JPS63136263A - Mechanical translating device - Google Patents

Abstract

PURPOSE:To quickly recognize a translation process by adding a process mark to a sentence which is under a translation processing. CONSTITUTION:A CPU 1 reads an input text and pushes a full-sentence translation key to start translation of a full sentence. A mark is displayed at a position of a sentence shown on a CRT 3. The displayed mark show the display of inverted sentence number, underline, the color, etc. Then the dictionary consulting and form analyzing jobs are carried out and the combination of the first parts of speech is set for each word containing many parts of speech that is properly selected in response to each word. A train of parts of speed thus set undergoes analysis of syntax structure. If this analysis succeeds, the conversion of language and production of a target language are carried out. Then the result of translation using the translated word of the parts of speech used for analysis of syntax structure is displayed on the CRT 3. Then the mark is erased and the processing is through.

Description

DETAILED DESCRIPTION OF THE INVENTION <Industrial Application Field> The present invention relates to a machine translation device that performs translation in units of sentences, for example.

<Prior art> Conventionally, several sentences (source language) displayed on a screen
- A machine translation device that translates sentence by sentence and displays the translation results (target language) sequentially on the screen. , it was not possible to recognize which sentences were being translated.

Especially when you translate a full text once, register it in the user dictionary, and then translate the whole text again, the translated text is displayed at the same time, so you can clearly see which sentences have been processed after being registered in the user dictionary. I couldn't do it.

<Object of the invention> The present invention has been made in view of such conventional problems.
It is an object of the present invention to provide a machine translation device in which it is possible to recognize that the translation process is in progress by attaching a mark indicating that the translation process is in progress to the sentence being translated.

<Example> The present invention will be explained in detail below based on the drawings.

FIG. 1 is a block diagram showing the configuration of a machine translation device according to the present invention. In connection with the central processing unit (CPU) 1 that performs processing such as translation processing, there is a main memory 2 in which programs, etc. for processing by the CPU 1 are stored, and a display device (CRT) for displaying necessary displays for the translation processing. )
3. Keyboard 4 for inputting information necessary for translation processing
, a translation module/in which information necessary for the translation process is stored.
L15, a dictionary for translation, grammar rules, and a structure conversion rule table 6 are provided.

FIG. 2 shows an embodiment of the translation module 5.

Translation module/L15 has five buffers A and B.

Includes C, D, E, CPU and translation program memory. These buffers A to H store data at each analysis level in the translation process, as will be described later.

Here, general machine translation processing will be explained.

Machine translation generally has levels as shown in Figure 3.

When the source language is input from the top left, ■ dictionary lookup, ■
Morphological analysis of , syntactic analysis and parsing of ■ proceed. Machine translation can be broadly divided into two types depending on the level of analysis. One is the pivot method, which analyzes concepts that do not depend on each language (called an intermediate language) and generates a target language from there. The other method is called the transfer one-way method, in which the internal structure of the source language is obtained by analyzing any of the following: morphological analysis of ■, syntactic analysis of ■, semantic analysis of ■, and context analysis of ■. After converting to the same level structure of the target language, the target language is generated. Here, the contents of each analysis are listed in Table 1.

In the translation module shown in Table 1, it is assumed that at least the level of parsing (■) is performed. That is, as shown in FIG.
It consists of four parts.

FIG. 5 shows the contents of each buffer in FIG.
a pen.

This example shows how to translate an English sentence into Japanese. First, the original text is read into the buffer A of FIG. 2 as shown in FIG. 5 fa). Dictionary lookup morphological analysis unit 51 in FIG.
The necessary information for each word is extracted and placed in buffer B in FIG. The part-of-speech information that is part of it is shown in Figure 5 (bl).

This is a multi-part speech word, which is uniquely determined by the parsing unit 52 shown in FIG. At this time, an analysis as shown in Table 2 is performed based on the grammar regulations of tape/L/6 shown in FIG.

This rule in Table 2 indicates, for example, that a par sentence is made up of a subject and a predicate.In the language conversion unit 53 in FIG. The results are stored in the buffer D in FIG. 2 as shown in FIG. 5 (dl). In the target language generation unit 54 in FIG. This is put into the buffer E in FIG. 2 as shown in FIG. 5 (el). This becomes the output of the translation module 5.

FIG. 8 is a flow chart of the present invention. First, read the input original text using Nuteg n1. Here, we have considered the case where the input original text exists as a file, but in this step it may be input from the keyboard, or the input original text may be prepared using OCR or the like. Next, in step n2, the whole text translation key is pressed to start translating the whole text. Although batch translation (full text translation) is assumed here, interactive one-sentence translation may also be used. In step n3, a mark is displayed on the CRT at the position of the sentence to be processed. Figures 6 and 7 are display examples of mark 7, especially the 6th mark.
Mark the sentence numbers in the diagram? It is displayed after converting to IC.

Marks include highlighted text numbers, underlines,
Color display etc. can be considered.

Dictionary lookup and morphological analysis are then performed, and the first combination of parts of speech of each multipart speech word appropriately selected corresponding to each word is set (n-4,). The part-of-speech sequence set in this way is parsed in step n5. If the parsing is successful, the process proceeds to step n6 for language conversion and step n7 to generate the target language, and in step n8, the translation result using the translated word of the part of speech used in the parsing is translated into C.
Display on RT. Then, in step n9, the mark is erased, and in step nlo, if there is the next sentence, the process returns to step n3, and if not, the process ends. Note that in the case of - sentence translation, step nlo is not necessary.

Effect> As explained in detail above, the machine translation device of the present invention displays a mark indicating that the translation process is in progress for the source language that is currently being translated among the plurality of source languages displayed on the screen. Therefore, it is possible to directly recognize which sentence is being translated by Vc, and it is also possible to confirm that the device is in translation processing. Furthermore, the processing waiting time can be recognized by moving the mark.

[Brief explanation of the drawing]

Figure 1 is a block diagram of the device of the present invention, Figure 2 is a schematic diagram of the translation module and table, Figure 3 is a diagram explaining translation levels, and Figure 4 is a diagram showing a specific example of the configuration of the translation module. , FIGS. 5A to 5E are diagrams showing configuration examples of each buffer in FIG. 2, FIGS. 6 and 7 are diagrams showing display examples, and FIG. 8 is a flowchart. 1 is a CPU. , 2 is the main memory, 3 is the CRT. 4 is the keyboard, and 5 is the translation module. Agent: Patent Attorney Takeshi Sugiyama (and 1 other person) Figure 2 Figure 3 Figure 4 Figure 5 (Q) Figure 5 Figure (b) - Buff completion C - Unexpectedly repeated bar Y7 completion Ya Fig. 5 (Su ° bar / 7th - Thursday) J @ Shioka (1 stem 1 rough 1 sentence) Figure 5 (α) Figure 5 (e) Figure 6 Figure 7

Claims (1)

[Claims] 1. In a machine translation device that translates a source language displayed on a screen into a target language and displays the target language on the screen, one of the plurality of source languages displayed on the screen is translated into a target language. A machine translation device comprising means for displaying a mark indicating that a source language is being processed.