Data processing: speech signal processing – linguistics – language – Linguistics – Natural language
Reexamination Certificate
1999-08-31
2001-06-05
Thomas, Joseph (Department: 2644)
Data processing: speech signal processing, linguistics, language
Linguistics
Natural language
C707S793000
Reexamination Certificate
active
06243670
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention generally relates to a semantic analysis method, a semantic analysis apparatus and a computer readable medium storing a semantic analysis program, and, more particularly, to the method, the apparatus and the computer readable medium in an information searching system used for an information providing service. The information searching system receives an inquiry information of a natural language sentence from a user, and carries out morphological analysis, syntax analysis and semantic analysis. As a result, a semantic structure is obtained. Then, the system extracts keywords as searching keys from the semantic structure, and infers a category name corresponding to the natural language sentence by using the keywords, and outputs a set of searching objects which belong to the category name.
2. Description of the Related Art
As a conventional example of the semantic analysis method, enhanced LINGOL has been proposed. The enhanced LINGOL generates the semantic structure by going back along the syntactic tree from a part of a speech node of the syntactic tree to a sentence (S) node which is a top node in a bottom-up manner.
The enhanced LINGOL includes semantic processing functions in each grammar rule which is used for syntax analysis. After the syntax analysis, the semantic processing functions are activated so as to carry out the semantic analysis. Shun Ishizaki, “Natural language processing”, Shoukoudou, can be referred to for more information on this method.
However, in the information searching system which extracts keywords as searching keys from the semantic structure, each of the keywords to be extracted is a specific deep case of a verb in many cases. For example, the keywords to be extracted from an inquiry sentence, “I want to buy flowers in Tokyo”, are a verb “buy”, a commodity “flowers” and an address “Tokyo”, the verb “buy” being the head of an infinitive phrase “to buy flowers in Tokyo” which is the objective case of a verb “want” which is the head of the sentence, the commodity “flowers” being the objective case of the verb “buy”, and the address “Tokyo” being the location case of the verb “buy”.
Thus, since deep cases which are necessary for extracting the keywords are determined in each information providing service session, it is unnecessary for extracting the keywords to obtain a semantic structure of the inside of the other deep cases.
In the conventional bottom-up search method, since semantic analysis of the inside of unnecessary deep cases is carried out, efficiency decreases and the time necessary for the semantic analysis increases.
In addition, in the method in which semantic processing functions are included in each grammar rule, since the semantic processing function needs to be made for each grammar rule, it is difficult to make the semantic processing function while grasping the whole flow of the semantic analysis.
SUMMARY OF THE INVENTION
It is an object of the present invention to provide a semantic analysis method, a semantic analysis apparatus and a computer readable medium storing a semantic analysis program which can reduce the time necessary for the semantic analysis by analyzing only necessary deep case phrases which are specified for keyword extraction so as to circumvent the need to analyze the inside of the unnecessary deep case, and which allow the user to easily understand the flow of the semantic analysis in a visual way such that the user can easily maintain and modify the semantic analysis apparatus.
The present invention can solve the above-mentioned objective by the following features.
According to a first aspect of the present invention, a method for performing a semantic analysis process on a computer system including a storage unit and an interface, includes the steps of:
receiving a syntactic tree generated from a natural language sentence text;
determining whether an analysis object, which is one of nodes of the syntactic tree, is a verb phrase class which has a verb as a head or a non-verb phrase class which has mainly a noun as the head on the basis of subdivided type information of a phrase of the node with reference to first data stored in the storage unit;
analyzing a relation between a verb in the analysis object and a deep case of the verb when the analysis object is the verb phrase class;
analyzing a modificative relation in the analysis object when the analysis object is the non-verb phrase class;
generating a semantic structure of the natural language sentence text wherein the semantic structure comprises semantic frames corresponding to nodes of the syntactic tree, at least two semantic frames of the semantic frames being linked by a head relation or a deep case relation or a modificative relation, and
storing the semantic structure in the storage unit or displaying the semantic structure on a display which is connectable to the computer system via the interface.
According to a second aspect of the present invention, a method for searching information which uses the method for performing the semantic analysis process on the computer system including the storage unit and the interface, includes the steps of:
receiving a natural language sentence text via the interface,
performing a morphological analysis process and a syntax analysis process of the natural language sentence text and generating a syntactic tree of the natural language sentence text;
performing the semantic analysis process for the syntactic tree and generating a semantic structure of the natural language sentence text;
extracting a keyword representing an intention of a user of the computer system from the semantic structure;
obtaining a category name and address information corresponding to the natural language sentence text from the keyword with reference to at least a knowledge database stored in the storage unit;
obtaining information to be searched with the category name and the address information with reference to an information database stored in the storage unit, the information database including the information which is classified by the category name and the address information, and
sending obtained information via the interface to another computer system or displaying the information on a display which is connectable to the computer system.
According to a third aspect of the present invention, an apparatus for performing a semantic analysis process, including a storage unit and an interface, includes:
unit for receiving a syntactic tree generated from a natural language sentence text;
first unit for determining whether an analysis object, which is one of nodes of the syntactic tree, is a verb phrase class which has a verb as a head or a non-verb phrase class which has mainly a noun as the head on the basis of subdivided type information of a phrase of the node with reference to first data stored in the storage unit;
second unit for analyzing a relation between a verb in the analysis object and a deep case of the verb when the analysis object is the verb phrase class;
third unit for analyzing a modificative relation in the analysis object when the analysis object is the non-verb phrase class;
unit for generating a semantic structure of the natural language sentence text wherein the semantic structure comprises semantic frames corresponding to nodes of the syntactic tree, at least two semantic frames of the semantic frames being linked by a head relation or a deep case relation or a modificative relation, and
wherein the semantic structure is stored in the storage unit or displayed on a display which is connectable to the apparatus via the interface.
According to a fourth aspect of the present invention, an apparatus for searching information which uses the apparatus for performing the semantic analysis process on the computer system including the storage unit and the interface, includes:
unit for receiving a natural language sentence text via the interface,
unit for performing a morphological analysis process and a syntax analysis process for the natural language se
Bessho Katsuji
Iwase Shigehito
Kenyon & Kenyon
Nippon Telegraph and Telephone Corporation
Thomas Joseph
LandOfFree
Method, apparatus, and computer readable medium for... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method, apparatus, and computer readable medium for..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method, apparatus, and computer readable medium for... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2532710