remove unnecessary data from learning data to improve accuracy (see Patent Document 2).

JP 2006-215823 A (first page, FIG. 1 etc.) Japanese Patent Laying-Open No. 2005-181928 (first page, FIG. 1 etc.)

  However, the conventional technique cannot obtain a word segmentation dictionary with high accuracy.

  The dictionary registration device according to the first aspect of the present invention is a word division dictionary that can store one or more words and one or more pieces of division information that is a set of two or more divided words that is a result of dividing the words. , A first division result acquisition unit that acquires a first division result that is a result of dividing one sentence by one word dividing device, and two or more other word dividing devices that are word dividing devices that are not one word dividing device Are the other division result acquisition unit for acquiring two or more other division results that are the result of dividing one sentence, and the part included in each of the two or more other division results, the first division result and each of the two or more When a different part acquisition unit that acquires one or more different parts that are different from other division results and one or more different parts acquired by the different part acquisition unit satisfy a predetermined condition, either one or more A word that is a character string corresponding to the difference part. A dictionary registration apparatus comprising the division information acquisition unit that constitutes the division information having 2 or more and the word is a different part, and a dictionary registration unit for storing divided information into words divided dictionary.

  With this configuration, a highly accurate word segmentation dictionary can be obtained.

  In addition, the dictionary registration device of the second invention is different from the first invention in that the other division result acquisition unit acquires the second division result and the third division result, which are two other division results, The partial acquisition unit acquires a first difference portion that is a difference portion between the first division result and the second division result, and a second difference portion that is a difference portion between the first division result and the third division result, When the first difference portion and the second difference portion are common, the division information acquisition unit uses the first difference portion, and is a word that is a character string corresponding to the first difference portion, and the first difference portion is 2 It is a dictionary registration apparatus which comprises the division | segmentation information which has the above word.

  With this configuration, a highly accurate word segmentation dictionary can be obtained.

  In addition, the word dividing device according to the third aspect of the present invention is a word constituted by a dictionary registration device, a reception unit that accepts a sentence having one or more characters, and a dictionary registration device with respect to the first or second invention. Using the division dictionary, the word having the maximum length matching the character string constituting the sentence received by the reception unit is acquired from the word division dictionary, and two or more divided words corresponding to the acquired word are acquired. Thus, the word division device includes a first division unit that acquires a first division result that is a set of two or more words obtained by dividing a sentence, and an output unit that outputs the first division result.

  With this configuration, it is possible to divide a sentence into two or more words at high speed using a highly accurate word division dictionary.

  The word segmentation device according to the fourth aspect of the present invention is a word segmentation device further comprising two or more other word segmentation units with respect to the third aspect.

  With this configuration, it is possible to divide a sentence into two or more words at high speed using a highly accurate word division dictionary.

  According to the dictionary registration device of the present invention, it is possible to obtain a word segmentation dictionary with high accuracy.

Block diagram of word segmentation apparatus 1 according to Embodiment 1 A flowchart for explaining the operation of the word segmentation apparatus 1 The figure which shows the dictionary 11 for the word division | segmentation The figure which shows the experimental result of the same word division | segmentation apparatus 1 The figure which shows the experimental result of the same word division | segmentation apparatus 1 Block diagram of dictionary registration apparatus 2 in the second embodiment The flowchart explaining operation | movement of the dictionary registration apparatus 2 Flowchart explaining the same difference acquisition processing Block diagram of word segmentation apparatus 3 according to Embodiment 3 A flowchart for explaining the operation of the word dividing device 3 Overview of the computer system in the above embodiment Block diagram of the computer system

  Hereinafter, embodiments of a word division device, a dictionary registration device, and the like will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again.

(Embodiment 1)
In the present embodiment, a word dividing device 1 that divides a sentence into two or more words will be described.

  FIG. 1 is a block diagram of a word segmentation apparatus 1 in the present embodiment. The word division device 1 includes a word division dictionary 11, a reception unit 12, a first division unit 13, and an output unit 14.

  The word division dictionary 11 can store one or more words and one or more pieces of division information. The division information is a set of a word and two or more divided words. The divided word is a result of dividing the word. The division information is, for example, “free format: free / format” or “is not: is / is / is”. “Free format” of the division information “free format: free / format” is a word, and “free” and “format” of “free / format” are divided words. In addition, “has not”: “has not”: “has not” is “word”, and “ha”, “no”, “no”, and “ha” are respectively segmented words. Note that the word may be considered to include any term having meaning such as a morpheme or a collocation. A divided word can also be said to be a word.

  In the word division dictionary 11, it is preferable that one or more words and one or more pieces of division information are held in the same file or the same database. However, the one or more words and the one or more pieces of division information may be held in separate files or separate databases. That is, the specific data structure of the word division dictionary 11 is not limited. The word division dictionary 11 only needs to hold one or more words and one or more pieces of division information.

  The word segmentation dictionary 11 is preferably a non-volatile recording medium, but can also be realized by a volatile recording medium. The process of storing words and division information in the word division dictionary 11 does not matter. For example, words and division information may be stored in the word division dictionary 11 via a recording medium, and words and division information transmitted via a communication line or the like are stored in the word division dictionary 11. Alternatively, a word or division information input via an input device may be stored in the word division dictionary 11.

  The accepting unit 12 accepts a sentence having one or more characters. The sentence may be an incomplete sentence. That is, the sentence may be a multiple word or the like. The language of the sentence is not limited. The sentence is usually a sentence in a language that is not divided, such as Japanese, Chinese, Korean, and Mongolian. However, the sentence may be a language such as English that is not shared. The sentence may be, for example, a character string indicating a URL or a character string indicating a file name. In addition, reception means reception of information input from an input device such as a keyboard, mouse, touch panel, reception of information transmitted via a wired or wireless communication line, an optical disk, a magnetic disk, a semiconductor memory, etc. This is a concept including reception of information read from the recording medium.

  The sentence input means may be anything such as a keyboard, mouse or menu screen. The receiving unit 12 can be realized by a device driver for input means such as a keyboard, control software for a menu screen, or the like.

The first dividing unit 13 divides the sentence received by the receiving unit 12 and acquires a first division result that is a set of two or more words.
More specifically, the first dividing unit 13 acquires, from the word dividing dictionary, the maximum length word that matches the character string constituting the sentence received by the receiving unit 12 using the word dividing dictionary. Two or more divided words corresponding to the acquired word are acquired, and a first division result which is a set of two or more words obtained by dividing the sentence is acquired. This process will be described in further detail as follows. The 1st division part 13 acquires one or more character strings which constitute the sentence which acceptance part 12 received using the dictionary for word division. Then, the first division unit 13 obtains the maximum length word that matches the one or more character strings from the word division dictionary. And the 1st division part 13 acquires two or more division words corresponding to a word for every one or more words acquired from the word division dictionary, and obtains two or more words obtained by dividing a sentence. The first division result that is a set is acquired.

  More specifically, the first dividing unit 13 performs processing as follows, for example. First, the first dividing unit 13 performs a first process of acquiring, from the word dividing dictionary 11, a word that matches the maximum length character string from the sentence pointer at the head of the sentence received by the receiving unit 12. When the first dividing unit 13 has two or more divided words corresponding to the acquired word, the first dividing unit 13 performs a second process of acquiring two or more divided words instead of the matching words. The first process and the second process are referred to as a divided word acquisition process. Then, the first dividing unit 13 moves the sentence pointer to the character next to the matching word. And the 1st division part 13 performs said division | segmentation word acquisition process to the word containing the last character of a sentence. As a result, the first division unit 13 can acquire a first division result that is a set of two or more words obtained by dividing a sentence. When the word acquired in the first process is not a word included in the division information, the first dividing unit 13 holds the word acquired in the first process as it is. The first division result is a set of two or more words, but has a data structure in which the two or more breaks can be determined.

Moreover, the method of the 1st process which the 1st division part 13 performs is not ask | required. For the first processing performed by the first dividing unit 13, a known technique such as a so-called longest match method (also referred to as a longest match or maximum match) can be used. The longest match method is described in “Iwanami Shoten, Iwanami Lecture, Software Science 15 Natural Language Processing, pages 126-127, Makoto Nagao”.

Further, the first dividing unit 13 determines the character string of the maximum length from the sentence pointer, and the character string from the character indicated by the sentence pointer to the last character of the sentence (assuming that it is the Nth character from the sentence pointer). It is determined whether or not a word that matches (this is referred to as a character string A) exists in the word segmentation dictionary 11, and if it exists, the character string A is acquired, and if it does not exist, a pointer to the sentence It is determined whether or not a word that matches the character string (referred to as character string B) from the character indicated by the sentence pointer to the (N-1) th character exists in the word segmentation dictionary 11; If it exists, the character string B is acquired. If it does not exist, the character string is reduced by one character at a time, and the word with the maximum character string in the character string starting with the character indicated by the sentence pointer is replaced with the word. Search from the partitioning dictionary 11. That is, the first dividing unit 13 searches the word dividing dictionary 11 in order while reducing the character by character from the longest character string of the unprocessed character string in the sentence, and obtains the longest character string from the pointer p. You may do it.
The first dividing unit 13 has a known technique “trie” as a data structure for detecting the maximum length character string from the sentence. Since the trial is described in the following (1) to (3), a detailed description is omitted.
(1) Takuyuki Tokunaga, “Technology supporting Japanese input”, pages 89-99 (2) Internet web page, URL “http://www.slideshare.net/higashiyama/ss-8738479”
(3) Internet Web page, URL “http://nanika.osonae.com/DArray/dary.html”

  The first dividing unit 13 can be usually realized by an MPU, a memory, or the like. The processing procedure of the first dividing unit 13 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The output unit 14 outputs the first division result acquired by the first division unit 13. Here, output refers to display on a display, projection using a projector, printing with a printer, sound output, transmission to an external device, storage in a recording medium, and output to other processing devices or other programs. It is a concept that includes delivery of processing results. When handing over the processing result to another program, the word segmentation device 1 and the other program realize, for example, a speech recognition device, a machine translation device, or the like. That is, the first division result obtained by dividing the sentence can be used for, for example, speech recognition processing, machine translation processing, and the like.

  The output unit 14 may be considered as including or not including an output device such as a display or a speaker. The output unit 14 can be realized by output device driver software, or output device driver software and an output device.

  Next, operation | movement of the word division | segmentation apparatus 1 is demonstrated using the flowchart of FIG.

  (Step S201) The reception unit 12 determines whether a sentence has been received. If a sentence is accepted, the process goes to step S202, and if no sentence is accepted, the process returns to step S201.

  (Step S202) The first dividing unit 13 sets the sentence pointer p to 1. The sentence pointer p indicates the position of the beginning of word acquisition in the sentence.

  (Step S203) The first division unit 13 searches for a word that is present in the word division dictionary 11 and matches the maximum length character string from characters corresponding to p in the sentence. Then, the first division unit 13 acquires a word that is a maximum length character string from the word division dictionary 11.

  (Step S204) The first division unit 13 determines whether or not the word acquired in step S203 is a word included in the division information. If it is a word included in the division information, go to step S205, and if it is not a word included in the division information, go to step S206.

  (Step S205) The first dividing unit 13 acquires two or more divided words corresponding to the word acquired in step S203 from the word dividing dictionary 11. Then, the first dividing unit 13 adds two or more divided words to the buffer. Note that the initial value of the buffer is NULL. The first dividing unit 13 puts a delimiter character in each of the two or more divided words and adds the two or more divided words to the buffer. The delimiter may be anything such as “/”, “(space)”, “,”, etc. Go to step S207.

  (Step S206) The first dividing unit 13 adds the word acquired in step S203 to the buffer. The first dividing unit 13 places a delimiter between the word acquired in step S203 and the previous or / and subsequent word.

  (Step S207) The first dividing unit 13 advances the pointer p by the maximum character string length.

  (Step S208) The first dividing unit 13 determines whether or not all the dividing processes have been completed. If all the division processes are completed, the process goes to step S209, and if not completed, the process returns to step S203. When the pointer p is the position next to the last character of the sentence, it can be said that all the division processes have been completed.

  (Step S209) The output unit 14 outputs two or more words in the buffer. The process returns to step S201.

In the flowchart of FIG. 2, the process is terminated by powering off or a process termination interrupt.
Further, in the flowchart of FIG. 2, the processing is started from the beginning of the accepted sentence, and the processing is sequentially performed until the end of the sentence. However, for example, the process may be started from the end of the accepted sentence, and the process may be performed in the previous direction after the sentence. In other words, in step S202, the first dividing unit 13 sets the sentence pointer p to the end of the sentence, and in step S207, the pointer p may return to the front of the sentence by the maximum character string length. good. In such a case, in step S203, the first division unit 13 is a word existing in the word division dictionary 11, and advances the pointer forward from the character corresponding to p in the sentence to match the maximum length character string. Search for the word you want. Then, the first division unit 13 acquires a word that is a maximum length character string from the word division dictionary 11.

  Hereinafter, a specific operation of the word segmentation apparatus 1 in the present embodiment will be described.

  FIG. 3 shows the word division dictionary 11. The records constituting the word division dictionary 11 have “ID”, “word”, and “division word”. The record of the word division dictionary 11 may have other information such as part of speech and appearance probability. Further, the record of the word division dictionary 11 has a word or a pair of a word and division information.

  A record corresponding to a word has a value of the attribute “divided word” of NULL (“−” in FIG. 3). The record corresponding to the word is, for example, a record of “ID = 5, 6, 8, 9, 10, 11, 12, 13” in FIG. Further, a record corresponding to a pair of a word and division information has a division word having an attribute “division word” value of 2 or more. Here, the divided words in the attribute “divided word” are separated by a delimiter “/”. Furthermore, the record corresponding to the pair of the word and the division information is, for example, a record of “ID = 1, 2, 3, 4, 7” in FIG. Note that the record of the word division dictionary 11 may have “a flag indicating whether it is a word or a pair of a word and division information” as an attribute value.

(Specific example 1)
In this situation, it is assumed that the reception unit 12 has received the sentence “Masao is a solid person”. Next, the first dividing unit 13 sets the sentence pointer p to 1. That is, the pointer p is set at the “positive” position of the sentence.

  Next, the first division unit 13 searches for the word “Matsuo” that is present in the word division dictionary 11 and matches the maximum character string from the character “Correct” corresponding to p in the sentence. And get.

  Next, the first division unit 13 determines whether or not the acquired word “Matsuo” is a word included in the division information. That is, the first division unit 13 determines that the division information corresponding to the word “Matsuo” is “− (NULL)”.

  Then, the first dividing unit 13 adds the acquired word “Matsuo” to the buffer.

  Next, the first dividing unit 13 calculates the character string length “2” of the word “Matsuo”. Next, the first dividing unit 13 advances the pointer p by “2” corresponding to the maximum length of the character string, and sets the pointer p to the position “ha” of the sentence.

  Next, the first division unit 13 determines that the division process has not been completed yet.

  Next, the first division unit 13 searches for a word “ha” that is present in the word division dictionary 11 and matches the maximum length character string from the character “ha” corresponding to p in the sentence. And get.

  Next, the first division unit 13 determines whether or not the acquired word “ha” is a word included in the division information. That is, the first division unit 13 determines that the division information corresponding to the word “ha” is “− (NULL)”.

  Then, the first dividing unit 13 adds the acquired word “ha” to the buffer. The first dividing unit 13 adds a delimiter “/” in front of the word “ha” and appends it to the buffer. Then, “Masao / Ha” is stored in the current buffer.

  Next, the first dividing unit 13 calculates the character string length “1” of the word “ha”. Next, the first dividing unit 13 advances the pointer p by “1” corresponding to the maximum length of the character string, and sets the pointer p to the position of “shi” of the sentence.

  Next, the first division unit 13 determines that the division process has not been completed yet.

  Next, the first dividing unit 13 is a word that exists in the word dividing dictionary 11, and from the character “shi” corresponding to p in the sentence, the word “solid” that matches the maximum length character string is obtained. Search and get.

  Next, the first division unit 13 determines whether or not the acquired word “firm person” is a word included in the division information. That is, since the divided word corresponding to the word “firm person” is not NULL, the first dividing unit 13 determines that the word “firm person” is a word included in the division information.

  Then, the first division unit 13 acquires the division information “firm / person” corresponding to the word “firm person” from the word division dictionary 11.

  Then, the first dividing unit 13 adds the delimiter “/” and the acquired word “solid / person” to the buffer. In the current buffer, “Masao / Ha / Ken / People” is stored.

  Next, the first dividing unit 13 calculates the character string length “5” of the word “firm person”. Next, the first dividing unit 13 advances the pointer p by “5” corresponding to the maximum length of the character string, and sets the pointer p to the position of “DA” in the sentence.

  Next, the first division unit 13 determines that the division process has not been completed yet.

  Next, the first division unit 13 searches for a word “DA” that is a word existing in the word division dictionary 11 and matches the maximum length character string from the character “DA” corresponding to p in the sentence. And get.

  Next, the first division unit 13 determines whether or not the acquired word “DA” is a word included in the division information. That is, the first division unit 13 determines that the division information corresponding to the word “DA” is “− (NULL)”.

  Then, the first division unit 13 adds the delimiter “/” and the acquired word “da” to the buffer. In the current buffer, “Masao / Ha / So / Person” is stored.

  Next, the first dividing unit 13 calculates the character string length “1” of the word “DA”. Next, the first dividing unit 13 advances the pointer p by “1” corresponding to the maximum length of the character string, and sets the pointer p to a position next to “DA” in the sentence.

  Next, the first division unit 13 determines that the division process has been completed.

  Then, the output unit 14 outputs two or more divided word strings “Masao / Ha / So / I / D” in the buffer.

(Specific example 2)
It is assumed that the reception unit 12 has received the sentence “Although it is said that it is still a child”. Next, the first dividing unit 13 sets the sentence pointer p to 1. That is, the pointer p is set at the position “s” in the sentence.

  Next, the first division unit 13 is a word that exists in the word division dictionary 11, and the word “So” corresponding to p in the sentence is matched with the maximum length character string “Yes. Search for and get "".

  Next, the first dividing unit 13 determines whether or not the acquired word “even if so” is a word included in the division information. That is, since the divided word corresponding to the word “Yes” is not NULL, the first dividing unit 13 determines that the word “No, yes” is a word included in the division information.

  Then, the first division unit 13 acquires the division information “so / ha / inte / mo” corresponding to the word “so yes” from the word division dictionary 11.

  Then, the first dividing unit 13 adds the acquired word “so / ha / inte / mo” to the buffer. In the current buffer, “yes / ha / te / mo” is stored.

  Next, the first dividing unit 13 calculates the character string length “7” of the word “even if so”. Next, the first dividing unit 13 advances the pointer p by “7” corresponding to the maximum length of the character string, and sets the pointer p to the position “ma” of the sentence.

  Next, the first division unit 13 determines that the division process has not been completed yet.

  Next, the first division unit 13 searches for the word “still” that matches the maximum length character string from the character “ma” corresponding to p in the sentence that is present in the word division dictionary 11. And get.

  Next, the first division unit 13 determines whether or not the acquired word “still” is a word included in the division information. That is, the first division unit 13 determines that the division information corresponding to the word “ha” is “− (NULL)”.

  Then, the first dividing unit 13 appends the delimiter “/” and the acquired word “still” to the buffer. In the current buffer, “yes / ha / te / mo / no” is stored.

  Next, the first dividing unit 13 calculates the character string length “2” of the word “still”. Next, the first division unit 13 advances the pointer p by “2” corresponding to the maximum length of the character string, and sets the pointer p to the position of the “child” of the sentence.

  Next, the first division unit 13 determines that the division process has not been completed yet.

  Next, the first division unit 13 searches for a word “child” that is in the word division dictionary 11 and matches the maximum character string from the character “child” corresponding to p in the sentence. And get.

  Next, the first division unit 13 determines whether or not the acquired word “child” is a word included in the division information. That is, the first division unit 13 determines that the division information corresponding to the word “ha” is “− (NULL)”.

  Then, the first dividing unit 13 adds the delimiter “/” and the acquired word “child” to the buffer. In the current buffer, “Yes / I / I / Mo / Still / Child” is stored.

  Next, the first dividing unit 13 calculates the character string length “2” of the word “still”. Next, the first dividing unit 13 advances the pointer p by “2” corresponding to the maximum length of the character string, and sets the pointer p to the position next to “don” in the sentence.

  Next, the first division unit 13 determines that the division process has been completed.

  Then, the output unit 14 outputs the two or more divided word strings “so / ha / de / mo / yana / child” in the buffer.

  As described above, according to the present embodiment, a sentence can be divided into two or more words by a very simple process. Therefore, the sentence can be divided into words very quickly.

  In the present embodiment, the algorithm by which the first dividing unit 13 acquires the word that is the maximum length character string from the word dividing dictionary 11 does not matter.

  Furthermore, the processing in the present embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded and distributed on a recording medium such as a CD-ROM. This also applies to other embodiments in this specification. Note that the software that implements the word segmentation apparatus in the present embodiment is the following program. That is, this program stores a word division dictionary having one or more words and one or more pieces of division information that is a set of two or more divided words that are the result of dividing the words. A word receiving dictionary that accepts a sentence having one or more characters, and a word that matches a maximum-length character string from a sentence pointer at the head of the sentence accepted by the accepting part. If there are two or more divided words corresponding to the acquired word, a divided word acquisition process is performed in which the two or more divided words are obtained instead of the matching words, and the sentence pointer is After moving to the next character of the matching word, the divided word acquisition process is performed up to the word including the last character of the sentence, and the first division result which is a set of two or more words obtained by dividing the sentence is acquired. The first minute to And parts, is a program, to function as an output unit for outputting the first result of division.

Hereinafter, experimental results using the word segmentation apparatus 1 will be described. In the experiment, the software that realizes the word segmentation apparatus 1 is named “MA-2”.
(Experiment 1)

As another word segmentation apparatus in Experiment 1, “MeCab 0.98”, which is a known technique, was used. “MeCab 0.98” is described in “http://mecab.googlecode.com/svn/trunk/mecab/doc/index.html”. In addition, as another word dividing device, the word dividing device developed by the applicant, the word dividing device “MA-1” using the Viterbi algorithm was also used. FIG. 4 shows the results of measuring the processing speed (KB / sec) of each device by inputting UTF-8 Japanese text 388.5 MB into the above three devices. “MA-2”, which is the word segmentation device 1, was 4.3 times faster than “MeCab 0.98”. In addition, according to “MA-2” which is the word dividing device 1, it can be understood that one year of newspaper can be analyzed in about 30 seconds (see FIG. 4).
(Experiment 2)

  Next, the result of Experiment 2 using the word segmentation apparatus 1 “MA-2” will be described. The result of Experiment 2 is described in FIG. As other word segmentation devices in Experiment 2, known technologies “JUMAN 6.0”, “MeCab 0.98”, “KyTea 0.3.0”, and “ChaSen 2.3.3” were used. "JUMAN 6.0" is "http://nlp.ist.i.kyoto-u.ac.jp/index.php?cmd=read&page=JUMAN&alias%5B%5D=%E6%97%A5%E6%9C%AC % E8% AA% 9E% E5% BD% A2% E6% 85% 8B% E7% B4% A0% E8% A7% A3% E6% 9E% 90% E3% 82% B7% E3% 82% B9% E3 % 83% 86% E3% 83% A0JUMAN ”,“ KyTea 0.3.0 ”is“ http://www.phontron.com/kytea/index-en.html ”,“ ChaSen 2.3.3 ”is“ http: / /chasen.naist.jp/hiki/ChaSen/ ”. Further, in this experiment, 80,000 web texts were input to the above five devices, and the processing time when each device was analyzed was measured (see FIG. 5). FIG. 5 shows that the processing speed of the word segmentation apparatus 1 “MA-2” is extremely faster than others. Note that the algorithm and model of the word segmentation apparatus 1 are “depth-first search + collocation” shown in FIG.

(Embodiment 2)
In the present embodiment, the dictionary registration device 2 for registering division information in the word division dictionary 11 when a division result of one word division device and a difference between the plurality of other word division devices satisfy a predetermined condition. Will be described. The other word segmentation device is a conventional word segmentation device, and is preferably a word segmentation device that has been confirmed to be segmented into words with high accuracy.

  FIG. 6 is a block diagram of dictionary registration apparatus 2 in the present embodiment. The dictionary registration device 2 includes a word division dictionary 11, a first division result acquisition unit 22, another division result acquisition unit 23, a different part acquisition unit 24, a division information acquisition unit 25, and a dictionary registration unit 26.

  The first division result acquisition unit 22 acquires the first division result. The first division result is a result of dividing one sentence by one word dividing device. The first division result is a set of one or two or more words, and usually has a structure capable of recognizing that words are separated. Moreover, the one word division device is the word division device 1, for example. The first division result acquisition unit 22 may receive the first division result from one word division device, or may read or accept the first division result stored in a recording medium (not shown). One sentence may be divided and the first division result may be acquired. When the first division result acquisition unit 22 divides one accepted sentence and acquires the first division result, the first division result acquisition unit 22 has the same function as the first division unit 13.

  The other division result acquisition unit 23 acquires two or more other division results. The other division result is a result of dividing one sentence by another word dividing device. The other division result is a set of two or more words, and has a structure capable of recognizing that the words are separated. The other word dividing device is a word dividing device that is not the one word dividing device described above.

  The other division result acquisition unit 23 may acquire the second division result and the third division result, which are two other division results.

  The different part acquisition unit 24 acquires one or more different parts. The different part is a part where the first division result and the other division result are different. The different part is a part included in the other division result. Note that the different part acquisition unit 24 may acquire two or more different parts. Moreover, the different part acquisition part 24 may acquire two or more different parts with respect to one sentence. The difference part usually has two or more divided words.

  The other word segmentation devices are, for example, a second word segmentation device and a third word segmentation device, the segmentation result obtained by the second word segmentation device is the second segmentation result, and the segmentation result obtained by the third word segmentation device is the first When it is a three-part division result, the different part acquisition unit 24, for example, a first different part that is a difference part between the first division result and the second division result, and a difference part between the first division result and the third division result You may acquire the 2nd different part which is.

  When one or more different parts acquired by the different part acquisition unit 24 satisfy a predetermined condition, the division information acquisition unit 25 configures the division information using any one or more different parts. The division information is information having a word that is a character string corresponding to a different part and two or more words that are different parts. The difference part in which it is determined whether or not a predetermined condition is satisfied is a difference part in the same different part in the sentence. Moreover, the different part is a part in which the way of dividing into words is different.

  Here, the predetermined condition is, for example, that two or more different parts are the same. In addition, for example, the predetermined condition may be that N (N is, for example, 50%) or more different portions among two or more different portions are the same.

  That is, for example, when the first different part and the second different part are common, the division information acquisition unit 25 uses the first different part and uses the first different part (or the second different part) as a character string. And division information having two or more words that are first different parts (or second different parts). Here, since the first different part and the second different part are the same, the divided information is the same regardless of which is used to form the divided information.

  The dictionary registration unit 26 accumulates the division information acquired by the division information acquisition unit 25 in the word division dictionary 11.

  The first division result acquisition unit 22 and the other division result acquisition unit 23 can be realized by, for example, wireless or wired communication means. The first division result acquisition unit 22 and the like may be realized by an MPU, a memory, or the like.

  The different part acquisition unit 24, the division information acquisition unit 25, and the dictionary registration unit 26 can be usually realized by an MPU, a memory, or the like. The processing procedure of the different part acquisition unit 24 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  Next, operation | movement of the dictionary registration apparatus 2 is demonstrated using the flowchart of FIG.

  (Step S701) The first division result acquisition unit 22 acquires the first division result.

  (Step S702) The other division result acquisition unit 23 acquires two or more other division results.

  (Step S703) The different portion acquisition unit 24 substitutes 1 for a counter i.

  (Step S704) The different portion acquisition unit 24 determines whether or not the i-th other division result exists in the other division results acquired in step S702. If the i-th other division result exists, the process goes to step S705. If the i-th other division result does not exist, the process goes to step S709.

  (Step S705) The different part acquisition unit 24 acquires a different part between the first division result and the i-th other division result. Such a process is called a different part acquisition process. A different part acquisition process is demonstrated using the flowchart of FIG.

  (Step S706) The different portion acquisition unit 24 determines whether or not a different portion has been acquired in step S705. If the different part can be acquired, the process goes to step S707, and if not, the process goes to step S708.

  (Step S707) The different part acquisition unit 24 temporarily stores the different part acquired in step S706 in a buffer (not shown). It should be noted that accumulating different parts is equivalent to accumulating information indicating the different parts. Further, the information indicating the different part is, for example, a pointer indicating a start character and an end character of the different part. Furthermore, when there are two or more different parts in one sentence, the different part acquisition unit 24 temporarily stores the different parts for each part.

  (Step S708) The different part acquisition unit 24 increments the counter i by one. The process returns to step S704.

  (Step S709) The division information acquisition unit 25 substitutes 1 for a counter j.

  (Step S710) The division information acquisition unit 25 determines whether there is a j-th different place. If there is a j-th different part, the process goes to step S711, and if not, the process ends.

  (Step S711) The division information acquisition unit 25 determines whether one or more different portions in the buffer satisfy a predetermined condition with respect to the j-th different portion. If the predetermined condition is satisfied, the process goes to step S712. If the predetermined condition is not satisfied, the process goes to step S716.

  (Step S712) The division information acquisition unit 25 acquires a word that is a character string corresponding to the different portion with respect to the j-th different portion. In addition, this word is a collocation word and is a word which comprises division | segmentation information normally.

  (Step S713) The division information acquisition unit 25 acquires two or more division words that are different parts.

  (Step S714) The division information acquisition unit 25 configures division information using the word acquired in step S712 and two or more division words acquired in step S713.

  (Step S715) The dictionary registration unit 26 accumulates the division information configured in step S714 in the word division dictionary 11.

  (Step S716) The division information acquisition unit 25 increments the counter j by 1. The process returns to step S710.

  In the flowchart of FIG. 7, the difference between the first division result and the other division result is usually one place, but there may be two or more places.

  Next, the different part acquisition process in step S705 will be described with reference to the flowchart of FIG.

  (Step S801) The different part acquisition unit 24 substitutes 1 for counters i and j. Here, the counter i is a counter for divided words in the first division result, and the counter j is a counter for divided words in the second division result.

  (Step S802) The different part acquisition unit 24 determines whether or not the i-th divided word exists in the first division result. If the i-th divided word exists, the process goes to step S803, and if the i-th divided word does not exist, the process ends.

  (Step S803) The different portion acquisition unit 24 acquires the i-th divided word in the first division result.

  (Step S804) The different part acquisition unit 24 acquires the j-th divided word in the other division result.

  (Step S805) The different portion acquisition unit 24 determines whether or not the i-th divided word acquired in step S803 is the same as the j-th divided word acquired in step S804. If the two divided words are the same, go to step S806, otherwise go to step S807.

  (Step S806) The different part acquisition unit 24 increments the counters i and j by 1. The process returns to step S802.

  (Step S807) The different portion acquisition unit 24 determines that i and j until the last character of the divided word of the first division result matches the last character of the divided word of the other division result, or until the end of the sentence. To proceed. The fact that the last character of the divided words matches does not mean that the character codes match, but that the characters in the sentence to be divided are characters at the same position. The characters at the same position have the same character code. Further, to advance i and j is to advance from the current positions of i and j, respectively.

  (Step S808) The different part acquisition unit 24 acquires, from the divided words before j is advanced in step S807 to the divided words after j is advanced, as different parts. The process returns to step S806.

Hereinafter, a specific operation of the dictionary registration device 2 in the present embodiment will be described. In a specific example, there are two other word segmentation devices, word segmentation device A and word segmentation device B, and the description will be made assuming that the predetermined conditions for registering in the dictionary match different portions. That is, the other division result acquisition unit 23 acquires the second division result and the third division result. Moreover, the different part acquisition unit 24 includes a first different part that is a difference between the first division result and the second division result, and a second different part that is a difference between the first division result and the third division result. Shall be obtained. Furthermore, it is assumed that the device that obtains the first division result is the word division device 1 described above. In addition,
Note that the word dividing device A and the word dividing device B are, for example, “MeCab 0.98”, “JUMAN 6.0”, “KyTea 0.3.0”, “ChaSen 2.3.3”, and the like described above. The word dividing device A and the word dividing device B are different word dividing devices.

  Here, it is assumed that the word segmentation device 1 and the other two word segmentation devices have received the sentence “Is there a mistake in free form”?

  Next, it is assumed that the word segmentation apparatus 1 has acquired the first segmentation result “free form / formula / de / incorrect / Hana / Ika”. Further, it is assumed that the other word segmentation apparatus A has acquired “free form / formula / de / incorrect / has / not / is”. Furthermore, it is assumed that the other word segmentation apparatus B has acquired “free / format / de / incorrect / has / not / is”.

  In such a situation, the first division result acquisition unit 22 of the dictionary registration device 2 acquires the first division result “free form / formula / de / incorrect / Hana / Ika” from the word division device 1.

  Next, the other division result acquisition unit 23 acquires the other division result A “free form / formula / de / incorrect / has / no /” from the word segmentation apparatus A. Further, the other division result acquisition unit 23 acquires the other division result A “free / format / de / incorrect / has / no /” from the word segmentation apparatus B.

  Next, the different portion acquisition unit 24 acquires a difference portion “ha / no /” between the first division result and the other division result A. Then, the different part acquisition unit 24 temporarily stores the different part “ha / no / ka” in the buffer. In order to distinguish the part in the sentence of the different part “ha / no / ka” from the other part, the different part acquisition unit 24 indicates the different part “ha / no / ka” and “9” indicating the position in the sentence. Is preferably stored in association with each other. Here, “9” is an offset (number of characters from the beginning) in the sentence of the first character “ha” of “ha / no / ka”. In the first division result and the other division result A, the divided words up to “free form / formula / de / incorrect” are the same, and the different part acquisition unit 24 determines “free form / formula / de / incorrect”. No difference is acquired for the divided words up to.

  Next, the different portion acquisition unit 24 acquires different portions “free / format” and “ha / no /” between the first division result and the other division result B. Then, the different part acquisition unit 24 temporarily stores the different parts “free / format” and “ha / no / ka” in the buffer. It is preferable that the different part acquisition unit 24 stores the different part “free / format” and “1” indicating the position in the sentence in association with each other. Further, it is preferable that the different part acquisition unit 24 stores the different part “ha / no / ka” and “9” indicating the position in the sentence in association with each other. In addition, the first divided result and the other divided result B have the same divided word in “de / wrong”, and the different portion acquisition unit 24 obtains a different portion regarding the divided word “de / wrong”. do not do.

  Next, the division information acquisition unit 25 acquires the first difference portion “free / format” from the buffer. Here, the division information acquisition unit 25 acquires only one different part “free / format”. However, regarding the first difference portion “free / format”, the difference portion acquired from the other division result A and the difference portion acquired from the other division result B are not common, and thus the predetermined condition is not satisfied. , And the division information acquisition unit 25 determine. Then, the division information acquisition unit 25 does not configure the division information for the first difference portion “free / format”.

  Next, the division information acquisition unit 25 acquires the second difference part “ha / no /” from the buffer. Here, the division information acquisition unit 25 acquires two different parts “ha / no / ka”. Since the difference part acquired from the other division result A and the difference part acquired from the other division result B are common with respect to the second difference part “ha / no / or”, a predetermined condition is set. The division information acquisition unit 25 determines that it is satisfied.

  Next, the division information acquisition unit 25 acquires the character string “Is there?” Corresponding to the second difference part “Is not / is”. Further, the division information acquisition unit 25 acquires two or more divided words “ha / no / ka” which are different parts. Next, the division information acquisition unit 25 configures the division information “has no: no / has / no” using the word “has no” and two or more divided words “ha / no / no”.

  Next, the dictionary registration unit 26 stores the configured division information “has no: no / no / no” in the word division dictionary 11.

  As described above, according to the present embodiment, it is possible to obtain a word segmentation dictionary with high accuracy.

  Note that, according to the present embodiment, various conditions for registering division information can be considered as described above.

  In addition, according to the present embodiment, there are many other word segmentation devices of three or more, and the larger the threshold value of the ratio (or the number) of common different parts, the more accurate the word segmentation. You can build a dictionary.

  Furthermore, the software that implements the dictionary registration apparatus according to the present embodiment is the following program. That is, this program stores a word division dictionary capable of storing one or more words and one or more division information that is a set of two or more division words as a result of dividing the words on the recording medium. A first division result acquisition unit that acquires a first division result obtained by dividing one sentence by one word dividing device; and a word dividing device that is not the one word dividing device. A part included in each of the two or more other division results, and another division result acquisition unit that acquires two or more other division results that are the result of dividing the one sentence by two or more other word division devices A different part acquisition unit that acquires one or more different parts that are different parts between the first division result and the two or more other division results, and one or more different parts acquired by the different part acquisition unit. 1 or more if predetermined conditions are met Using any one of the different parts, a division information acquisition unit that forms division information having a word that is a character string corresponding to the different part and two or more words that are the different parts; and It is a program for functioning as a dictionary registration part which accumulate | stores in the dictionary for word division.

  In the above program, the other division result acquisition unit acquires a second division result and a third division result, which are two other division results, and the different part acquisition unit includes the first division result and the first division result. A first difference part that is a difference part from the two-part dividing result and a second different part that is a difference part between the first division result and the third division result are obtained, and the division information obtaining unit is configured to obtain the first difference part. When one different part and the second different part are common, using the first different part, a word that is a character string corresponding to the first different part and two or more words that are the first different part It is preferable to make a computer function as what constitutes the division information having

(Embodiment 3)
In the present embodiment, a word dividing device 3 including the dictionary registration device 2 described in the second embodiment will be described.

  Moreover, in this Embodiment, the other word division | segmentation apparatus may also be included. Other word segmentation devices are, for example, “MeCab 0.98”, “JUMAN 6.0”, “KyTea 0.3.0”, “ChaSen 2.3.3”, etc. described above.

  FIG. 9 is a block diagram of word segmentation apparatus 3 in the present embodiment. The word division device 3 includes a dictionary registration device 2, two or more other word division devices 31, a reception unit 12, a first division unit 13, and an output unit 14.

  Next, operation | movement of the word division | segmentation apparatus 3 is demonstrated using the flowchart of FIG. In the flowchart of FIG. 10, the description of the same steps as those in the flowchart of FIG. 2 is omitted.

  (Step S1001) The reception unit 12 assigns 1 to the counter i.

  (Step S1002) The reception unit 12 determines whether or not the i-th other word dividing device 31 exists. If the i-th other word dividing device 31 exists, the process goes to step S1003, and if the i-th other word dividing device 31 does not exist, the process goes to step S1005.

  (Step S1003) The i-th other word dividing device 31 receives a sentence from the receiving unit 12, and performs a process of dividing the sentence into words. Then, the i-th other word dividing device 31 acquires the other division result.

  (Step S1004) The reception unit 12 increments the counter i by one. The process returns to step S1002.

  (Step S1005) The dictionary registration device 2 performs a dictionary registration process. The dictionary registration process is the process described with reference to FIG. The process returns to step S201.

  In the flowchart of FIG. 10, the process ends when the power is turned off or the process ends.

  As described above, according to the present embodiment, it is possible to divide a sentence into two or more words at high speed using a high-precision word division dictionary.

  Further, according to the present embodiment, it is possible to enrich the word division dictionary while performing a process of dividing a sentence into two or more words.

  According to the present embodiment, the word dividing device 3 includes two or more other word dividing devices 31. However, two or more other word dividing devices 31 may exist outside the word dividing device 3. In such a case, the word dividing device 3 includes a dictionary registration device 2, a receiving unit 12, a first dividing unit 13, and an output unit 14. In such a case, the word dividing device 3 acquires the other division result from each of the two or more other word dividing devices 31.

  Furthermore, the software that implements the word segmentation apparatus in the present embodiment is the following program. That is, this program stores a word division dictionary capable of storing one or more words and one or more division information that is a set of two or more division words as a result of dividing the words on the recording medium. A first division result acquisition unit that acquires a first division result obtained by dividing one sentence by one word dividing device; and a word dividing device that is not the one word dividing device. A part included in each of the two or more other division results, and another division result acquisition unit that acquires two or more other division results that are the result of dividing the one sentence by two or more other word division devices A different part acquisition unit that acquires one or more different parts that are different parts between the first division result and the two or more other division results, and one or more different parts acquired by the different part acquisition unit. 1 or more if predetermined conditions are met Using any one of the different parts, a division information acquisition unit that forms division information having a word that is a character string corresponding to the different part and two or more words that are the different parts; and It is a program for functioning as a dictionary registration part which accumulate | stores in the dictionary for word division.

  In the above program, it is preferable to further cause the computer to function as two or more other word dividing devices.

  FIG. 11 shows the external appearance of a computer that executes the program described in this specification to realize the dictionary registration apparatus and the like of the various embodiments described above. The above-described embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 11 is an overview diagram of the computer system 300, and FIG. 12 is a block diagram of the system 300.

  In FIG. 11, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

  12, in addition to the CD-ROM drive 3012, the computer 301 includes an MPU 3013, a bus 3014 connected to the MPU 3013 and the CD-ROM drive 3012, a ROM 3015 for storing a program such as a bootup program, and an MPU 3013. And a RAM 3016 for temporarily storing instructions of the application program and providing a temporary storage space, and a hard disk 3017 for storing the application program, the system program, and data. Although not shown here, the computer 301 may further include a network card that provides connection to a LAN.

  A program that causes the computer system 300 to execute the functions of the dictionary registration device and the like of the above-described embodiment may be stored in the CD-ROM 3101, inserted into the CD-ROM drive 3012, and further transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored in the hard disk 3017. The program is loaded into the RAM 3016 at the time of execution. The program may be loaded directly from the CD-ROM 3101 or the network.

  The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 301 to execute functions such as the dictionary registration device according to the above-described embodiment. The program only needs to include an instruction portion that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 300 operates is well known and will not be described in detail.

  In the above program, in a transmission step for transmitting information, a reception step for receiving information, etc., processing performed by hardware, for example, processing performed by a modem or an interface card in the transmission step (only performed by hardware). Not included) is not included.

  Further, the computer that executes the program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

  Further, in each of the above embodiments, it goes without saying that two or more communication units existing in one apparatus may be physically realized by one medium.

  In each of the above embodiments, each process (each function) may be realized by centralized processing by a single device (system), or by distributed processing by a plurality of devices. May be.

  The present invention is not limited to the above-described embodiments, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention.

  As described above, the dictionary registration device according to the present invention has an effect of being able to obtain a highly accurate word segmentation dictionary, and is useful as a dictionary registration device or the like.

DESCRIPTION OF SYMBOLS 1, 3 Word division | segmentation apparatus 2 Dictionary registration apparatus 11 Dictionary for word division 12 Reception part 13 First division part 14 Output part 22 First division result acquisition part 23 Other division result acquisition part 24 Different part acquisition part 25 Division | segmentation information acquisition part 26 Dictionary registration unit 31 Other word segmentation device

Claims (8)

A word division dictionary that can store one or more words and one or more pieces of division information that is a set of two or more divided words that is a result of dividing the word and the word;
A first division result acquisition unit that acquires a first division result obtained by dividing one sentence by one word dividing device;
An other division result acquisition unit that acquires two or more other division results that are a result of dividing two or more other word division devices that are word division devices that are not the one word division device;
A different part acquisition unit that acquires one or more different parts that are parts included in each of the two or more other division results and that are different from the first division result and the two or more other division results;
When one or more different parts acquired by the different part acquisition unit satisfy a predetermined condition, using one or more different parts, the word that is a character string corresponding to the different part and the difference A division information acquisition unit that forms division information having two or more words that are parts;
A dictionary registration device comprising: a dictionary registration unit that accumulates the division information in the word division dictionary. The other division result acquisition unit
Obtain two other split results, the second split result and the third split result,
The difference part acquisition unit is
Obtaining a first different part that is a difference between the first split result and the second split result, and a second different part that is a different part between the first split result and the third split result;
The division information acquisition unit
When the first different part and the second different part are common, using the first different part, a word that is a character string corresponding to the first different part and two or more that are the first different part The dictionary registration device according to claim 1, comprising division information having a plurality of words. The dictionary registration device according to claim 1 or 2,
A reception unit for receiving a sentence having one or more characters;
Using the word segmentation dictionary constructed by the dictionary registration device, the word having the maximum length that matches the character string constituting the sentence accepted by the accepting unit is obtained from the word segmentation dictionary, and the obtained word A first dividing unit that obtains two or more divided words corresponding to, and obtains a first division result that is a set of two or more words obtained by dividing the sentence;
A word segmentation device comprising: an output unit that outputs the first segmentation result. The word dividing device according to claim 3, further comprising two or more other word dividing devices. On the recording medium,
Storing a word division dictionary that can store one or more words and one or more pieces of division information that is a set of two or more divided words that is a result of dividing the word and the word;
A dictionary registration method realized by a first division result acquisition unit, another division result acquisition unit, a different part acquisition unit, a division information acquisition unit, and a dictionary registration unit,
A first division result acquisition step in which the first division result acquisition unit acquires a first division result which is a result of dividing one sentence by one word dividing device;
The other division result acquisition unit obtains two or more other division results that are the result of dividing the one sentence by two or more other word division devices that are word division devices that are not the one word division device. A division result acquisition step;
The different part acquisition unit is a part included in each of the two or more other division results, and acquires one or more different parts that are different parts between the first division result and the two or more other division results. A difference acquisition step to perform,
When the division information acquisition unit satisfies one or more different parts acquired in the different part acquisition step, a character corresponding to the different part using one or more different parts A division information acquisition step that constitutes division information having words that are columns and two or more words that are the different parts;
A dictionary registration method, wherein the dictionary registration unit includes a dictionary registration step of storing the division information in the word division dictionary. On the recording medium,
Storing a word division dictionary that can store one or more words and one or more pieces of division information that is a set of two or more divided words that is a result of dividing the word and the word;
A word division method realized by a reception unit, a first division unit, an output unit, and a dictionary registration device,
An accepting step in which the accepting unit accepts a sentence having one or more characters;
The first division unit uses the word division dictionary to acquire the maximum length word that matches the character string constituting the sentence received by the reception unit from the word division dictionary, and the acquired word A first division step of obtaining a first division result which is a set of two or more words obtained by dividing the sentence by obtaining two or more divided words corresponding to
An output step in which the output unit outputs the first division result; and
A word division method comprising: the dictionary registration device comprising steps constituting the dictionary registration method according to claim 6. On the recording medium,
A dictionary for word division constructed by the dictionary registration device according to claim 1 or 2 is stored;
Computer
A first division result acquisition unit that acquires a first division result obtained by dividing one sentence by one word dividing device;
An other division result acquisition unit that acquires two or more other division results that are a result of dividing two or more other word division devices that are word division devices that are not the one word division device;
A different part acquisition unit that acquires one or more different parts that are parts included in each of the two or more other division results and that are different from the first division result and the two or more other division results;
When one or more different parts acquired by the different part acquisition unit satisfy a predetermined condition, using one or more different parts, the word that is a character string corresponding to the different part and the difference A division information acquisition unit that forms division information having two or more words that are parts;
The program for functioning as a dictionary registration part which accumulate | stores the said division | segmentation information in the said dictionary for word division | segmentation. Computer
A reception unit for receiving a sentence having one or more characters;
3. The word segmentation dictionary using the word segmentation dictionary constructed by the dictionary registration device according to claim 1 or 2 to determine a maximum length word that matches a character string constituting a sentence accepted by the accepting unit. A first dividing unit that acquires two or more divided words corresponding to the acquired word, and obtains a first division result that is a set of two or more words obtained by dividing the sentence;
A program for functioning as an output unit for outputting the first division result.