JPH01113870A - Mechanical translating device - Google Patents

Abstract

PURPOSE:To ensure the accurate and high-speed interpretation of an original sentence even in case grammatical regulation does not cope with a specific syntax structure or a long sentence having complicated active-passive relation by translating a dividing translation part designated by a dividing translation part mark after separating said translation part from other parts. CONSTITUTION:When the analysis of a syntax structure is carried out, a grammatical rule deciding means decides whether the taken-in grammatical rule for analysis of syntax structures is equal to a dividing translation rule or not. If not, the grammatical rule is available. If so, the dividing translation rule is available only when a dividing translation part mark deciding means decided that a dividing translation part mark is included in a word string. Thus the dividing translation rule is applied for analysis of syntax structures only when a dividing translation part is designated in the input word string by the dividing translation part mark. Then the dividing translation part is translated after separation from other parts. Thus it is possible to interpret an original sentence in a correct and quick way.

Description

DETAILED DESCRIPTION OF THE INVENTION <Industrial Application Field> The present invention relates to a machine translation device that can classify and translate arbitrary syntax of an input sentence.

<Prior Art> Conventionally, there are the following machine translation devices. This machine translation device inputs the Norse language input from the keyboard into the translation module under the control of the main CPU, and the translation module transfers the input source language to the dictionary, grammar rules, and book structure stored in the memory. It uses conversion rules to translate into the target language. The above grammar rules are used to determine the syntactic structure of an input sentence (hereinafter referred to as the original sentence).

<Problem to be solved by the invention> However, when translating with the above-mentioned conventional machine translation device, the syntactic structure of the original sentence is determined according to the grammatical rules stored in the memory. If the memorized grammar rules do not correspond to specific structures in the original text, there is a problem that the original text may be misinterpreted or cannot be translated. Furthermore, even if the above-mentioned grammar rules correspond to specific syntax in the original text, there is a problem that it is easy to misinterpret the original text if the dependency is very complicated. Furthermore, when a long sentence with complex dependencies is input, there is a problem that the processing time increases in proportion to the length of the sentence. .

Therefore, an object of the present invention is to attach a divided translation department mark to an arbitrary syntax in the original text, so that only the syntax in that part can be divided and translated, so that the grammar rules can be adjusted to a specific syntax. To provide a machine translation device capable of correctly and quickly interpreting an original text even if the original text is not supported or has complex dependencies.

Means for Solving the Problems In order to achieve the above object, the present invention comprises a morphological analysis unit that divides an input sentence into morphemes using a dictionary and obtains information such as parts of speech, and the morphological analysis unit. a syntactic analysis unit that analyzes the syntax of the morpheme sequence divided by using a dictionary and grammar rules, a conversion unit that exchanges the syntactic structure obtained by the syntactic analysis unit into a syntactic structure in the target language, and the conversion unit In a machine translation device having a translated sentence generation unit that generates a translated sentence according to the syntactic structure of the target language obtained by the unit,
A mark input means for inputting a divided translation unit mark for specifying a divided translation unit that divides and translates arbitrary syntax of a sentence that can be inputted, and whether or not the divided translation unit mark is present in the input word string. mark discriminating means for determining whether the above-mentioned grammatical rules for syntax analysis that have been imported are rules for split translation, and if they are not rules for split translation, the above-mentioned grammatical rules that have been imported can be used. On the other hand, when the rule is for split translation, grammar rule discriminating means makes it possible to use the split translation rule only when the mark discriminating means determines that there is a split translation part mark in the word string. It is characterized by having the following.

Effect> A divided translation part mark is inputted from the mark input means to an arbitrary syntax of an input sentence to specify that this sentence is a divided translation part that is to be translated separately.

When a sentence to which the divided translation part mark has been given is input to the divided translation part mark determination means, it determines whether there is a divided translation part mark for specifying the divided translation part in the word string of the inputted sentence. is discriminated by the mark discrimination means of the divided translation section, and then divided into morphemes by the morpheme analysis section to obtain information such as part of speech, and based on this information and grammar rules, the syntactic analysis section parses the morpheme sequence. It is done. and,
The syntactic structure obtained by the syntactic analysis section is converted into the syntactic structure of the target language by the conversion section, and the translated sentence generation section generates a translated sentence according to the syntactic structure of the target language.

In such a translation process, when executing the syntactic analysis, the grammar rule determining means determines whether the imported grammar rule for syntactic analysis is a rule for split translation. As a result, when the rules are not for split translation, the imported grammar rules can be used, but when the rules are for split translation, the split translation part mark discriminating means detects that there is a split translation part mark in the word string. The above divisional translation rule can be used only when it is determined. Therefore, only when a divided translation part in the input word string is specified by the divided translation part mark, the rules for divided translation are used to perform syntax analysis, and the divided translation part is translated with distinction from other parts. be done.

<Example> Hereinafter, the present invention will be explained in detail with reference to illustrated embodiments.

FIG. 1 is a block diagram of an embodiment of a machine translation apparatus according to the present invention. 1 is the main CPU (central processing unit),
2 is a main memory, 3 is a CRT (cathode ray tube), 4 is a keyboard, 5 is a translation module, and 6 is a memory that stores a dictionary for translation, 9 grammar rules, tree structure conversion rules, etc.

When the source language is input, the translation module 5
It translates it and outputs the target language.

That is, the source language input from the keyboard 4 is sent to the translation module 5 under the control of the main CPU 1. The translation module 5 uses the dictionary 2 grammar rules, tree structure conversion rules, etc. stored in the memory 6 to translate the input source language into the target language as will be detailed later. The results are temporarily stored in the main memory 2 and displayed on the CRT 3.

FIG. 2 shows a specific configuration of the translation module 5 of this embodiment.

The operation of the translation module will be explained below using FIGS. 1 and 2.

First, the read original text is divided into each morpheme string (word string) by the dictionary reference morphological analysis unit 11 using the dictionary in the memory 6, and grammatical information such as part of speech and translation for each word are obtained. Tense, person, number, etc. are analyzed. In the syntactic analysis unit 12, in accordance with the dictionary in the memory 6 and the grammatical rules, the dependencies between each word are determined as shown in FIG. 5 by creating a structural analysis tree indicating the relationship as will be described later.

The conversion unit 13 uses the tree structure conversion rules in the memory 6 to convert the structure of the parse tree for the input original text into the structure of the parse tree for the translated text. Then, the translated sentence generation unit 14 adds particles and auxiliary verbs appropriate for the translated sentence in the target language, and the obtained translated sentence is output from the translation module 5, stored in the main memory 2, and displayed on the CRT 3. .

Next, in the operation of the above-mentioned translation module, a divided translation process in which arbitrary syntax of an input sentence is translated separately from others will be explained in detail. Here, it is assumed that the memory 6 stores only the grammar rules shown in Table 1.

Table 1 The grammar rules in Table 1 above represent the following:

That is, grammar rule (a) indicates that a prepositional phrase is made up of a preposition and a noun phrase. Grammar rule (b) indicates that a noun phrase is made up of a determiner and a noun. Grammar rule (C) indicates that the verb phrase is made up of BE auxiliary adjectives. Grammar rule (d) indicates that a declarative sentence is made up of a noun phrase and a verb phrase. Grammar rule (e) indicates that a THAT clause is made up of THAT and a declarative sentence. Grammar rule (D means that a sentence is made up of a declarative sentence and a sentence ending. Grammar rule (g) means that a sentence is made up of a subtree and a sentence ending. Grammar rule (h) means that a sentence is made up of a subtree and a sentence ending. indicates that a subtree is made up of a subtree, a double slash, and a subtree. Grammar rule (i) indicates that a subtree is made up of a prepositional phrase. Grammar rule (j) indicates that a subtree is made up of a THAT clause. It means that it is made up of. Grammar rules (
lr) indicates that the subtree is made up of BE auxiliary verbs. Among the grammar rules (a) to (k) above, grammar rule (g)
) to (k) are rules for divided translation used in the divided translation process.

FIG. 3 is a flowchart of translation processing according to this embodiment. The operation of translation processing will be explained below with reference to FIG.

In step S, a divided translation flag indicating execution of divided translation processing is reset.

In step S, it is determined whether or not the input word string contains a double sura sosh "//" which is a divided translation part mark that designates a divided translation part. As a result, if "//" is found, the process proceeds to step S3; otherwise, the process proceeds to step S3.
Skip.

In step S, a split translation flag is turned on to indicate execution of the split translation process.

In step S4, dictionary lookup processing is executed by the dictionary lookup morphological analysis unit 11 to obtain grammatical information such as parts of speech and translations, and further analysis of tense, person, number, etc. is performed.

In step S, the syntax analysis unit 12 performs syntax analysis and determines the structure of the syntax analysis tree.

In step S, the conversion unit 13 converts the structure of the parse tree of the source language into the structure of the parse tree of the target language.

In step S, the translated text generation unit 14 generates an appropriate translated text.

Next, the syntax analysis process in step S will be described in more detail with reference to the flowchart of FIG.

In step S5+, the next grammar rule is imported from among the grammar rules shown in Table 1.

In step 511m, it is determined whether the imported grammar rule is a rule for split translation. As a result, if the rule is for split translation, the process proceeds to step S54, and if not, the process proceeds to step S53.

In step SS3, syntax analysis is performed using the imported grammar rules, and the process proceeds to step S56.

In step S54, it is determined whether the divided translation flag is on. As a result, if it is on, step S
Go to step ss, otherwise go to step 5i11.

At step SO8, syntax analysis is performed using the imported grammar rules (ie, rules for segmented translation).

In step 5Ila, it is determined whether or not there is a word string that has not been parsed in the input word string. As a result, if there is an unprocessed word string, the process returns to step SS+, and if not, the syntax analysis process ends.

The above translation processing operation will be further explained using a specific input sentence. First, input sentence (a) rAmong those a
van-tages is that the in
Assume that the string is effective, J is input. This input sentence (a) has an inverted syntax, and the normal word order is rThat theinst
rument is efficient is
among thoseadvantages,
It is J.

When the input sentence (a) is input, in the flowchart of FIG. 3, since there is no "//" in the input word string, the process goes through steps S, , S, , S, and reaches step S. 4
Analysis processing is executed according to the flowchart in the figure. However, as shown in Table 1, the grammar rules of this embodiment lack a grammar rule that can handle inverted syntax, so that syntactic analysis fails in normal translation processing.

Then, from the keyboard 4, enter the input sentence (b) by inserting a double slash into the above input sentence (a) r A mongt
hose advantages // is //
that the instrument is e
fTicient, J is input. Then, the third
In the flowchart shown in the figure, “//” appears in the input word string.
, so step S, via step S, ,S,
Turn on the split translation flag with . The process then proceeds to step S via step S4, and the syntax analysis process is executed as follows according to the flowchart of FIG.

That is, assume that the grammar rule (g) in Table 1 is first imported. This grammar rule (g) is a rule for split translation as described above, and the split translation flag has already been turned on in step S3 of FIG.

Therefore, using the grammar rule (g) in step SSS via steps Ss+, Sst, and Ss*, the input sentence (b) is classified into the end of a partial Mizuko sentence, as shown in the upper column of FIG. Next, assume that the grammar rule (h) in Table 1 is imported.

As described above, this grammar rule (h) is a rule for divided translation stations, and the divided translation flag is already turned on as described above. Therefore, step Ss++Ssz+95+
Step S via. Using grammar rule (h), the fifth
As shown in the second row of the figure, the above subtree is further divided into partial water-child double slash ten subtrees. Thereafter, the input sentence (b) is parsed in the same manner, and if the parsing is successful, a parsing tree of the source language is determined as shown in FIG. Thereafter, based on this parse tree, the split translation part between "//" and //" is separated from the others and the conversion process and generation process are executed. As a result, as shown in FIG. The divided translation part between "//" and "//" in the original text is separated from others and translated, and the output sentence "Between those advantages // is // that the equipment is highly efficient."" is output to the CRT3.

In this way, even long sentences with complex dependencies can be divided into blocks using "//" and translated for each block, and special grammar rules are also provided for special constructions such as inverted structures. There is no need to keep the grammar rules in perspective (
Become. Therefore, it becomes possible to interpret the original text correctly and at high speed.

Furthermore, since it is possible to analyze even special syntax, it is possible to identify the part of speech of an input word string, making it easy to change translations of words.

<Effects of the Invention> As is clear from the above, the present invention has a morphological analysis section,
A mark input means for inputting a divided translation unit mark into a machine translation device including a syntactic analysis unit, a conversion unit, and a translated sentence generation unit, and a mark for determining whether or not the divided translation unit mark is present in an input word string. A determining means determines whether or not the imported grammar rules for syntactic analysis are rules for split translation, and performs syntactic analysis using the rules for split translation only when there is a split translation mark in the input word string. We have provided a means for determining grammar rules that makes it possible to separate the divided translation part specified by the divided translation part mark from others and make it possible to translate it. , even when a long sentence with complex dependencies is input, the original text can be interpreted correctly and at high speed.

[Brief explanation of the drawing]

Fig. 1 is a block diagram of an embodiment of the machine translation device of the present invention, Fig. 2 is a functional block diagram of the translation module in the above embodiment, Fig. 3 is a flowchart of translation processing according to the above embodiment, and Fig. 4 is Syntax analysis process flowchart, 5th
The figure shows an example of a determined parse tree, and FIG. 6 is a diagram showing an example of an input sentence to the machine translation device of FIG. 1 and an example of an output sentence (translated sentence) therefor. l...Main CPU, 2...Main memory, 3.
... CRT, 4... Keyboard, 5... Translation module, 6... Memory, 11... Dictionary lookup morphological analysis section, 12... Syntax analysis section, 13... Conversion section, 14
...Translation generation unit. Patent applicant: Sharp Corporation Agent
Patent attorney Aoyama Aoyama and 2 others Figure 3 Figure 4 Figure 6

Claims (1)

[Claims] (1) A morphological analysis unit that divides the input sentence into morphemes using a dictionary to obtain information such as parts of speech, and analyzes the syntax of the morpheme string divided by the morphological analysis unit using a dictionary and grammar rules. a syntactic analysis unit, a conversion unit that exchanges the syntactic structure obtained by the syntactic analysis unit into a syntactic structure in the target language, and a translated sentence that generates a translated sentence according to the syntactic structure of the target language obtained by the conversion unit. In a machine translation device having a generation unit, a mark input means for inputting a division translation unit mark for specifying a division translation unit that divides and translates arbitrary syntax of an input sentence, and a mark input means for inputting a division translation unit mark; a mark discriminating means for determining whether or not the above-mentioned divided translation part mark is present in the above-mentioned divided translation part mark; While it is possible to use the imported grammar rules, when the rules are for split translation, the above rules for split translation are used only when the mark discriminating means determines that there is a split translation part mark in the word string. A machine translation device characterized in that it is equipped with a grammar rule discriminating means that enables use of the machine translation device.