JPS59127140A - Automatic error detecting and correcting device of sentence - Google Patents

Abstract

PURPOSE:To detect and correct automatically the wrong words, omitted words and inadequate words by using a dictionary storing faulty character trains having possibility for use in a sentence. CONSTITUTION:A sentence to be checked is read out of a sentence memory 13 and sent to a faulty character train detecting part 16 and a character display control part 5. A character train reading dictionary 18 stores the character trains having possibility to be used in a sentence together with the information on the connecting relations and the correcting method of sentence errors. A dictionary reading part 17 reads the desired information out of the dictionary 18 and then collated with the sentence to be checked through a faulty character train detecting part 16. When an error is detected, this error is displayed at a display device 2 via a character control part 5 together with the correcting method. Thus an operator can perform desired correction.

Description

[Detailed Description of the Invention] Technical Field of the Invention The present invention relates to 100-word processing used in printing, publishing, etc., and relates to a device that automatically detects and corrects errors such as typos and omissions in sentences. The present invention particularly relates to a device for detecting errors in languages such as Japanese where word boundaries are ambiguous.

(B) Technical background Many parts of printing, publishing, and other operations have been mechanized and automated. However, since humans are the ones who think about sentences, it is inevitable that errors will occur during the process of inputting the sentences into a machine. This may be a typographical error caused by the writer's misunderstanding, or a typographical error or omission during input. In addition, when publishing newspapers, etc., there are some that limit the range of terms used, apart from social common sense.
At present, it is essential for humans to inspect and proofread texts entered into machines. This manual inspection and calibration requires a great deal of effort and time. In addition, manual proofreading is prone to errors and oversights, and in some cases, double or double proofreading.
Requires triple checking and proofreading.

The present invention is capable of automatically detecting typographical errors, etc., which was previously impossible for languages such as Japanese where word boundaries are unclear.
By using the present invention, a great deal of labor and time can be saved, and moreover, more complete inspection and calibration can be performed.

(C) Prior art and problems Conventionally, in English, etc., there is a device that detects words that are not in the dictionary (possibly incorrect) by matching the spelling of the Chinese language used in Japanese literature with words in the dictionary. However, in languages such as Japanese, where the tax world is unclear, it is impossible to use the above method.

This device is capable of combining character string units (hereinafter referred to as words).
By determining whether it matches the text,
This makes it possible to automatically check and correct languages such as Japanese, where word boundaries are unclear.

■) Purpose of the Invention Accordingly, the purpose of the present invention is to eliminate typographical errors that were conventionally done manually in text processing such as printing and publishing.

The purpose of this invention is to provide a device that automatically detects and corrects abnormalities such as misspellings and inappropriate terms, and is particularly effective in processing languages with ambiguous word boundaries such as Japanese.

(G) Structure of the Invention In order to achieve this object, the text abnormality inspection and correction device of the present invention stores in advance character sequences such as typographical errors or incorrectly inputted words in a manuscript and their correction methods, and stores them in advance. It stores multiple correction methods for one abnormal character string and automatically detects and corrects it by comparing it with the text.
It is characterized by having the operator make a decision.

■ Embodiment of the Invention The figure shows one embodiment of the present invention. In the figure, 1 is an audio output device such as a speaker or headphone, 2 is a character display device such as a Japanese display, and 3 is a key board with kanji characters, etc. 4 is a voice synthesis device, 5 is a character display control unit, 6 is a system control unit that controls the entire system,
7 is a corrected character string input section, 8 is an arbitrary word speech parameter synthesis section, 9 is an arbitrary word speech parameter dictionary, 10 is an automatic correction string determination section, 11 is a character string correction section, 12 is a text reading section 4- , 13 is a text storage unit, 14 is a reading analysis unit, 15
16 is a text analysis result storage unit, 16 is an abnormal character string detection unit, and 17 is a sentence analysis result storage unit.
is a dictionary entry section, and 18 is a character string and reading dictionary.

Next, the operation of this embodiment will be explained.

First, the text to be tested is read out from the text storage device 13 by the text reading section 12 and sent to the abnormal character string detection section 16 and the character display control section 5. The text storage device 13 is a magnetic disk or a semiconductor storage device, etc., and contains text (character code string) and text numbers 9 pages and numbers 1 necessary for managing the texts.
Memorizes line numbers, etc.

The text reading section 12 sequentially reads out the text to be inspected from the character input device 13 in units of sentences or small units separated by 6 pins such as periods, commas, parentheses, etc., and sends them to the abnormal character string detection section 16 and character display control. Send to Section 5.

The text input to the abnormal character string detection section is compared with the character string read out from the dictionary extraction section 17 and the reading dictionary 18 .

The character string and reading dictionary 18 contains character strings that may appear in sentences (Tsubogo,
Compound words), their connection relationship information (distinguishing between allowed and disallowed combinations in a sentence pattern), character strings that are likely to appear in a sentence (incorrect words), and how to correct them (correct word characters) (columns, etc.) and audio information (reading, word accent type) for use in reading aloud.

The dictionary extraction section 17 is equipped with an address table, etc., for quickly reading out necessary information from the character string and reading dictionary 18, and reads out character strings and readings from the text according to instructions from the abnormal character string detection section 16 or the reading analysis section 14. Information regarding matching character strings in the dictionary is read out from the dictionary 18 and sent to the abnormal character string detection section 16, reading analysis section 14, or automatic correction character string determination section 10.

The abnormal character detection unit 16 determines whether the combination of the character string of the test target sentence read out from the text storage device 13 and the character string read out from the dictionary by the dictionary extraction unit 17 matches, and whether the combination is allowed. , and whether a character string matching the erroneous word exists in the text to be inspected, and sends the results to the automatically corrected character string determination section 10 and character display control section 5 .

To check whether the above combinations match, first extract all character strings in the dictionary that match a partial character string in the sentence, and then check whether the combination matches the sentence exactly. A method for determining whether a combination exists or not can be applied, and any method can be easily realized by a person skilled in the art. In addition, to check whether the above combination is allowed, store the forward connection characteristics and backward connection characteristics for each character string in the dictionary, and check the backward connection characteristics and forward connection characteristics that are still allowed. A method of storing combinations separately and determining whether the backward connection characteristics of the preceding character string and the forward connection characteristics of the following character string are allowed at the boundary of each character string, etc. is applicable.

In addition, the abnormal character string detection unit 16 stores the sentence analysis results (information such as how to combine dictionary character strings that match the sentence) that cannot be used in the reading analysis unit 14 in the sentence analysis result storage unit, if necessary. 5 and memorize it.

As a result of the above determination, the abnormal character string detection unit 16 detects the entire sentence whose combination does not match or the partial character string in the sentence which cannot be expressed by the combination as an abnormality of the sentence, and controls the character display control unit. Send on 5th.

The automatic correction character string determination section instructs the character display control section 5 on the correction method, if necessary, based on the incorrect word input from the abnormal character string detection section 16 and the correction method input from the dictionary output section 17. Confirm it with the operator by sending it and displaying it on the character display device 2.

A selection is requested, a corrected character string is determined, and the corrected character string is sent to the character string correction unit 11. Examples of words that are easily entered incorrectly, words that are likely to be incorrectly written, and words that can be corrected in multiple ways are as follows 8- Example O error Submit words that are easy to input → Sweeping Shock → Liao Bound Q Words that are easy to miswrite , the information input from the automatically corrected character string determination unit is displayed, and the operator is asked to select confirmation 1 and input a corrected character string. It also displays the character string input from the modified character string input section 7.

Claims (1)

[Claims] (1) In a device that automatically inspects sentences for abnormalities, abnormal character sequences that may be used in sentences are stored in advance, and abnormal character sequences that may be used in sentences are stored in advance. An apparatus for automatically correcting abnormal lateral distortion of a text, characterized in that it compares an abnormal character sequence with an abnormal character sequence and detects when a character sequence identical to a pre-stored abnormal character sequence appears in the sentence. (2. In an apparatus for automatic abnormality inspection and correction of sentences as described in claim 1, abnormal character sequences and their correction methods are stored in advance, and the abnormal character sequences and the abnormal character sequences stored in advance are If the same character sequence as the abnormal character sequence memorized in advance appears in the sentence,
An automatic abnormality correction device for sentences, characterized in that this is automatically corrected according to a pre-stored correction method for the character series. (3) In the abnormality inspection and correction device for sentences set forth in claim 1 or 2, the detected abnormal character string or the detected abnormal character string and its automatic correction results are automatically detected. A device characterized by having means for displaying or printing. (4) The apparatus for inspecting and correcting text abnormalities as set forth in claim 2 is characterized by having a function of automatically returning the correction result to the character string before correction when there is an external request. A device that does this. (5) Percentage Allowance In the abnormality inspection and correction device for sentences as set forth in claim 2, a plurality of correction methods are stored in advance for each abnormal character sequence, and the plurality of correction methods are simultaneously executed. A device characterized by having a display function and allowing a correction method to be selected from the outside.