JP2019003387A - Program, device and method creating scatter diagram with scattered word group - Google Patents

Abstract

To provide a program or the like creating a scatter diagram capable of causing a user to recognize words of a known language with which meaning may be close to sensory expression words of an unknown language.SOLUTION: A scatter diagram in which a plurality of words based on a first language are scattered on a plurality of evaluation axes is displayed on a display. According to the present invention, for the scatter diagram, a first co-occurrence word with high co-occurrence degree in both a first word and a second word is derived between the first word and the second word based on the first language, and a second co-occurrence word based on a second language to be a paginal translation of a first co-occurrence word is displayed. The first word and the second word based on the first language are, for example, onomatopoeia (onomatopoeic). The evaluation axes of the scatter diagram may be based on a correspondence analysis or any feature vector. Also, the evaluation axes of the scatter diagram represents the strength of the characteristic based on human sense.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a technique for creating a scatter diagram in which a group of words is scattered so that a user can easily understand the meaning of words based on a language.

  In understanding languages other than the native language, it is extremely difficult to understand the usage scenes and nuances of words using only a dictionary description. For example, “onomatopee” (onomatopee) is an expression that is difficult for foreigners to understand in Japanese. "Onomatopoeia" is based on onomatopoeia and mimetic words, and is especially preferred in Japanese daily conversation. Onomatopoeia can be expressed accurately and simply when it conveys the mental state (feelings and attitudes) based on human senses and the state of the object.

For foreigners, when they try to understand onomatopoeia, they are often not listed in general bilingual dictionaries, and the opportunities to learn with examples are considerably limited. On the other hand, it is not always practical to describe onomatopoeia in a bilingual dictionary. Onomatopoeia can be classified and arranged to some extent, but it is difficult to describe the usage scene and nuances.
On the other hand, foreigners who visit Japan for sightseeing purposes can also help understand communication beyond linguistic meaning if they can correctly understand Japanese onomatopoeia.

  Conventionally, there is a technique for collecting usage examples such as verbs and nouns modified by onomatopoeia from a website and calculating an evaluation value of a sensitivity evaluation index from the appearance frequency (see, for example, Non-Patent Document 1). This technique focuses on the phonetic sense of onomatopoeia. Therefore, it is not designed to understand even the appearance context and nuances.

  There is also a technique for constructing a related network of evaluation words including onomatopoeia from review texts and analyzing semantic differences between fields of use (see Non-Patent Document 2, for example). This is because onomatopoeia has a particularly different meaning depending on the field of use and context.

Furthermore, there is also a technique for estimating a fine impression for each onomatopoeia based on experimental numerical values by a subject (see, for example, Non-Patent Document 3).
In addition, there is an electronic picture book system technology for supporting onomatopoeia learning for international students (see Non-Patent Document 4, for example). According to this technology, it is possible to visually represent a difference in usage status of onomatopoeia having relatively close meaning through an interactive user interface.

  As another research paper, there is also a technique for displaying a plurality of onomatopoeia as a scatter diagram of “corresponding analysis” (see, for example, Non-Patent Document 5). This technique is a systematic analysis of each onomatopoeia, but it does not make onomatopoeia itself understandable.

  FIG. 1 is a scatter diagram of correspondent analysis.

“Corresponding analysis scatter diagram” is a visual representation of a cross tabulation table, and elements with higher correlations are plotted closer to each other.
According to the scatter diagram of FIG. 1, a plurality of onomatopoeia based on the application field “texture” is plotted at relative positions on the evaluation axis.
First evaluation axis: Mechanical properties (Ease of crushing <-> Difficulty of crushing)
Second evaluation axis: Geometric characteristics (aerial lightness <-> aerial weight)
In other words, the user can understand at a glance that the closer the first onomatopoeia and the second onomatopoeia are, the closer the texture is.

JP2013-033351A JP 2010-256957 A Japanese Patent Laid-Open No. 11-203278 JP 2012-123039 A

Fumiko Chubu, Chisato Asaga, Chiemi Watanabe, “Development of onomatopoeia learning system using Kansei information”, 1st Forum on Data Engineering and Information Management (DEIM2009), E5-1, 2009. Tatsuya Senmoto, Kazuhiro Takeuchi, “Assignment of onomatopoeia expressions to evaluation word-related networks trained by field data”, IEICE Technical Report, TL2014-44, 2014. Yuichiro Shimizu, Ryuichi Dobasaki, Maki Sakamoto, “System for Estimating Fine Impressions by Onomatopoeia”, Journal of the Japanese Society for Artificial Intelligence, Vol.29 No.1, pp.41-52, 2014. Maeda Yuri, Kamima University, Matsushita Mitsunori, “Evaluation of Electronic Picture Book System to Support Onomatopoeia Learning for International Students”, IPSJ 76th National Convention, 2ZF-8, 2014. Fumiyo Hayakawa, “Systematization of Japanese Texture Terms and Use for Sensory Evaluation”, Journal of Japan Society for Food Science and Technology, Vol.60, No.7, pp.311-322, 2013.

  According to the aforementioned prior art, it is difficult for foreigners to understand Japanese onomatopoeia. In particular, onomatopoeia is not described in general bilingual dictionaries, and it is very difficult to understand usage scenes and nuances.

  On the other hand, the inventors of the present application recognize that there is a human sensory expression word (for example, onomatopoeia) that is difficult to describe in a bilingual dictionary between different languages. That is, the foreigner has a known language (second language, eg, mother language) that will be close in meaning to sensory expressions in an unknown language (first language, eg, the language of the destination country). I thought that I could understand it if I could clearly show the word in Japanese.

  Therefore, the present invention provides a program, an apparatus, and a method for creating a scatter diagram that allows a user to recognize a word in a known language that has a meaning close to that of a sensory expression word in an unknown language. The purpose is to do.

According to the present invention, there is provided a program for causing a computer to function such that a scatter diagram in which a plurality of words based on a first language are scattered on a plurality of evaluation axes is displayed on a display,
For the scatter diagram, a first co-occurrence word having a high degree of co-occurrence in both the first word and the second word is derived between the first word and the second word based on the first language. The computer is caused to function so as to display the second co-occurrence word based on the second language as the translation.

According to another embodiment of the program of the present invention,
It is also preferable to cause the computer to function so that the first word and the second word based on the first language are onomatopoeia.

According to another embodiment of the program of the present invention,
It is also preferable to make the computer function so that the evaluation axis of the scatter diagram is based on correspondence analysis or based on an arbitrary feature vector.

According to another embodiment of the program of the present invention,
It is also preferable to make the computer function so that the evaluation axis of the scatter diagram represents the strength of characteristics based on human senses.

According to another embodiment of the program of the present invention,
It is also preferable to cause the computer to function so that the second co-occurrence word displayed in the scatter diagram is displayed as a thumbnail image instead of the text.

According to another embodiment of the program of the present invention,
Using a corpus based on the first language, a first co-occurrence word based on the first language that has a high degree of co-occurrence on both the first word and the second word based on the first language is extracted. First co-occurrence word extraction means;
A second co-occurrence word extracting means for translating a first co-occurrence word based on the first language into a second co-occurrence word based on the second language, using a bilingual dictionary;
Causing a computer to function as a scatter diagram creating means for creating a scatter diagram for displaying a second co-occurrence word based on a second language between a first word based on a first language and a second word Is also preferable.

According to another embodiment of the program of the present invention,
The first co-occurrence word extracting means calculates a ratio between the co-occurrence degree between the first word and the first co-occurrence word and the co-occurrence degree between the second word and the first co-occurrence word. Calculate
The scatter diagram display means preferably causes the computer to display the second co-occurrence word at a position corresponding to the ratio between the first word and the second word.

According to another embodiment of the program of the present invention,
Each application field further has a scatter diagram storage means for storing a scatter diagram,
It is also preferred to have the computer function to display the second co-occurrence word for a scatter plot based on the user desired field of application.

According to another embodiment of the program of the present invention,
Search key input means for allowing a user to input a first word based on a first language as a search key;
Scatter chart search means for searching a scatter chart including a search key from the scatter chart storage means;
It is also preferable to further cause the computer to function as a scatter diagram display means for clearly displaying the retrieved scatter diagram to the user.

According to another embodiment of the program of the present invention,
Each scatter diagram is further associated with one or more application terms based on the field of application,
The search key input means further inputs an application mode word for the first word,
The scatter diagram search means preferably causes the computer to search for a scatter diagram including the search key from one or more scatter diagrams associated with the application mode words input to the search key input means. .

According to the present invention, a device for displaying a scatter diagram in which a plurality of words based on a first language are scattered on a plurality of evaluation axes on a display,
For the scatter diagram, a first co-occurrence word having a high degree of co-occurrence in both the first word and the second word is derived between the first word and the second word based on the first language. The second co-occurrence word based on the second language serving as the parallel translation is displayed.

According to the present invention, there is provided a display method for an apparatus for displaying on a display a scatter diagram in which a plurality of words based on a first language are scattered on a plurality of evaluation axes.
For the scatter diagram, a first co-occurrence word having a high degree of co-occurrence in both the first word and the second word is derived between the first word and the second word based on the first language. The second co-occurrence word based on the second language serving as the parallel translation is displayed.

  According to the program, apparatus, and method of the present invention, a scatter diagram is created that allows a user to recognize a word in a known language that would have a similar meaning to a sensory expression word in an unknown language.

It is a scatter diagram of correspondent analysis. It is a scatter diagram of correspondent analysis in the present invention. It is a scatter diagram in which thumbnail images are displayed. It is a functional block diagram of the server in this invention.

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

  FIG. 2 is a scatter diagram of correspondent analysis in the present invention.

  According to FIG. 2, as in FIG. 1, a scatter diagram of correspondent analysis in which a plurality of onomatopoeia (onomatopoeia) is plotted is shown. The evaluation axis of the scatter diagram is based on the mechanical characteristics and geometric characteristics of the application field “texture” and represents “strength of characteristics based on human senses”. Onomatopoeia is frequently used in daily conversation for Japanese people, but is based on human senses. Therefore, onomatopoeia is not described in the bilingual dictionary or is difficult to convey even if it is described.

For example, a foreigner in English (second language) cannot understand the meaning of mochimochi in Japanese (first language).
At this time, according to FIG. 2, “mochimochi” and “tsurutsuru” are represented as onomatopoeia (onomatopoeia) of Japanese (first language) for the application field “texture”. And, “noodle (first co-occurrence word)” with high co-occurrence in both mochimochi and tsurutsuru is derived between mochimochi (first word) and tsurutsuru (second word) based on Japanese. In addition, “noodle (second co-occurrence word)” based on English (second language) as a parallel translation is displayed.
The foreigner just looks at the scatter diagram in Fig. 2 and the Japanese mochimochi is close to the Japanese tsurutsuru and has the image of "noodle".

In addition, according to FIG. 2, between the tootoro (first word) and fuwafuwa (second word) based on Japanese, both the torotoro and fuwafuwa have a high co-occurrence degree “pudding (first common "Word") is derived, and "pudding (second co-occurrence word)" based on English (second language) as the translation is displayed.
Furthermore, according to FIG. 2, between the sakusaku (first word) and boroboro (second word) based on Japanese, “cookie (first "Word") is derived, and "cookie (second co-occurrence word)" based on English (second language) as a translation is displayed.

  Note that, according to FIG. 2, the scatter diagram is such that words are scattered two-dimensionally with two evaluation axes, but even if words are scattered n-dimensionally with three or more evaluation axes. Good.

  FIG. 3 is a scatter diagram in which thumbnail images are displayed.

  According to FIG. 2, “noodle” as text is displayed between mochimochi and tsurutsuru based on Japanese. On the other hand, according to FIG. 3, a thumbnail image of “noodle” is displayed as another embodiment. In this case, as a foreigner, even a non-English speaking foreigner who cannot understand “noodle” can imagine the texture of mochimochi.

  FIG. 4 is a functional configuration diagram of the server in the present invention.

According to FIG. 4, the server 1 and the terminal 2 possessed by the user are connected via a network.
The server 1 includes a scatter diagram storage unit 100, a corpus 101, a bilingual dictionary 102, a first co-occurrence word extraction unit 11, a second co-occurrence word extraction unit 12, a scatter diagram creation unit 13, and a search A key input unit 14, a scatter diagram search unit 15, and a scatter diagram display unit 16 are provided. These functional components are realized by executing a program that causes a computer mounted on the server to function. The processing flow of these functional components can also be understood as a scatter diagram creation method.

A corpus 101 is a database in which natural language sentences are structured and accumulated on a large scale.
The bilingual dictionary 102 is a dictionary in which English (second language) words are described as bilingual translations of Japanese (first language) words, for example.

[Scatter diagram storage unit 100]
The scatter diagram storage unit 100 stores scatter diagrams for each application field. In other words, the scatter diagrams are created with different evaluation axes, such as application fields “texture”, “tactile sensation”, “attitude”, “emotion”, “health”, “medicine”, and “sports”. Among such words based on human senses, there is Onomatopoeia, for example, which is easy for Japanese to understand but difficult for foreigners to understand.

The evaluation axis of the scatter diagram is based on the following analysis, for example.
(1) Corresponding analysis Elements with higher correlation are plotted closer.
(2) Arbitrary feature vector For example, word2vec (registered trademark), which is a vector that expresses a word and compresses the dimension in order to capture the meaning and grammar of the word. This is a two-layer neural network that can output a feature vector of a word from input text.

For example, onomatopoeia may have completely different meanings depending on the field of application. For example, in the case of “strain”, it has the following meaning.
Field of application: “Food texture”: “This noodle is“ shikoshi ””
“Cheap”
Field of application “Attitude”: “Study with“ Shiko ””

As another embodiment, it is also preferable that one or more “application mode words” based on the application field are further associated with each scatter diagram. The “application mode word” is a keyword representing an application field of onomatopoeia.
For example, for the scatter diagram of the application field “texture”, keywords such as “meal”, “cooking”, and “food” are assigned as application mode words. Such keywords are used by the scatter diagram search unit 15 described later.

  According to FIG. 4, the scatter diagram storage unit 100 outputs the existing scatter diagram as shown in FIG. 1 to the first co-occurrence word extraction unit 11 from the scatter diagram creation unit 13 according to the present invention. Enter and accumulate. In other words, the existing scatter diagram is updated to the scatter diagram of the present invention by the first co-occurrence word extraction unit 11, the second co-occurrence word extraction unit 12, and the scatter diagram creation unit 13.

[First Co-occurrence Word Extraction Unit 11]
The first co-occurrence word extraction unit 11 inputs a scatter diagram from the scatter diagram storage unit 100. The first co-occurrence word extraction unit 11 uses the corpus based on the first language, and the first co-occurrence degree is high in both the first word and the second word based on the first language. A first co-occurrence word based on the language is extracted.
Specifically, according to FIG. 2 described above, the degree of co-occurrence in both the onomatopoeia (onomatopoeia) “mochimochi” and “tsurutsuru” using the Japanese (first language) corpus 101. “Noodle (first co-occurrence word)” having a high is extracted.

The degree of co-occurrence is calculated based on, for example, a mutual information amount standard between “mochimochi” as a key and each of other words (for example, “noodle”, “salmon”, “udon”, “rice”, etc.). For example, for each word that co-occurs with “mochi mochi” from the corpus, the counted appearance frequency is set as “co-occurrence degree”. For example, assume that the corpus has the following text:
"Noodles with" mochimochi ""
"The noodles are mochimochi"
"The rice cake that was mochimochi"
"Udon made"
"Rice with rice cake"
...

Here, the co-occurrence degree is calculated as mutual information. The mutual information amount is a probabilistic method that represents a measure of mutual dependence in two random variable elements xi and yj, and is calculated as follows.
I (xi, yj) = log {p (xi, yj) / p (xi) p (yj)}
p (): Number of appearances For example, suppose that there are the following number of appearances in 10,000 words.
Number of occurrences of “mochimochi” and “noodle” p = 20 times Number of occurrences of “mochimochi” p = 24 times Number of occurrences of “noodle” p = 120 times In this case, mutual information between “mochimochi” and “noodles” The quantity is expressed as follows:
I (mochimochi, noodle) = log {p (mochimochi, noodle) / p (mochimochi) p (noodle)}
= Log ₂ {(20/10000) / ((120/10000) ・ (24/10000))}
≒ 6.118

In this way, the mutual information amount for all the dependency words is calculated.
I (mochimochi, noodles)
I (mochi, mochi)
I (mochimochi, udon)
I (mochimochi, rice)
...
In this, it means that it is used combining relatively many, so that mutual information amount is large. In order to calculate an appropriate mutual information amount, it is assumed that an absolute appearance frequency of a certain level or more is observed using the corpus 101. On the other hand, reliability is ensured by excluding minority cases that do not meet this requirement.

Next, in the scatter diagram, “smooth vine” arranged near the key “mochi mochi” is also calculated, for example, based on the mutual information criterion between each of the other words as described above. For example, assume that the corpus has the following text:
"Smooth noodles"
"Sudden udon"
"Ramen that is smooth"
“Some noodles that were“ smooth ””
...
In this case, the mutual information amount for all the dependency words is calculated as follows.
I (smooth, noodles)
I (Smooth, Udon)
I (Smooth, Ramen)
I (Smooth, Somen)
...

  Here, it is assumed that a word having a high co-occurrence degree for both “mochimochi” and “smooth vine” is “noodle”. At this time, “noodle” is extracted as the first co-occurrence word. “Noodle” (first co-occurrence word) is an important associative concept for “mochimochi” (first word) and “surutsuru” (second word) based on Japanese (first language). It becomes the word.

Further, as another embodiment, the first co-occurrence word extraction unit 11 calculates the degree of co-occurrence between the first word and the first co-occurrence word, and the second word and the first co-occurrence word. It is also preferable to calculate a ratio with the co-occurrence degree.
Specifically, for the first co-occurrence word (eg, “noodle”), the co-occurrence degree between the first word (eg, “mochimochi”) and the second word (eg, “smooth”) The ratio with the co-occurrence degree is calculated. For example, assume the following.
“Mochimochi” 0.3: 0.7 “Smooth”
Of course, when the co-occurrence degree between the first word (for example, “mochimochi”) and the co-occurrence degree between the second word (for example, “smooth”) are exactly the same, as follows: Become.
“Mochimochi” 0.5: “Smooth” 0.5

[Second Co-occurrence Word Extraction Unit 12]
The second co-occurrence word extraction unit 12 translates the first co-occurrence word based on the first language into the second co-occurrence word based on the second language, using the bilingual dictionary 102.
Specifically, “noodle” (first co-occurrence word) based on Japanese (first language) is translated into “noodle” (second co-occurrence word) based on English (second language). To do. This allows foreigners in English-speaking countries to understand that “mochimochi” in the application field “texture” is close to “noodle”.

[Scatter plot creation unit 13]
The scatter diagram creation unit 13 creates a scatter diagram for displaying the second co-occurrence word based on the second language between the first word based on the first language and the second word.
Specifically, the English “noodle” (second co-occurrence word) is displayed between the Japanese “mochimochi” (first word) and “smooth” (second word). Update the scatter plot. Accordingly, a universal interface that does not depend on the native language can be provided to the user by displaying words (nouns and verbs) that frequently appear, for example, for onomatopoeia.
The first co-occurrence word extraction unit 11 extracts a plurality of first co-occurrence words, and the second co-occurrence word extraction unit 12 translates the plurality of second co-occurrence words into the first You may display between a word and a 2nd word.
The scatter diagram updated in this way is output to the scatter diagram storage unit 100.

As another embodiment, it is also preferable that the scatter diagram creating unit 13 displays the second co-occurrence word at a position corresponding to the ratio of the co-occurrence degree between the first word and the second word.
According to FIG. 2, for example, when the ratio of co-occurrence between “mochimochi” and “smooth vine” with respect to “noodle” is 0.3: 0.7, from the plot position of “smooth vine”, “mochimochi” “Noodles” are plotted at a position of 0.3: 0.7 between the plot positions. This means that the user can recognize at a glance that “noodle” has a higher degree of co-occurrence with “smooth” than “mochimochi”.

  As another embodiment, onomatopoeia having phonological similarity can be further plotted on the onomatopoeia plotted in the scatter diagram. Since onomatopoeia based on Japanese has a strong tendency to make words, there is an elapsed period from the creation of a new coined expression to its establishment (reflected in a knowledge source such as a dictionary). In such a case, it is assumed that no corresponding translation is found. For example, there is a case where a coined word such as “Fuwatoro” is prevalent for onomatopoeia. In that case, the appearance context is expected to be close to both “fluffy” and “torotoro”. Therefore, from the similarity of co-occurrence words in the corpus, “Fuwatoro” is plotted in the vicinity of “Fuwafuwa” and “Torotoro” in the scatter diagram. In this case, the user can understand the translations of the closely related word group even if the direct translation is not displayed.

[Search key input unit 14]
The search key input unit 14 inputs a first word based on the first language as a “search key” from the terminal 2 possessed by the user. According to the above, for example, when a foreigner wants to know the meaning of “mochimochi” (first word) in Japanese (first language), “mochimochi” is input as a search key.
The input search key is output to the scatter diagram search unit 15.

  As another embodiment, it is also preferable that the search key input unit 14 further causes the user to input an “application mode word” for the first word. For example, it is like “meal” (application mode word) for “mochimochi”. The application mode word is used by the scatter diagram search unit 15 to search for a scatter diagram based on the application field.

  Further, as another embodiment, the search key input unit 14 inputs, for example, a search sentence, and extracts a word appearing as a context as an application mode word from the search sentence using onomatopoeia as a search key. There may be.

[Scatter diagram search unit 15]
The scatter diagram search unit 15 uses the scatter diagram storage unit 100 to search for a scatter diagram including a search key. Specifically, a scatter diagram including “mochimochi” (search key) input by the search key input unit 14 is searched.

At this time, a plurality of scatter diagrams based on different application fields may be searched. For this purpose, the scatter diagram search unit 15 may also search for a scatter diagram including the search key from one or more scatter diagrams associated with the “application mode word” input to the search key input unit 14. preferable.
In the scatter diagram of the application field “texture”, keywords such as “meal”, “cooking”, and “food” are given as application mode words (see the scatter diagram storage unit 100 described above). When the search key “mochimochi” and the application mode word “meal” are input from the user, a scatter diagram including “mochimochi” is searched from one or more scatter diagrams to which the application mode word “meal” is assigned. Is done.

[Scatter diagram display section 16]
The scatter diagram display unit 16 returns the scatter diagram retrieved by the scatter diagram search unit 15 to the terminal 2.

As described above in detail, according to the program, apparatus, and method of the present invention, a user recognizes a word in a known language that has a meaning close to that of a sensory expression word in an unknown language. Create a scatter plot that you can.
Specifically, a known language (second language, eg, native language) that will be close in meaning to a sensory expression word in an unknown language (first language, eg, the language of the destination country) By clearly indicating the word, it is possible for foreigners to understand the usage situation and nuance of the word.

  Various changes, modifications, and omissions of the above-described various embodiments of the present invention can be easily made by those skilled in the art. The above description is merely an example, and is not intended to be restrictive. The invention is limited only as defined in the following claims and the equivalents thereto.

DESCRIPTION OF SYMBOLS 1 Server 100 Scatter chart storage part 101 Corpus part 102 Bilingual dictionary part 11 1st co-occurrence word extraction part 12 2nd co-occurrence word extraction part 13 Scatter figure creation part 14 Search key input part 15 Scatter figure search part 16 Scatter figure Display section

Claims (12)

A program for causing a computer to function on a display to display a scatter diagram in which a plurality of words based on a first language are scattered on a plurality of evaluation axes.
For the scatter diagram, a first co-occurrence word having a high degree of co-occurrence is derived between the first word and the second word based on the first language in both the first word and the second word. And a program for causing the computer to function to display a second co-occurrence word based on the second language to be translated. The program according to claim 1, wherein the computer functions so that the first word and the second word based on the first language are onomatopoeia. The program according to claim 1 or 2, wherein the computer is caused to function so that the evaluation axis of the scatter diagram is based on correspondence analysis or based on an arbitrary feature vector. The program according to any one of claims 1 to 3, wherein the computer is caused to function so that the evaluation axis of the scatter diagram represents the strength of characteristics based on a human sense. 5. The computer according to claim 1, wherein the computer functions so that the second co-occurrence word displayed in the scatter diagram is displayed as a thumbnail image instead of the text. 6. program. Using a corpus based on the first language, a first co-occurrence word based on the first language that has a high degree of co-occurrence on both the first word and the second word based on the first language is extracted. First co-occurrence word extraction means;
A second co-occurrence word extracting means for translating a first co-occurrence word based on the first language into a second co-occurrence word based on the second language, using a bilingual dictionary;
Causing a computer to function as a scatter diagram creating means for creating a scatter diagram for displaying a second co-occurrence word based on a second language between a first word based on a first language and a second word The program according to any one of claims 1 to 5. The first co-occurrence word extracting means calculates a ratio between the co-occurrence degree between the first word and the first co-occurrence word and the co-occurrence degree between the second word and the first co-occurrence word. Calculate
The scatter diagram creating means causes the computer to function to display a second co-occurrence word at a position corresponding to the ratio between the first word and the second word. 6. The program according to 6. Each application field further has a scatter diagram storage means for storing a scatter diagram,
The program according to any one of claims 1 to 7, wherein the computer is caused to function to display a second co-occurrence word with respect to a scatter diagram based on an application field desired by a user. Search key input means for allowing a user to input a first word based on a first language as a search key;
Scatter chart search means for searching a scatter chart including the search key from the scatter chart storage means;
9. The program according to claim 8, further causing the computer to function as a scatter diagram display means for clearly displaying the retrieved scatter diagram to the user. Each scatter diagram is further associated with one or more application mode words based on the application field,
The search key input means further inputs an application mode word for the first word,
The scatter diagram search means functions a computer to search for a scatter diagram including the search key from one or more scatter diagrams associated with the application mode word input to the search key input means. The program according to claim 9, wherein: A device that displays on a display a scatter diagram in which a plurality of words based on a first language are scattered on a plurality of evaluation axes,
For the scatter diagram, a first co-occurrence word having a high degree of co-occurrence is derived between the first word and the second word based on the first language in both the first word and the second word. And displaying a second co-occurrence word based on the second language to be translated. A display method of an apparatus for displaying on a display a scatter diagram in which a plurality of words based on a first language are scattered on a plurality of evaluation axes,
For the scatter diagram, a first co-occurrence word having a high degree of co-occurrence is derived between the first word and the second word based on the first language in both the first word and the second word. And displaying a second co-occurrence word based on the second language to be translated.

Images