JP3972698B2 - Natural language processing system, natural language processing method, and computer program - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a natural language processing system, a natural language processing method, and a computer program for mathematically handling a natural language used by humans for daily communication, and in particular, syntactic and semantic analysis of Japanese syntax. The present invention relates to a natural language processing system, a natural language processing method, and a computer program.
[0002]
More specifically, the present invention relates to a natural language processing system, a natural language processing method, and a computer program for performing syntactic and semantic analysis processing of a Japanese sentence including a verb whose valence changes between a use sentence and a passive sentence, and in particular, a computer program. The present invention relates to a natural language processing system, a natural language processing method, and a computer program that accurately and syntactically analyze a Japanese sentence including a verb whose valence changes between a use sentence and a passive sentence without increasing costs.
[0003]
[Prior art]
Words that humans use for everyday communication, such as Japanese and English, are called “natural languages”. Many natural languages have a naturally occurring origin and have evolved with the history of mankind, people and society. Of course, people can communicate with each other by gestures and hand gestures, but natural language can realize the most natural and advanced communication.
[0004]
On the other hand, with the development of information technology, computers have become established in human society and have deeply penetrated into various industries and daily life. Now, not only computer data, but almost all information content such as images and sounds are handled on the computer, making it possible to perform advanced processing such as editing / processing, storage, management, transmission and sharing of information. .
[0005]
Natural language is inherently abstract and has a high nature of nature, but it can perform computer processing by handling sentences mathematically. As a result, various applications / services related to natural language are realized by automated processing such as machine translation, dialogue system, and search system.
[0006]
Natural language processing is generally divided into processing phases of morphological analysis, syntax analysis, semantic analysis, and context analysis.
[0007]
In morphological analysis, a sentence is segmented into morpheme, which is a semantic minimum unit, and part-of-speech recognition processing is performed. In syntax analysis, sentence structure such as phrase structure is analyzed based on grammatical rules. Since the grammatical rule is a tree structure, the parsing result generally has a tree structure in which individual morphemes are joined based on a dependency relationship. In semantic analysis, a semantic structure that expresses the meaning conveyed by a sentence is obtained based on the meaning (concept) of the words in the sentence and the semantic relationship between words, and the semantic structure is synthesized. In context analysis, a sentence (discourse) that is a sequence of sentences is regarded as a basic unit of analysis, and a discourse structure is constructed by obtaining a semantic group between sentences.
[0008]
Syntactic semantic analysis uses a valence dictionary that describes the relationship between verbs and other components in the sentence, such as the subject, for the structure sentence after the dependency relationship is obtained by syntactic analysis, etc. Extracting the semantic relationship of the words related to it.
[0009]
[Problems to be solved by the invention]
There are two types of sentences: a servant sentence that expresses something that causes others to do something, and a passive sentence that expresses what others are working on.
[0010]
In Japanese sentences and passive sentences, the valence of the verb changes. For example, in the sentence “Student writes a composition”, the subject, that is, “the person who writes the composition” is a “student” standing in the gait. On the other hand, in the sentence “The teacher made the student write the composition”, “the person who wrote the composition” is the “student” standing in the second case.
[0011]
Therefore, in order to perform accurate semantic analysis processing, it is necessary to accurately handle such a phenomenon of valence change.
[0012]
Conventionally, in order to analyze the above example sentence, such a problem has been solved by preparing a plurality of items such as the underlined portion below in a valence dictionary.
[0013]
(A) [Subject] writes [Object].
(B) [Subject] causes [Operator] to write [Object].
[0014]
However, in such a method, it is necessary to describe in the dictionary the valences for all expressions that form a service sentence such as “I want you to write” and “I want you to write”, which is very expensive.
[0015]
The present invention takes into account the technical problems as described above, and its purpose is to accurately synchronize a Japanese sentence containing a verb whose valence is changed between a working sentence and a passive sentence without increasing costs. An object of the present invention is to provide an excellent natural language processing system, natural language processing method, and computer program that can perform semantic analysis.
[0016]
It is a further object of the present invention to accurately syntactically mean a Japanese sentence containing a verb whose valence changes between the active sentence and passive sentence without describing the valence for all expressions forming the active sentence in the dictionary. An object of the present invention is to provide an excellent natural language processing system, natural language processing method, and computer program that can be analyzed.
[0017]
[Means and Actions for Solving the Problems]
The present invention has been made in consideration of the above-mentioned problems. The first aspect of the present invention is described with reference to a valence dictionary that describes the relationship between verbs and other components in the sentence such as the subject and object. A natural language processing system or a natural language processing method for extracting a semantic relationship between a part and a word related thereto,
A valence dictionary management means or step for giving a valence to an auxiliary verb or an auxiliary verb that is an expression that bears a duty or passive;
A link forming means or step for forming a link between case elements by referring to a valence dictionary for a service sentence or a passive sentence;
A natural language processing system or a natural language processing method.
[0018]
Here, the link forming means or step links the subject of the verb in the working sentence or passive sentence with the essential case of the working role or passive. As a result, the subject of the verb that is NULL can be expressed using the valence of the original verb.
[0019]
Therefore, according to the natural language processing system or the natural language processing method according to the present invention, auxiliary verbs such as “sore”, “re”, “get”, and “get” are expressions that are responsible for use / passiveness. By attaching a link between case elements, the valence of the original verb can be used as it is.
[0020]
As a result, it is not necessary to describe the valence for all the expressions that form the usage sentence in the dictionary, and the cost of dictionary description can be significantly reduced.
[0021]
In addition, the second aspect of the present invention is a natural method for extracting a semantic relationship between a predicate and a word related thereto by referring to a valence dictionary that describes a relationship between a verb and another component in a sentence such as a subject and an object. A computer program written in a computer readable format for performing language processing on a computer system,
A valence dictionary management step of giving a valence to an auxiliary verb or an auxiliary verb that is an expression that plays a role of use and passiveness;
A link forming step for forming a link between case elements by referring to a valence dictionary for a service sentence or a passive sentence;
A computer program characterized by comprising:
[0022]
The computer program according to the second aspect of the present invention defines a computer program described in a computer-readable format so as to realize predetermined processing on a computer system. In other words, by installing the computer program according to the second aspect of the present invention in the computer system, a cooperative action is exhibited on the computer system, and the natural language according to the first aspect of the present invention. Effects similar to those of the processing system and the natural language processing method can be obtained.
[0023]
Other objects, features, and advantages of the present invention will become apparent from more detailed description based on embodiments of the present invention described later and the accompanying drawings.
[0024]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
[0025]
Natural language parsing techniques can be broadly divided into methods based on statistical processing and methods based on grammatical rule description. The present invention can achieve a remarkable effect when applied to syntactic / semantic analysis based on grammar rule description.
[0026]
The natural language processing system according to the present invention can be implemented by being incorporated into syntactic / semantic analysis processing based on, for example, LFG (Lexical-Functional Grammar) grammar theory. In LFG, linguistic knowledge, that is, grammar of native speakers is configured as a component separated from computer processing and other non-grammatical processing parameters that affect the processing operation of the computer. First, an overview of the natural language processing system will be briefly described. Although the present embodiment will be described based on the LFG grammar theory, it is needless to say that the present invention can be similarly applied to an analysis system having other grammar rules.
[0027]
FIG. 5 schematically shows the configuration of the natural language processing system 1 based on LFG.
[0028]
The morpheme analysis unit 2 has a morpheme rule 2A and a morpheme dictionary 2B related to a specific language such as Japanese, and performs a part-of-speech recognition process by segmenting an input sentence into morphemes that are semantic minimum units. For example, if the sentence “My daughter speaks English” is entered, the result of the morphological analysis is that {up} daughter {Noun} of me {Noun} {up} English {Noun} } Speak {Verb1} {tr} Mas {jp}. {Pt} "is output.
[0029]
Such a morphological analysis result is then input to the syntactic / semantic analysis unit 3. The syntactic / semantic analysis unit has dictionaries such as grammar rules 3A and valence dictionaries 3B. Based on grammatical rule analysis, the meaning of words in a sentence, and the semantic relationship between words. Analyzes the semantic structure expressing the meaning conveyed by a sentence (a valence dictionary describes the relationship between verbs and other constituent elements in the sentence, such as the subject, and extracts the semantic relations between predicates and related words can do).
[0030]
As a result of the parsing, the input sentence is questioned based on “c-structure (constituent structure)” representing a phrase structure of a sentence composed of words, morphemes and the like as a tree structure, and a case structure such as a subject and an object. “F-structure (functional structure)” is output as a result of semantically and functionally analyzing sentences, past tense, polite sentences, and the like.
[0031]
FIGS. 6 and 7 respectively show c-structure and f-structure obtained as a result of processing the input sentence “My daughter speaks English” by the syntactic / semantic analysis unit 1.
[0032]
c-structure represents the structure of words and phrases in a sentence in a tree structure format, and is defined by a syntax category. For example, phonological interpretation for generating a phoneme string can be performed based on c-structure. On the other hand, f-structure clearly expresses a grammatical function, and includes a grammatical function name, a semantic form, and a feature symbol. By referring to the f-structure, it is possible to obtain an understanding of the meaning such as a subject, an object, a complement, and a modifier. The f-structure is a set of features associated with each node of the c-structure, and is expressed in the form of an attribute-attribute value matrix as shown in FIG. That is, the left side in [] is a feature (attribute) name, and the right side is a feature value (attribute value).
[0033]
For details on LFG, see, for example, the paper "Lexical-Functional Grammar: A Formal System for Grammatical Representation" by RM Kaplan and J. Bresnan (The MIT Press, Cambridge (1982). Reprinted in Formal Issues in Lexical-Functional Grammar. , pp. 29-130. CSLI publications, Stanford University (1995)).
[0034]
As already mentioned, there is a change in the valence of verbs in Japanese sentences and passive sentences. Therefore, in order to perform accurate semantic analysis processing, it is necessary to accurately handle such a phenomenon of valence change. However, it is very expensive to write the valence for all the expressions that form the usage sentence in the dictionary.
[0035]
Therefore, in the natural language processing system 1 according to the present invention, in the valence dictionary 3A, the valence is added to the auxiliary verbs such as “set”, “re”, “get”, and “get” that are expressions that play a role of use / passion. imparted by a link between case elements, valency original verb decided to use it. This can significantly reduce the cost of dictionary description.
[0036]
FIG. 1 shows a syntactic / semantic analysis procedure for a service / passive sentence according to this embodiment in the form of a flowchart.
[0037]
When a sentence composed of a usage sentence or a passive sentence is input to the process, the valence dictionary 3A is referred to (step S1).
[0038]
FIG. 2 shows a configuration example of headwords in the valence dictionary 3A. In the valence dictionary shown in the figure, the valence pattern of the auxiliary verb “Sel” and the valence of an ordinary verb are described. For example, “set” other than the common valence of “[subject] ga [object]]” and “[subject] ga bloom” for normal verbs such as “write” and “bloom” For auxiliary verbs, valences such as “[subject] ga [required case] ni [verb] make” and “[subject] ga [required case] wo [verb] make” are described.
[0039]
For example, for the sentence “Teacher to write a composition” for a sentence, when the two valences of the verb “write” and the auxiliary verb “sell” are inquired to such a valence dictionary 3A, the following two references are shown: Get results.
[0040]
1. 1. [Subject: Teacher] [Write] to [Required: Student] [Subject: NULL] writes [Object: Composition] [0041]
Next, the subject of the verb is linked to the required case of “S” (step S2). As a result, the subject of the verb that is NULL can be expressed using the valence of the original verb.
[0042]
For example, in the case of the above-described example sentence “Teacher to write a composition by a student”, the semantic analysis result shown in FIG. 3 can be obtained by the syntactic semantic analysis shown in FIG. As shown in the drawing, the subject of “writing a composition”, which was NULL until then, becomes “student”.
[0043]
As shown in FIG. 3, it is possible to describe in the semantic structure that the subject is “student” by using the valence “write” as it is. Therefore, we decided to use the valence of the original verb as it is to express the usage sentence. This can significantly reduce the cost of dictionary description.
[0044]
Next, let us consider a case where a semantic analysis of another usage sentence “He made the flower bloom” is performed according to the processing procedure shown in FIG.
[0045]
First, in step S1, the valence dictionary is inquired about two valences of the verb “Saku Saku” and the auxiliary verb “sue”. This sentence does not contain the case particle D, and “blooming” is an intransitive verb, so the following two reference results are obtained.
[0046]
1. [Subject: He] [Must]: [Flowers] [Subject: NULL] blooms. [0047]
Next, by linking the subject of the verb and the required case of the usage sentence (step S2), the subject of the verb that is NULL is expressed using the valence of the original verb.
[0048]
As a result, a semantic analysis result as shown in FIG. 4 can be obtained. As shown in the figure, the subject of “blooming”, which was NULL until then, becomes “flower”.
[0049]
As shown in FIG. 4, the valence “blooming” can be used as it is, and it can be described in the semantic structure that the subject is “flower”. Since the usage sentence is expressed using the valence of the original verb as it is, the cost of dictionary description can be significantly reduced.
[0050]
[Supplement]
The present invention has been described in detail above with reference to specific embodiments. However, it is obvious that those skilled in the art can make modifications and substitutions of the embodiment without departing from the gist of the present invention. That is, the present invention has been disclosed in the form of exemplification, and the contents described in the present specification should not be interpreted in a limited manner. In order to determine the gist of the present invention, the claims section described at the beginning should be considered.
[0051]
【The invention's effect】
As described above in detail, according to the present invention, a Japanese sentence including a verb whose valency changes between a use sentence and a passive sentence can be accurately and syntactically analyzed without increasing the cost. A natural language processing system, a natural language processing method, and a computer program can be provided.
[0052]
In addition, according to the present invention, a Japanese sentence including a verb whose valence is changed between a usage sentence and a passive sentence can be accurately syntactically defined without describing the valence for all expressions forming the usage sentence in a dictionary. An excellent natural language processing system, natural language processing method, and computer program that can be analyzed can be provided.
[0053]
According to the natural language processing system or the natural language processing method according to the present invention, the auxiliary verbs such as “sore”, “re”, “get”, and “get”, which are expressions responsible for use / passiveness, have a valence, By putting a link between the case elements, the original verb verb valence can be used as it is to express a useful sentence or passive sentence. That is, it is not necessary to describe the valence for all the expressions forming the usage sentence in the dictionary, and the cost of dictionary description can be significantly reduced.
[Brief description of the drawings]
FIG. 1 is a flowchart showing a procedure of syntactic / semantic analysis processing of a use / passive sentence according to the present embodiment;
FIG. 2 is a diagram showing an example of a valence dictionary.
FIG. 3 is a diagram showing a semantic analysis result obtained by processing a usage sentence by syntactic semantic analysis according to the present embodiment.
FIG. 4 is a diagram showing a semantic analysis result obtained by processing a usage sentence by syntactic semantic analysis according to the present embodiment.
FIG. 5 is a diagram schematically showing a configuration of a natural language processing system 1 based on LFG.
FIG. 6 is a diagram showing c-structure obtained as a result of processing the input sentence “My daughter speaks English” by the syntactic / semantic analysis unit 1;
FIG. 7 is a diagram showing f-structure obtained as a result of processing an input sentence “My daughter speaks English” by the syntactic / semantic analysis unit 1;
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... Natural language processing system 2 ... Morphological analysis part 2A ... Morphological rule, 2B ... Morphological dictionary 3 ... Syntactic / semantic analysis part 3A ... Grammar rule, 3B ... Valency dictionary

Claims (2)

A natural language processing system that extracts a semantic relationship between a predicate and a word related thereto by referring to a valence dictionary that describes a relationship between a verb and other components in a sentence such as a subject and an object,
A valence dictionary management means for giving a valence to an auxiliary verb or an auxiliary verb that is an expression that bears a duty or passiveness,
Queries the valency dictionary for the valence of each verb and auxiliary verb or auxiliary verb that appears in the servant sentence or passive sentence, and obtains a verb with no subject set by referring to the valence of the verb, and the subject of the verb And a correspondence forming means for forming a correspondence between essential cases obtained by referring to the valence of the auxiliary verb or the auxiliary verb, and
A natural language processing system comprising: In a natural language processing system built using a computer, the semantic relationship between predicates and related words is extracted by referring to a valence dictionary that describes the relationship between verbs and other components in the sentence, such as subject and object. A natural language processing method,
The valence dictionary management means provided in the computer has a valence dictionary management step of giving a valence to an auxiliary verb or an auxiliary verb that is an expression that bears a role of use and acceptance,
The link forming means included in the computer inquires the valence dictionary about the valence and auxiliary verb or auxiliary verb appearing in the working sentence or passive sentence, and the subject is not set by referring to the valence of the verb. A correspondence forming step for obtaining a verb and forming a correspondence between the subject of the verb and the essential case obtained by referring to the valence of the auxiliary verb or the auxiliary verb;
A natural language processing method comprising:

Images