JP2001043220A - Method and device for processing document and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent a sentence from being unclear by containing no omitted the subject or the object in a summary sentence when preparing the summary sentence of an electronic document. SOLUTION: In the case of preparing a summary sentence of a document, when a zero corresponding element zi such as omitted subject or object of a vocabulary element ti contained in the summary sentence to be prepared exists, it is discriminated whether this zero corresponding element zi is the element of a zero correspondence list ZAList or not (step S85) and in the case of YES, the vocabulary element ti is added to the summary sentence as it is (step S86) but in the case of NO, only when the zero corresponding element zi is not contained in the summary sentence, the zero corresponding element zi is put in parentheses and added to the summary sentence together with the vocabulary element ti (step S89). Then, ti and zi are added to ZAList.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to a document processing method and apparatus for processing an electronic document and a recording medium on which a document processing program for processing an electronic document is recorded.

[0002]

2. Description of the Related Art Conventionally, WWW (World Wide Web) is known as an application service for providing hypertext information in a window format on the Internet.

[0003] The WWW is a system that executes document processing for creating, publishing, or sharing a document and showing the way of a new style document. However, from the viewpoint of practical use of documents, advanced document processing beyond WWW, such as classification and summarization of documents based on the contents of the documents, is required. For such advanced document processing, mechanical processing of the contents of the document is indispensable.

However, mechanical processing of the contents of a document is still difficult for the following reasons. First, HTML (Hyper Text Markup Language), which is a language for describing hypertext, defines the expression of a document, but hardly defines the content of the document. Third, a written hypertext network is not always easy for readers of a document to understand the contents of the document, and thirdly, authors of texts generally write without the convenience of the reader. However, the fact that the convenience of the reader of the document is not coordinated with the convenience of the author is the reason why the mechanical processing of the document is difficult.

[0005] As described above, WWW is a system showing the way of a new document. However, since the document is not mechanically processed, advanced document processing cannot be performed. In other words, in order to perform advanced document processing, it is necessary to process the document mechanically.

Therefore, a system for supporting mechanical processing of documents has been developed based on the results of natural language research, with the goal of mechanical processing of documents. As a document processing based on natural language research, mechanical document processing using tags attached to a document has been proposed on the assumption that attribute information about the internal structure of the document by the author of the document, so-called tags are added. I have.

By the way, the spread of computers in recent years,
With the progress of networking, there has been a demand for sophisticated document processing for creating, labeling, and changing text documents by using text processing, indexes depending on the contents of documents, and the like. For example, it is desired to summarize a document according to a user's request, classify the document, and the like.

[0008] That is, a user uses an information search system such as a so-called search engine to search for desired information from a vast amount of information provided through the Internet. This information search system is a system that searches for information based on a specified keyword and provides the searched information to a user. The user selects desired information from the provided information.

[0009] In the information retrieval system, information can be easily retrieved as described above. However, the user must read the retrieved and provided information to understand the outline, and determine whether the information is the desired information. It is necessary to determine whether or not. This operation imposes a heavy burden on the user, especially when the amount of provided information is large. Therefore, recently, a so-called automatic summary sentence creating system, which is a system for automatically summarizing text information, that is, a content of a document, has attracted attention.

The automatic summary text creation system is a system for creating a summary text by reducing the length and complexity of text information while maintaining the original information, ie, the meaning of the document. The user can understand the outline of the document by reading the summary sentence created by the automatic summary sentence creation system.

Normally, an automatic summary sentence creating system assigns a sentence or word in a text as one unit, and assigns an importance based on some information to order the sentence or word. Then, the automatic summary sentence creating system collects sentences and words ordered in a higher order and creates a summary sentence.

[0012]

By the way, in the above-mentioned automatic summary text creation system, it is possible to create a summary text from a document. Was determined by for that reason,
In the automatic summary text creation system, for example, when the created summary text is too simple for the user to grasp the outline of the document, the user cannot refer to a more detailed summary text.

In addition, when the omitted part of the subject in the original sentence is incorporated in the abstract, if the omitted part is not included in the abstract, accurate contents cannot be grasped from the abstract. Also.

The present invention has been proposed in view of the above-mentioned circumstances, and a document processing method capable of automatically generating an accurate summary sentence easily understood by a user for an input document. And a recording medium on which a document processing program is recorded.

[0015]

In order to solve the above-mentioned problems, the present invention provides a document processing method and apparatus for processing a document in the form of an electronic document. When the omitted subject or object in the sentence is not included in the abstract, the corresponding subject or object in the original document is added to the abstract.

Here, the abbreviated subject or object is referred to as a zero-anaphoric element, and it is determined whether or not the zero-anaphoric element is included in the summary sentence. Preferably, the anaphoric element is added in parentheses in the summary sentence.

Thus, it is possible to prevent the abbreviated subject from including any omitted subject or object.

[0018]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of a document processing method and apparatus and a recording medium in which a document processing program is recorded according to the present invention will be described with reference to the drawings.

As shown in FIG. 1, a document processing apparatus according to an embodiment of the present invention includes a main unit 10 having a control unit 11 and an interface 12, an input unit 20 which receives an input from a user and sends it to the main unit 10. A communication unit 22 that receives an external signal and sends it to the main unit 10, a display unit 30 that displays an output from the main unit 10, and a recording / reproducing unit 31 that records / reproduces information on / from a recording medium 32. Have.

The main body 10 has a control unit 11 and an interface 12, and constitutes a main part of the document processing apparatus. The control unit 11 includes a CPU 13 that executes processing in the document processing apparatus, and a RA that is a volatile memory.
M14 and a ROM 15 which is a non-volatile memory. The CPU 13 performs control for executing each process in accordance with, for example, a procedure of a program recorded in the ROM 15. The RAM 14 temporarily stores programs and data necessary for the CPU 13 to execute various processes. The interface 12 includes a control unit 11, an input unit 20, a communication unit 22, a display unit 30, and a recording / reproducing unit 31.
It is connected to the. The interface 12 transmits data for input of data from the input unit 20 and the communication unit 22, transmission of data to the display unit 30, and transmission and reception of data to the recording / reproducing unit 31 under the control of the control unit 11. To adjust the timing of data conversion and data format conversion.

The input section 20 is a section for receiving a user's input to the document processing apparatus, and comprises, for example, a keyboard and a mouse. The user can use the input unit 20 to input a keyword using a keyboard or select and input an element of the electronic document displayed on the display unit 30 using a mouse. In the following, an electronic document will be simply referred to as a document. Here, the element is an element constituting a document, and includes, for example, a document, a sentence, a phrase, and a word.

The communication section 22 is a section for receiving a signal transmitted from the outside to the document processing apparatus via a communication path, for example, a telephone line. Specifically, the communication unit 22 is configured by, for example, a modem, a terminal adapter, and the like, is connected to the Internet 23 via a telephone line, accesses a server 24 connected to the Internet, and from there, data such as a document. Have been able to receive. Such a communication unit 22 receives data such as a plurality of documents transmitted from the outside, and sends the received data to the main body 10.

The display unit 30 displays the output of characters and image information from the document processing device. The display unit 30 includes, for example, a cathode ray tube (CRT) or a liquid crystal display (li).
It is composed of a liquid crystal display (LCD) and displays, for example, one or more windows, and displays characters, figures, images, and the like.

The recording / reproducing unit 31 records and / or reproduces data on a removable recording medium 32 such as a floppy disk, an optical disk, and a magneto-optical disk. In the recording medium 32, a document processing program for processing a document is recorded. The recording medium 32 records an electronic document processing program for processing a document and a document to be processed.

The hard disk drive 33 records and / or reproduces data on a hard disk which is a large-capacity magnetic recording medium.

Such a document processing apparatus receives a desired document and displays it on the display unit 31 as follows.

In the document processing apparatus, first, the user operates the input unit 20 to start a program for performing communication via the Internet 23, and inputs a URL (Uniform Resource Locator) of the server 24 (search engine). , The control unit 11 controls the communication unit 22 and the server 2
Access 4

In response, the server 24 outputs the data of the search screen to the communication unit 22 of the document processing device via the Internet 23. CPU1 in the document processing device
3 outputs the data to the display unit 30 via the interface 12 and causes the display unit 30 to display the data.

In the document processing apparatus, when a user inputs a keyword or the like on this search screen using the input unit 20 and instructs a search, the communication unit 22 transmits the keyword to the Internet 23.
, A search command is transmitted to the server 24 as a search engine.

When receiving the search command, the server 24 executes the search command and transmits the obtained search result to the communication unit 22 via the Internet 23. In the document processing apparatus, the control unit 11 controls the communication unit 22 and
, And a part thereof is displayed on the display unit 30.

Specifically, when the user inputs a keyword such as “TCP” using the input unit 20 and instructs a search, the document processing apparatus includes the keyword “TCP” from the server 24. Various information is transmitted and displayed on the display unit 30.

Next, a document according to the present embodiment will be described. In the present embodiment, document processing is performed with reference to a tag that is attribute information given to a document. Tags used in the present embodiment include a syntactic tag indicating the structure of a document and a semantic (semanti) tag that enables mechanical understanding of the content of a document between multiple languages.
c) ・ There is a pragmatic tag.

Some syntactic tags describe the internal structure of a document. As shown in FIG. 2, the internal structure by tagging is configured such that each element such as a document, a sentence, and a vocabulary element is associated with a normal link and a reference / referenced link. In the figure, white circle “○”
Indicates an element, and the white circle at the bottom is a vocabulary element corresponding to the lowest level word in the document. A solid line is a normal link indicating a connection between elements such as a document, a sentence, and a vocabulary element. The broken line is a reference link (refe
rence link). The internal structure of a document is document, subdivision (su
bdivision), paragraph, sentence (
Subsentential segmen
t) consists of vocabulary elements. Of these, the subdivisions and paragraphs are used, for example, as options.

On the other hand, as semantic / pragmatic tagging, tags such as syntactic structure indicating a referent of a pronoun or the like or semantic like the meaning of a polysemy are used. There is something that describes the information. Tagging in the present embodiment is performed in HTML.
XML (eXte) similar to (Hyper Text Markup Language)
nsible Markup Language).

The following is an example of a tagged sentence or document, but tagging of the document is not limited to this method. In the following, examples of English and Japanese documents are shown. However, it is needless to say that the description of the internal structure by tagging can be similarly applied to other languages.

For example, "Time flies like an arrow."
Can be tagged as follows:

<Sentence><noun phrase meaning = “time0”> time
</ Noun phrase><verbphrase><verb meaning = "fly1"> flies </ verb><adjective verb phrase><adjective verb meaning = "like0"> like <
/ Adjective verb><nounphrase> an <noun word meaning = "arrow0"> arrow </ noun></ noun phrase></ adjective verb phrase></ verb phrase>. <// sentence> where <sentence>, < Noun, <noun phrase>, <verb>, <verb phrase>, <adjective verb>, <adjective verb phrase> are sentence, noun, noun phrase, verb, verb phrase, prepositional phrase or postposition including adjective, respectively. It represents a syntactic structure of a sentence, such as an adjective / adjective phrase or an adjective / adjective verb phrase. Tags are arranged corresponding to immediately before the front end and immediately after the end of the element. The tag placed immediately after the end of the element indicates that it is the end of the element by the symbol "/". Elements indicate syntactic constituents, ie, phrases, clauses, and sentences. Note that word sense =
“Time0” indicates a plurality of meanings of the word “time”, that is, a 0th meaning of the plurality of meanings. Specifically, the word “time” has at least the meanings of a noun, an adjective, and a verb. Here, it indicates that the word “time” is a noun. Similarly, the word "orange" has at least the meaning of plant name, color, and fruit, but these can also be distinguished by their meaning.

As shown in FIG. 3, the document used in the present embodiment is a window 101 of the display unit 30 shown in FIG.
The syntactic structure can be displayed. This window 1
In 01, the vocabulary elements are displayed on the right half 103, and the internal structure of the sentence is displayed on the left half 102.
In this window 101, not only a document described in Japanese but also a document described in an arbitrary language such as English can display a syntactic structure.

In the window 101, for example,
The following document describing the internal structure by tagging: "In the city C where Mr. A's B meeting was over, some popular papers and general newspapers clarified the policy to voluntarily regulate the photo report Is displayed. An example of tagging this document follows.

<Document><sentence><adjective verb phrase relation = “position”><nounphrase><adjective verb phrase place = “C city”><adjective verb phrase relation = “subject”><noun phrase identifier =
“B meeting”><adjective verb phrase relation = “affiliation”><person name identifier = “Mr. A”> Mr. A </ person name></ adjective verb phrase><organization name identifier = “B meeting”> B meeting < / Organization name><Nounphrase></ Adjective verb phrase> Finished </ Adjective verb phrase><Place name identifier = "C city">
C city </ place name></ noun phrase>, </ adjective verb phrase><adjective verb phrase relation = "subject"><noun phrase identifier = "pres
s ”syntactic =“ parallel ”><nounphrase><adjective verb phrase> Some </ adjective verb phrases> popular paper </ noun phrase> and <noun> general paper </ noun></ noun phrase> / Adjective verb phrase><adjective verb phrase relation = “object”><adjective verb phrase relation = “content” subject = “press”><adjective verb phrase relation =
"Object"><nounphrase><adjective verb phrase><noun co-reference =
"B-kai"> so </ noun></ adjective verb phrase> photo coverage <
</ Noun phrase></ adjective verb phrase> Self-regulating </ adjective verb phrase> Policy </ adjective verb phrase><adjective verb phrase relation = "position"></ adjective verb phrase> on paper. </ Sentence></document> In this document, "part of popular paper and general paper" is expressed in parallel by a tag of syntactic = "parallel". The definition of parallel is to share a dependency relationship. If nothing is specified, for example, <noun phrase relation = x><noun> A </ noun><noun> B <//
Noun >></ noun phrase> indicates that A has a dependency on B. Relation = x represents a relation attribute.

The relation attribute describes the mutual relation between syntactic, meaning, and rhetorical. Grammar functions such as subjects, objects, and indirect objects, subject roles such as an actor, a subject, beneficiaries, and the like, and rhetorical relations such as a reason and a result are described by the relation attributes. In the present embodiment, relation attributes are described for relatively easy grammatical functions such as a subject, an object, and an indirect object.

In this document, "Mr. A"
For proper nouns such as "B Association" and "C City", place names,
Attributes are described by tags such as person names and organization names. These words to which tags such as place names, personal names, and organization names are given are proper nouns.

In such a tagged document, a reference to a pronoun or a restrictive clause or a referenced relationship is represented by a tag. For example, in the above document,
The "that" part of the "photo coverage" element
By having the attribute “co-reference =“ B meeting ””, that part can be an element (in this case, a noun phrase) “Mr. A's B meeting” having the attribute “identifier =“ B meeting ””. It is shown. Therefore, replacing the part of "the photograph report" with "the report" becomes "the photograph report of Mr. A's B meeting".

Further, in such a tagged document, the omitted subject, object, and the like can be supplemented by other parts. That is, in the example of the above document, the element of “self-regulating” is “subject =“ pres
s ”” attribute indicates that the semantic subject is an element (in this case, a noun phrase) with the attribute “identifier =“ press ”” “some general paper and popular paper” Have been. Therefore, the complement of the subject is
"(Some general and popular newspapers) self-regulate."
Thus, the elimination of an omission by another part is called zero anaphor.

Hereinafter, a specific operation of the document processing apparatus according to the embodiment of the present invention will be described. The document processing apparatus according to the present embodiment is configured to perform an automatic summarization process on a document tagged as described above. Performs a zero anaphoric process to supplement the omitted subject.

When the document processing apparatus creates a summary of a document, the user operates the input unit 20 while the document is displayed on the display unit 30 in FIG. Switch. When the control section 11 is switched to the automatic summary mode, the control section 11 displays an initial screen of the automatic summary statement creation program as shown in FIG. 4 and waits for the user to start the automatic summary statement creation operation.

That is, when the user performs an operation to switch to the automatic summary sentence creation mode, the control unit 11 shown in FIG.
Starts the automatic summary sentence creation program stored in the hard disk device 33, controls the display unit 30,
Display the initial screen of the automatic summary sentence creation program as shown in (1). In this example, a window 190 displayed on the display unit 31 includes a document name display unit 191 for displaying the name of the document, a keyword input unit 192 for inputting a keyword, and an execution button for creating a summary of the document. , A display area 200 for displaying a document, a display area 210 for displaying a document, and a display area 220 for displaying a summary of the document.

In the document name display section 191 of the display area 200, the document name of the document displayed in the display area 210 is displayed. In addition, a keyword for creating a summary of a document is input to the keyword input unit 192 using, for example, the keyboard of the input unit 20. The summary sentence creation execution button 193 is an execution button for starting execution of a summary sentence creation process for the document displayed in the display area 210 by being pressed using, for example, the mouse of the input unit 20.

In the display area 210, a document is displayed.
At the right end of the display area 210, a scroll bar 211,
Buttons 212 and 213 for moving the scroll bar 211 up and down are provided. The user can directly move the scroll bar 211 up and down by using, for example, a mouse of the input unit 20 or scroll by pressing the buttons 212 and 213. By moving the bar 211 up and down, the display content displayed in the display area 210 can be scrolled in the vertical direction. By operating the input unit 20, the user can select and summarize a part of the document displayed in the display area 210, or can summarize the entire document.

The display area 220 displays a summary sentence. In FIG. 4, nothing is displayed in display area 220 because a summary has not been created yet. The user can change the display range (size) of the display area 220 of the summary sentence by operating the input unit 20. Specifically, the user changes the display range (size) of the display area 220 shown in FIG.
It can be enlarged as shown in FIG.

The document processing device allows the user to input, for example,
When the summary sentence creation execution button 193 is turned on by using a mouse 0 or the like, under the control of the CPU 13,
The process shown in FIG. 6 is executed to start creating a summary sentence.

The process of creating an abstract from a document is executed based on tagging of the internal structure of the document. In the document processing apparatus, the size of the display area 220 of the window 190 can be changed as shown in FIG. The document processing device, under the control of the CPU 13,
Whether a new window 190 is drawn on the display unit 31 or
Alternatively, when the summary sentence creation execution button 193 is operated after the size of the display area 220 is changed, at least a part thereof is displayed in the display area 210 of the window 190 so as to match the display area 220. From the existing document.

First, as shown in FIG. 6, the document processing apparatus performs a process called active diffusion under the control of the CPU 13 in step S21. In the present embodiment, a summary sentence of a document is performed by employing the central activity value obtained by activity diffusion as the importance. That is, in a document tagged with an internal structure, by performing active diffusion, a central activation value corresponding to the tagging with respect to the internal structure can be given to each element.

Here, the active diffusion is a process for giving a high central activity value also to an element related to an element having a high central activity value. In other words, the active diffusion means that the central activity values become equal between the element expressed in anaphora (coreference) and its antecedent, and otherwise, each central activity value converges to the same value. . Since the central activity value is determined according to tagging relating to the internal structure of the document, it can be used for analysis of the document in consideration of the internal structure.

The document processing apparatus executes active diffusion by going through a series of steps shown in FIG.

First, as shown in FIG. 7, the document processing apparatus initializes each element under the control of the CPU 13 in step S41. The document processing device assigns the initial value of the central activity value to all the elements except the vocabulary element and the vocabulary element. For example, the document processing apparatus sets the initial value of the central activity value to “1” for all elements except the vocabulary element.
And “0” is assigned to the vocabulary element. In addition, the document processing apparatus can reflect the bias of the initial value in the central activity value obtained as a result of activity diffusion by assigning a non-uniform value to the initial value of the central activity value of each element in advance. For example, the document processing apparatus can obtain a central activity value reflecting the interest of the user by setting a high initial value of the central activity value for an element of interest to the user.

Regarding the reference / referenced link which is a link having a dependency relationship by reference / reference between elements and the normal link which is another link, the end point activation value of the end point of the link connecting the elements. Is set to “0”. The document processing apparatus stores the initial value of the end point activation value thus assigned, for example, in the RAM 14.

FIG. 8 shows an example of an element-to-element connection structure. In the figure, an element _Ei and an element _Ej are shown as a part of the structure of the element and the link that constitute the document. Element E _i
And the element E _j are the central activation values e _i and e _j , respectively.
And are connected by a link L _ij . The end point of the link L _ij connected to the element E _i is T _ij , and the end point of the link L _ij connected to the element E _j is T _ji . Element E _i
, In addition to the elements _{E j,} which is connected by a link L _ij, the link _L ik, L _il and L _im element E _k (not shown) by, respectively connected to the E _l and E _m. The element E _j is connected to elements E _p , E _q, and _{Er (} not shown) by links L _jp , L _jq, and L _jr , respectively, in addition to the element E _i connected by the link L _ji .

[0059] Then, the document processing device, in step S42 in FIG. 7, under the control of the CPU 13, performs initialization of a counter for counting the elements E _i of a document. That is, the document processing apparatus sets the counter value i of the counter for counting the elements to “1”. Thus, the counter will be that refers to the first element E _1.

Subsequently, the document processing device proceeds to step S43.
, Under the control of the CPU 13, a link process for calculating a new central activation value is executed for the element referred to by the counter. This link processing will be further described later.

Subsequently, the document processing device proceeds to step S44.
, Under the control of the CPU 13, it is determined whether or not the calculation of a new central activation value has been completed for all elements in the document.

Here, when the document processing device determines that the calculation of the new central activation value has been completed for all the elements in the document, the process proceeds to step S45, while the process proceeds to step S45. If it is determined that the calculation of the new central activity value has not been completed for all the elements, the process proceeds to step S47.

More specifically, the document processing device is a CPU 13
Under the control of, it is determined whether or not the counter value i of the counter has reached the total number of elements included in the document. If the document processing apparatus determines that the counter value i of the counter has reached the total number of elements included in the document, it is determined that all elements have been calculated, and the process proceeds to step S45. . On the other hand, when the document processing apparatus determines that the counter value i of the counter has not reached the total number of elements included in the document, it is determined that the calculation has not been completed for all elements, and the process proceeds to step S47. Transition.

The document processing apparatus sets the counter value i
Determines that the total number of elements included in the document has not been reached, in step S47
Under the control of 3, the count value i of the counter is incremented by “1” and the count value of the counter is incremented by “i +
As a result, the counter refers to the (i + 1) th element, that is, the next element. Then, the document processing apparatus shifts the processing to step S43, calculates the endpoint activation value, and follows the calculation. A series of steps is performed for the next (i + 1) th element.

When the document processing device determines that the counter value i of the counter has reached the total number of elements included in the document, the document processing device determines in step S45 that the CPU 1
Under the control of 3, the average value is calculated for the change in the central activity value of all the elements included in the document, that is, the change in the newly calculated central activity value from the original central activity value.

Under the control of the CPU 13, the document processing apparatus reads, for example, the original center activity value and the newly calculated center activity value stored in the RAM 14 for all the elements included in the document. The document processing apparatus divides the sum of the respective changes of the newly calculated central activity value from the original central activity value by the total number of elements included in the document, thereby obtaining the change in the central activity value of all the elements. Calculate the average value. The document processing device calculates the average value of the change in the central activity value of all the elements calculated in this way,
For example, it is stored in the RAM 14.

Then, the document processing apparatus proceeds to step S46.
In step S45 under the control of the CPU 13,
It is determined whether or not the average value of the change in the central activity values of all the elements calculated in the above is within a preset threshold value. Then, when the document processing device determines that the change is within the threshold, the document processing apparatus ends the series of steps.
On the other hand, when the document processing device determines that the change is not within the threshold, the process proceeds to step S42, where the count value i of the counter is set to “1” and the central activation value of the element of the document is set. Execute the series of steps to be calculated again.
In the document processing apparatus, each time the loop of steps S42 to S46 is repeated, the amount of change gradually decreases.

The document processing apparatus can perform active diffusion in this way. Next, a link process executed in step S43 to perform this active diffusion will be described with reference to FIG. The flowchart shown in the figure, but shows the processing for one element E _i, this processing is to be performed for all elements.

[0069] First, the document processing apparatus, as shown in FIG. 9, in step S51, under the control of the CPU 13, the counter for counting the links one element E _i and one end of a document is connected Perform initialization. That is, the document processing apparatus sets the count value j of the counter for counting links to “1”. This counter will refer to the first link L _ij connected to element E _i .

Subsequently, the document processing device proceeds to step S52.
, Under the control of the CPU 13, the elements E _i
It is determined whether or not the link L _ij is a normal link by referring to the tag of the relation attribute for the link L _ij connecting the link L _ij and E _j . The document processing device uses the link L _ij
Is a normal link indicating the relationship between the vocabulary element corresponding to the word, the sentence element corresponding to the sentence, the paragraph element corresponding to the paragraph, and the like, and a reference link indicating the dependency relationship by reference / reference. Judge. When the document processing device determines that the link L _ij is a normal link, the document processing device shifts the processing to step S53 and executes the link L _ij
If it is determined that is a reference link, step S5
The processing shifts to step 4.

When the document processing device determines that the link L _ij is a normal link, in step S 53,
An end point T _ij connected to the normal link L _ij of the element E _i
To calculate a new end point activity value.

In step S53, step S52
It is clear from the determination in that the link _Lij is a normal link. The new endpoint activation value t _ij of the endpoint T _ij connected to the normal link L _ij of the element E _i is:
Of the end point activation values of the element E _j, the end point activation values t _jp , t _jq , t _{jr of} all the end points T _jp , T _jq , T _jr connected to the links other than the link L _ij , and the element E _i is the link L _ij
And the central activity value e _j of the element E _j connected by the following _formula, and the value obtained by this addition is divided by the total number of elements included in the document.

Under the control of the CPU 13, the document processing apparatus reads necessary endpoint activation values and central activation values from the RAM 14, for example. The document processing device calculates a new endpoint activity value of the endpoint connected to the normal link as described above for the endpoint activity value and the center activity value that have been read.
Then, the document processing apparatus stores the new endpoint activation value calculated in this way in, for example, the RAM 14.

On the other hand, when the document processing device determines that the link L _ij is not a normal link, in step S54, the end point T connected to the reference link of the element E _i is determined.
A process for calculating the endpoint activity value of _ij is performed.

In step S54, step S52
It is clear from the determination in that the link _Lij is a reference link. Point activation values t _ij endpoint T _ij that is connected to the reference link L _ij of the element E _i, of the end-point activation value of the element E _j, all endpoints T _uk which is connected to the link, excluding the link L _ij, T _jq, point activation value t _uk of t _jr, is obtained by adding t _jq, and t _jr, a central activation value e _j of the element E _j of the element E _i is connected by a link L _ij.

Under the control of the CPU 13, the document processing apparatus reads necessary endpoint activation values and central activation values from, for example, the endpoint activation values and the central activation values stored in the RAM 14. The document processing apparatus calculates a new endpoint activity value connected to the reference link as described above using the read endpoint activity value and the central activity value. Then, the document processing apparatus stores the calculated endpoint activation value in the RAM 1
4 is stored.

The processing of the normal link in step S53 and the processing of the reference link in step S54 go from step S52 to step S55, and are referred to by the count value i as shown in a loop returning to step S52 via step S57. Element E
_This is executed for all the links L _ij connected to _i .
In step S57, the are increments the count value j for counting the links connected to the element E _i.

The document processing apparatus performs these steps S53
Alternatively, after performing the processing of step S54, step S55
, Under the control of the CPU 13, the elements E _i
It is determined whether or not the endpoint activation values have been calculated for all the links connected to. If the document processing apparatus determines that the end point activation values have been calculated for all the links, the process proceeds to step S56, and determines that the end point activation values have not been calculated for all the links. In this case, the process proceeds to step S57.

Here, if the document processing apparatus determines that the end point activation values have been calculated for all the links, in step S 56, the central activation value e of the element E _i is controlled under the control of the CPU 13. Perform _i update.

[0080] new value of central activation value e _i of the element E _i, i.e. updated value is currently a central activation value e _i of the element E _i, the new end-point activation values of all of the end points of the element E _i It is obtained by taking the sum e _i '= e _i + _{ t _j '. Here, the prime “′” means a new value. Thus, the new central activity value is obtained by adding the element's original central activity value to the sum of the new endpoint activity values for the endpoints of the element.

Under the control of the CPU 13, the document processing apparatus reads necessary end point activation values from the end point activation values and the center activation values stored in the RAM 14, for example. The document processing device performs the calculations as described above and its elements E _i
Is calculated. Then, the document processing apparatus stores the calculated new central activation value e _{i in} , for example, the RAM 14.
To memorize.

As described above, the document processing apparatus calculates a new central activation value for each element in the document. Then, the document processing apparatus executes the active diffusion in step S21 in FIG.

Subsequently, in step S22 in FIG. 6, the document processing apparatus, under the control of the CPU 13, sets the window 19 previously displayed on the display unit 30 shown in FIG.
0, that is, the size of the display area 220,
The maximum number of characters that can be displayed is set to W _s to 20. Also,
The document processing device, under the control of the CPU 13,
Is initialized to set an initial value S ₀ = “”. This indicates that there is no character string in the summary sentence. Document processing device, thus set, the initial value S ₀ of the maximum number of characters W _s and summary S can be displayed in the display area 220, is stored in, for example, the RAM 14.

Subsequently, the document processing device proceeds to step S23.
, Under the control of the CPU 13, the count value i of a counter that counts the sequential creation of the skeleton of the summary sentence is set to “1”. That is, the document processing apparatus sets i = 1 for the count value. The document processing apparatus stores the count value i set in this way in, for example, the RAM 14.

Subsequently, the document processing device proceeds to step S24.
Then, under the control of the CPU 13, for the count value i of the counter, the skeleton of the sentence having the i-th highest average central activity value is extracted from the sentence to be summarized. Here, the average central activity value is the average of the central activity values of the elements constituting one sentence. The document processing device reads, for example, the summary sentence S _i-1 stored in the RAM 14, and
Adding strings skeleton of the extracted sentence against the summary S _i-1, and summary S _i. Then, the document processing device:
Such a summary S _i thus obtained, is stored in, for example, the RAM 14. At the same time, the document processing device, creates a list l _i the central activation value order of the elements that are not included in the backbone of the sentence, and stores the list l _i for example the RAM 14.

That is, in step S24, the document processing apparatus selects sentences in descending order of the average central activity value using the result of the activity diffusion under the control of the CPU 13, and selects the skeleton of the selected sentence. Is extracted. The skeleton of the sentence is
It consists of required elements extracted from the sentence. Required elements can be element heads (hea
d) and subject, object, indirect object, owner (posessor), cause (c
an element having a relation attribute of “ause”, “condition” or “comparison”, and an element directly included in the coordination structure when the related element having the coordination structure is an essential element. The document processing apparatus connects the essential elements of the sentence to generate a sentence skeleton,
Add to the summary sentence.

Subsequently, the document processing device proceeds to step S25.
Under the control of the CPU 13, the length of the summary sentence S _i , that is, the number of characters is displayed in the display area 2 of the window 190.
It is determined whether or not more than the maximum number of characters W _s of 20.

Here, when the document processing apparatus determines that the number of characters of the summary sentence S _i is larger than the maximum number of characters W _s ,
In step S30, under the control of the CPU 13,
The summary sentence S _i-1 is set as the final summary sentence, and the series of processing ends. In this case, the summary sentence S _i = S ₀ =
Since “” is output, the summary sentence is not displayed in the display area 220.

On the other hand, if the document processing device determines that the number of characters of the abstract sentence S _i is not larger than the maximum number of characters W _s , the process proceeds to step S 26, and under the control of the CPU 13, i + 1 The average central activity value of the sentence with the second highest average central activity value and the list l _i created in step S24
Is compared with the center activity value of the element having the highest center activity value among the elements. Then, the document processing device sets i
If it is determined that the average central activity value of the sentence having the + 1st average central activity value is higher than the central activity value of the element having the highest central activity value among the elements of the list l _i , the process proceeds to step S27. Transfer processing. On the other hand, the document processing apparatus has determined that the average central activity value of the sentence having the (i + 1) th average central activity value is not higher than the central activity value of the element having the highest central activity value among the elements of the list l _i . In this case, the process proceeds to step S28.

The document processing apparatus determines that the average central activity value of the sentence having the (i + 1) -th highest average central activity value is higher than the central activity value of the element having the highest central activity value among the elements of the list l _i . In this case, in step S27, under the control of the CPU 13, the count value i of the counter is incremented by "1", and in step S24
Return processing to

In the document processing apparatus, the average central activity value of the sentence having the (i + 1) th average central activity value is not higher than the central activity value of the element having the highest central activity value among the elements of the list l _i. If it is determined that the list 1 has been entered under the control of the CPU 13 in step S28.
_The element e having the highest central activity value among the elements _i is added to the summary sentence S _i to generate SS _i , and the element e is deleted from the list l _i . Then, the document processing device converts the summary sentence SS _i thus generated into, for example, R
It is stored in AM14.

Subsequently, the document processing device proceeds to step S29.
In, under the control of the CPU 13, the number of characters in summary SS _i it is determined whether or not more than the maximum number of characters W _s of the display area 220 of the window 190. The document processing device
If the number of characters in summary SS _i is determined to not more than the maximum number of characters W _s repeats the processing from step S26. On the other hand, the document processing device, when the number of characters in summary SS _i is determined to greater than the maximum number of characters W _s, in step S31, under the control of the CPU 13, summary S
_i is set as the final summary sentence, displayed in the display area 220, and the series of processing ends. In this way, the document processing apparatus generates a summary so as not more than the maximum number of characters W _s.

By performing such a series of processing, the document processing apparatus can summarize a tagged document and create a summary sentence. When, for example, the document shown in FIG. 4 is summarized, the document processing apparatus creates a summary sentence as shown in FIG. 10 and displays it in the display area 220 of the display range.

That is, the document processing apparatus states, "The history of TCP / IP cannot be described without ARPANET.
In 1969, ARPANET departed from a small network connecting host computers of four universities and research institutes on the west coast of North America with 50 kbps lines. At that time, a general-purpose computer series of mainframes was developed in 1964. Given this historical background, such a project that anticipated the future of computer communications could be said to have been unique to the United States. Is created and displayed in the display area 220.

In the document processing apparatus, instead of reading the entire text of the document, the user can read the summary to understand the outline of the text and determine whether or not the text is the desired information. can do.

In the document processing apparatus, as a method of assigning importance to elements in a document, it is not always necessary to use active diffusion as described above. For example, the weight of words appearing in a document may be weighted. May be used as the importance of the document. Further, as a method of assigning importance, methods other than these methods can be used. Further, by inputting a keyword into the keyword input section 192 of the display area 200, it is possible to set the importance based on the keyword.

Now, the document processing apparatus can enlarge the display range of the display area 220 of the window 190 displayed on the display unit 31 as shown in FIG. When the display range of the display area 220 is changed in the state where the display is displayed in the area 220, the information amount of the summary sentence can be changed according to the display range.

In this case, under the control of the CPU 13, the document processing apparatus changes the display range of the display area 220 of the window 190 displayed on the display unit 31 in response to the user operating the input unit 20. Wait for the change. When the display range of the display area 220 is changed, the document processing apparatus performs the same processing as the series of processing shown in FIG. Create a summary sentence corresponding to.

In this way, the document processing apparatus can newly create a summary according to the display range of the display area 220. For example, the document processing apparatus displays the display area 2 by dragging the mouse of the input unit 20 by the user.
When the display range 20 is expanded, a more detailed summary is newly created, and a new summary is displayed in the display area 220 of the window 190 as shown in FIG.

That is, the document processing apparatus states, "The history of TCP / IP cannot be described without ARPANET.
Is an experimental and research packet-switched network sponsored by the U.S. Department of Defense DOD's Defense Advanced Research Projects Agency. In 1969, ARPANET departed from a very small network connecting host computers of four universities and research institutes on the west coast of North America with 50 kbps lines. At that time it was the world's first computer in 1945
ENIAC was developed at the University of Pennsylvania, and in 1964 the first mainframe general-purpose computer series that implemented ICs as theoretical elements was developed. Given this historical background, such a project that anticipated the future of computer communications could be said to have been unique to the United States. Is created, and the display area 2
20 is displayed.

As described above, in the document processing device, when the displayed summary is too simple to grasp the outline of the document, the user can increase the display range of the display area 220 to increase the A more detailed summary sentence having the information amount of can be referred to.

Here, when the document processing apparatus prepares the summary sentence of the document in this manner, if the summary sentence includes a pronoun or a restrictive clause in the summary sentence, it performs replacement.
When the subject, object, and the like are omitted, the above-described zero anaphoric processing is performed to supplement the corresponding subject, object, and the like.

First, a specific example of the replacement of the pronoun and the like and the zero anaphor will be described with reference to the following document.

"About work.

I do not like my current job very much.
But you have to do it. An example of tagging this document would look like this:

<Document><title><adjective verb phrase Relation = "object"><nounphrase> job </ noun phrase> and </ adjective verb phrase></title><paragraph><sentence><adjective Verb phrase relation = “subject”><noun phrase identifier = “identifier 1”> I </ noun phrase> is </ adjective verb phrase><adjective verb phrase relation = “object”><noun phrase identifier = “identifier 0” "><Adjective verb phrase> now </ adjective verb phrase>
The job </ noun phrase> is </ adjective verb phrase><verb><adjective verb phrase Relationship = "degree"> not so much </ adjective verb phrase><verb> I don't like </ verb></verb>.</Sentence><sentence>
<Adjective verb phrase> However, </ adjective verb phrase><verb><adjective verb phrase relation = “object”><noun phrase reference = “identifier 0”> that </ noun phrase></ adjective verb phrase><Verb
Subject = "identifier 1"> must do </ verb>
</ Verb>. </ Sentence></paragraph></document>

In this document, the noun phrase “it” has an attribute “reference =“ identifier 0 ”” and is an element containing “identifier =“ identifier 0 ””. Is referred to. That is, the reference element which is the antecedent corresponding to the pronoun "it" which is the referenced element is "current work". Therefore, if the noun phrase "current work" is not included in the summary sentence even though the noun phrase "it" is included, "it" in the summary sentence is replaced with "current work". .

In the above document, the verb “must do” has the attribute “subject =“ identifier 1 ””, so the semantic subject is “identifier =“ identifier 1 ””. It can be seen that this is a noun phrase “I” which is an element having an attribute. That is, the zero anaphoric element of the element "must do" is "I". Therefore, if the semantic subject "I" is not included in the summary sentence even though "I must do" is included, "(I must do)" in the summary sentence And supplement the zero illuminating element.

Such a process of replacing a pronoun or the like and a zero anaphoric process are performed following the above-mentioned summary sentence creation or simultaneously with the creation of the summary sentence. A concrete example of these processing contents is shown in FIG. This will be described with reference to the flowchart of FIG.

That is, FIG. 12 is a flowchart for explaining the processing when a pronoun or a restrictive clause is included in the summary sentence. The processing shown in FIG.
Are performed following steps S30 and S31. This figure 1
In the processing shown in FIG. 2, the referenced list RBList is used to list the referenced elements such as pronouns in the reference / reference relationship in the document, and the i-th element of the summary vocabulary element array is set to t. _i, and the reference element of the vocabulary element t _i is r _i .

At the first step S71 in FIG.
The document processing apparatus empties the referenced list RBList under the control of the CPU 13 in FIG. Next step S72
Then, the document processing apparatus sets the count value i of the counter that counts the summary vocabulary elements in the arrangement order to 1 (i = 1).

At the next step S73, the document processing device
I-th element t of the array of vocabulary elements for summarization
_{For i} , add the referenced element set of the vocabulary element t _{i to} the referenced list RBList. Also, let the reference element of the vocabulary element t _{i be} r _i . The process in this step S73 is to, when another pronoun or the like refers to the element t _i, to refer to another pronoun or the like in the referenced list RB.
In addition to the List, when the element t _i is a pronoun or the like and refers to another element (advance), the referring element (advance) is set as the reference element r _i .

At the next step S74, the document processing device
It determines whether the reference elements r _i of the vocabulary elements t _i is present. The document processing device performs this step S74.
In YES, that there are r _i, when it is determined that the process proceeds to step S75, the if NO, the process proceeds to step S76. That is, according to the determination in step S74, the element t _i is a pronoun or the like and the reference element r _i
Only when exists, the process proceeds to step S75.

In step S75, the document processing apparatus determines whether or not the vocabulary element t _i is an element of the referenced list RBList. If YES, the process advances to step S76.
If NO, the process proceeds to step S77. Step S76
Then, the document processing device adds the vocabulary element t _i to the summary sentence, and proceeds to step S79. In step S77, the document processing apparatus adds the vocabulary columns of reference elements r _i of t _i in summary, the process proceeds to step S78, after the addition of referenced elements set of r _i in the reference list RBList, step Proceed to S79.

The processing in these steps S75 to S78 is such that if the element t _i is a pronoun or the like and refers to another element, the element t _i is an element of the referenced list RBList, If the antecedent is already included in the abstract, the element t _i is added to the abstract as it is without replacing the element t _i with the antecedent.
If There be an element of the referenced list RBList, since the antecedent is not yet included in the summary sentence, but added by replacing the reference element r _i is a antecedent of the element t _i in summary.

In step S79, the document processing apparatus proceeds to step S7 for all the arrangements of the vocabulary elements for summarization.
It is determined whether or not the processing after step 3 has been completed. If NO, the count value i is incremented by 1 (i = i + 1) in step S80, and the process returns to step S73.
If YES, the process ends.

By the above-described replacement processing, if the referenced sentence such as a pronoun or a restrictive clause exists in the abstract sentence but the corresponding reference element as the antecedent is not included in the abstract sentence, with referenced elements t _i of the first occurrence is replaced with the reference element r _i, referenced element set of the reference element r _i is from is added to a referenced list RBList, corresponding to the subsequent same reference elements r _i of the The reference element is added to the summary sentence without being replaced.

Although the specific example of the replacement process shown in FIG. 12 has been described as being performed following the process of creating the summary sentence shown in FIG. 6, it may be performed simultaneously with the creation of the summary sentence. Good.

Next, FIG. 13 is a flow chart for explaining the above-mentioned zero anaphoric processing when there is a sentence containing the omitted subject, object, etc. in the abstract sentence, and is shown in FIG. The processing is performed, for example, in step S3 in FIG.
Subsequent to 0, S31, it is performed before, after, or simultaneously with the processing of FIG. In the process shown in FIG.
The zero anaphor list ZAList is used to list the zero anaphor elements such as the omitted subject and object in the document. The i-th element of the summary vocabulary element array is represented by t _i, and this vocabulary element The zero anaphoric element of t _i is denoted by z _i .

In the first step S81 of FIG.
The document processing apparatus empties the zero analytic list ZAList under the control of the CPU 13 in FIG. Next step S8
In step 2, the document processing apparatus sets a count value i of a counter that counts vocabulary elements for summarization in the order of arrangement to 1 (i = 1).

At the next step S83, the document processing apparatus
Regarding the i-th element in the array of vocabulary elements for summarization, t _i is defined as r _i if a zero-anaphoric element of the vocabulary element t _i exists. In the next step S84,
The document processing device determines whether the zero anaphor element z _i of the vocabulary element t _i exists. This step S
If it is determined at 84 that YES (the zero illuminating element z _i exists), the flow proceeds to step S85, and if NO, the flow proceeds to step S86.

In step S85, the document processing apparatus determines whether or not the vocabulary element t _i is an element of the zero anaphor list ZAList. If YES, proceed to step S86; if NO, proceed to step S87. . Step S8
In 6, the vocabulary element t _i is added to the summary sentence, and the process proceeds to step S89. Document processing device, in step S87, it is determined whether or not the zero anaphoric elements z _i are present already included in the summary sentence, if YES in addition zero anaphora elements z _i in the zero anaphora list ZAList Proceed to step S86, and if NO, proceed to step S89. In the step S89, that is, the document processing device, enclosed vocabulary trailing zeros anaphoric elements z _i vocabulary elements t _i in parentheses, in addition to the summary with vocabulary elements t _i, the process proceeds to step S90, the vocabulary elements t _i and zero after adding and anaphoric elements z _i to zero anaphoric list ZAList, and the process proceeds to step S91. In step S89, S90, the document processing device, if zero anaphoric elements z _i are subject enclosed in parentheses by adding "ga" in its vocabulary column, by adding "wo" in its lexicon string if object And placed before or after the vocabulary element t _i . In the case of Japanese, the zero-anaphoric element is placed before the vocabulary element.

In step S91, the document processing apparatus performs step S8 for all of the arrangements of the vocabulary elements for summarization.
It is determined whether or not the processing after step 3 has been completed. If NO, the count value i is incremented by 1 (i = i + 1) in step S92, and the process returns to step S83.
If YES, the process ends.

By the above-described zero anaphor processing, the corresponding zero anaphor element z _i is not included in the abstract sentence even though there is an element t _i in which the subject and the object are omitted in the abstract. In this case, the element t _i
Is added to the zero anaphor element z _i in parentheses, and the element t _i and the zero anaphor element z are added.
because there is a _i are applied to zero anaphoric list ZAList, for subsequent elements corresponding to the same zero anaphoric elements z _i, will be applied to the intact summary without being added zero anaphoric elements z _i.

When the process of replacing pronouns and the like shown in FIG. 12 and the process of zero anaphoresis shown in FIG. 13 are performed subsequent to the creation of the summary sentence shown in FIG. 6, the number of characters in the summary sentence is reduced. It may change and exceed the maximum number of characters of the above-mentioned summary sentence, that is, the maximum number of characters that can be displayed determined according to the size of the above-mentioned summary sentence display area, or become smaller than the maximum number of characters. Therefore, in order to reduce the number of characters in the summary sentence to the maximum number of characters within the above maximum number of characters, it is necessary to adjust the final number of characters. This is because if the number of characters in the summary exceeds the maximum number of characters in the summary sentence by performing the pronoun replacement process or the zero anaphoresis process, the elements of the summary sentence with lower importance, that is, the element with the lower central activity value sequentially. Delete it so that the number of characters in the summary is within the maximum number of characters. If the number of characters is less than the maximum number of characters, the elements that are not included in the abstract sentence in the original document are added to the abstract sentence in descending order of the element with the highest central activity value. By stopping the addition of the element immediately before exceeding the maximum number of characters, a summary sentence having the number of characters closest to the maximum number of characters and within the maximum number of characters can be obtained.

In the present embodiment, an example of a method for tagging a document has been described, but it is needless to say that the present invention is not limited to this tagging method. Further, in the present embodiment, the document is transmitted from the outside to the communication unit 22 of the document processing apparatus via a telephone line, but the present invention is not limited to this. For example, the present invention can be applied to a case where a document is transmitted via a satellite or the like.
1, the document may be read from the recording medium 32, or the document may be written in the ROM 13 of the document processing apparatus.

In the embodiment of the present invention, it is also easy to provide a disk-shaped recording medium or a tape-shaped recording medium in which the above-mentioned document processing program is written, as the recording medium 32 in FIG. it can. Further, the above-described document processing program can be easily supplied via a transmission medium such as a communication line.

In the above-described embodiment, a mouse is exemplified as a device for selecting a desired element from a document displayed on the display unit 30 of the document processing apparatus.
It goes without saying that the present invention is not limited to this. Other devices such as a tablet and a light pen can be used for inputting elements in the document processing apparatus.

Furthermore, in the above-described embodiment, Japanese sentences have been exemplified. However, the present invention is not limited to Japanese, but English, German, French, Russian, Italian, Spanish, and Chinese. Needless to say, it can be applied to various languages such as Korean.

[0130]

As is clear from the above description, according to the present invention, a summary of a document is created, and the omitted subject or object in the created summary is included in the summary. When not present, by adding the corresponding subject or object in the original document to the summary sentence, the zero-anaphoric element will always appear once in the summary sentence, making it easy and accurate for the user to summarize the content. Sentences can be automatically generated.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a schematic configuration of a document processing apparatus according to an embodiment;

FIG. 2 is a diagram illustrating an example of an internal structure by tagging a document.

FIG. 3 is a diagram showing a window displaying an internal structure by tagging a document.

FIG. 4 is a diagram showing a window displaying a document.

FIG. 5 is a diagram showing a window displaying a document,
FIG. 14 is a diagram showing a state in which a display area for displaying a summary sentence is enlarged from the display area shown in FIG.

FIG. 6 is a flowchart illustrating a series of processes when creating an abstract sentence.

FIG. 7 is a flowchart illustrating a series of processes when performing active diffusion.

FIG. 8 is a diagram showing a connection structure of elements for explaining a process of active diffusion.

FIG. 9 is a flowchart illustrating a series of processing when performing link processing of active spread.

FIG. 10 is a diagram showing a window displaying a document and its summary.

11 is a diagram showing a window displaying a document and a summary sentence thereof, and showing a state in which the summary sentence is displayed in the window shown in FIG. 5. FIG.

FIG. 12 is a flowchart illustrating a replacement process with a reference element when a referenced element is included in a summary sentence.

FIG. 13 is a flowchart illustrating zero anaphoric processing in a summary sentence.

[Explanation of symbols]

10 body of document processing device, 11 control unit, 12
Interface, 13 CPU, 20 input unit,
22 communication unit, 30 display unit, 31 recording / reproducing unit, 32 recording medium, 33 hard disk device

Claims (15)

[Claims] 1. A document processing method for processing a document in the form of an electronic document, comprising: a summary sentence creating step of creating an abstract sentence of the document; and an omitted subject or object in the created summary sentence A zero-anaphora processing step of adding the corresponding subject or object in the original document to the abstract sentence when not included in the sentence. 2. The method according to claim 1, further comprising: setting the size of the summary sentence display area in which the summary sentence of the document is displayed in an entire display area; and setting the display set in the setting step. A determining step of determining the length of the summary sentence of the document based on the size of the area; and the document having a length that fits in the summary sentence display area based on the length of the summary sentence determined in the determining step. And a step of creating a summary sentence.
Document processing method described. 3. The document processing method according to claim 1, wherein the document has an internal structure in which a plurality of elements are hierarchized, and tag information indicating the internal structure is added in advance. 4. The document processing method according to claim 3, wherein in the summary sentence creating step, an active sentence is performed based on the tag information to create an abstract sentence of the document. 5. In the zero anaphor processing step, it is determined whether or not the abbreviated subject or object is included in the abstract sentence. If the abbreviated subject or object is not included, the abbreviated subject or object is bracketed. 2. The document processing method according to claim 1, wherein the document is added to the summary sentence. 6. A document processing apparatus for processing a document in the form of an electronic document, comprising: a summary sentence creating means for creating a summary sentence of the document; and an abbreviated subject or object in the created summary sentence being an abstract. A document processing apparatus comprising: a zero-anaphora processing means for adding a corresponding subject or object in an original document to a summary sentence when not included in the sentence. 7. The summary sentence creating means includes: setting means for variably setting the size of the summary sentence display area in which the summary sentence of the document is displayed in the entire display area; and a display set by the setting means. Determining means for determining the length of the summary sentence of the document based on the size of the area; and the document having a length that fits within the summary sentence display area based on the length of the summary sentence determined by the determining means Means for creating a summary sentence of
Document processing device as described. 8. The document processing apparatus according to claim 6, wherein the document has an internal structure in which a plurality of elements are hierarchized, and tag information indicating the internal structure is added in advance. 9. The document processing apparatus according to claim 8, wherein said abstract sentence creating means creates an abstract sentence of said document by performing active diffusion based on said tag information. 10. The zero anaphor processing means determines whether or not the abbreviated subject or object is included in the summary sentence. If the abbreviated subject or object is not included, the abbreviated subject or object is bracketed. 7. The document processing apparatus according to claim 6, wherein the document is added to the summary sentence. 11. A recording medium on which a computer-controllable document processing program for processing a document in the form of an electronic document is recorded, wherein the document processing program comprises: A zero-anaphora processing step of adding a corresponding subject or object in the original document to the abstract when the omitted subject or object in the generated abstract is not included in the abstract. A recording medium on which a characteristic word processing program is recorded. 12. The summary sentence creating step includes: a setting step of variably setting a size of the summary sentence display area in which the summary sentence of the document is displayed in the entire display area; and a display set in the setting step. A determining step of determining the length of the summary sentence of the document based on the size of the area; and the document having a length that fits in the summary sentence display area based on the length of the summary sentence determined in the determining step. And a step of creating a summary sentence.
A recording medium on which the document processing program according to 1 is recorded. 13. The document processing program according to claim 11, wherein the document has an internal structure in which a plurality of elements are hierarchized, and tag information indicating the internal structure is added in advance. The recorded recording medium. 14. The document processing program according to claim 13, wherein in the abstract sentence creating step, an active sentence is performed based on the tag information to create an abstract sentence of the document. recoding media. 15. In the zero anaphor processing step, it is determined whether or not the omitted subject or object is included in the summary sentence, and if not included, the omitted subject or object is enclosed in parentheses. The recording medium according to claim 11, wherein the document processing program is added to the summary sentence.