-
[in Japanese]
Article type: Preface
1994 Volume 9 Issue 6 Pages
791
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Cover article
1994 Volume 9 Issue 6 Pages
792
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
G. Hiroshi OKUNO
Article type: Special issue
1994 Volume 9 Issue 6 Pages
793-798
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Yoshiyasu TAKEFUJI
Article type: Special issue
1994 Volume 9 Issue 6 Pages
799-803
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Hiroshi MIZUSHIMA
Article type: Special issue
1994 Volume 9 Issue 6 Pages
804-809
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Toshihiro TAKADA
Article type: Special issue
1994 Volume 9 Issue 6 Pages
810-816
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese], [in Japanese]
Article type: Cover article
1994 Volume 9 Issue 6 Pages
817
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Hirokazu TAKI
Article type: Special issue
1994 Volume 9 Issue 6 Pages
818-822
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Seiji YAMADA
Article type: Special issue
1994 Volume 9 Issue 6 Pages
823-829
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Tatsuo UNEMI
Article type: Special issue
1994 Volume 9 Issue 6 Pages
830-836
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Masayuki NUMAO
Article type: Special issue
1994 Volume 9 Issue 6 Pages
837-842
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Takahira YAMAGUCHI
Article type: Corner article
1994 Volume 9 Issue 6 Pages
843-849
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Yuichi NAKANMURA, Masahiro HORI
Article type: Corner article
1994 Volume 9 Issue 6 Pages
850-858
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Shigeru YAMANE
Article type: Corner article
1994 Volume 9 Issue 6 Pages
859-862
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Satoshi TOJO, Hiroshi TSUDA, Hideki YASUKAWA, Kazumasa YOKOTA, Yukihir ...
Article type: Technical paper
1994 Volume 9 Issue 6 Pages
863-874
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
In natural language processing, a very complex flow of information must be dealt with. There are two remarkable features in the current paradigm of computational linguistics : one is the constraint-based formalism of grammar and the other is the situatedness of semantics. In order to realize these features, we developed a language QUIXOTE as a framework for representing and processing such linguistic information. QUIXOE is a hybrid language of deductive object-oriented database and constraint logic programming language. The new mechanism of QUIXOT is a combination of the object-oriented notion such as object identity and the concept of module that classifies a large knowledge base. In addition, its logical inference is extended to be able to make restricted abduction. We first introduce the basic structure of QUIXOTE and thereafter we show that the typed-feature structure of constraint-based grammar can be represented in QUIXOTE, using complex objects and constraints upon them. Next, we show how QUIXOTE can contribute to the description of situation-based semantics, regarding modules as situations, where an abductive reasoning system for hidden information and an ambiguity analyzer of noun phrase reference are given as examples.
View full abstract
-
Osamu TAKIZAWA, Akira ITO
Article type: Technical paper
1994 Volume 9 Issue 6 Pages
875-881
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
We designed a method for detecting ironic utterances. The system is based on the fact that ironies generally satisfy 4 conditions : (1) the situation has a negative "personal evaluation value" (PEV), (2) the surface meaning of the utterance has a positive PEV, (3) the situation and the utterance are opposite in meaning, and (4) the utterance includes "ironic markers". The system, whose input is the situation and the utterance, consists of 4 processing steps. First, the system determines the PEV of the input. Second, the System checks whether the input satisfies conditons (l) and (2). Third, the system compares the opposite relation between the situation and the utterance. And fourth, the system inspects the sentence particle in the utterance. The output is the calculated "degree of irony". The proposed method contributes to the improvement of the understanding system of connotation in natural language.
View full abstract
-
Toyoshi OKADA, Kazuo HIRAKI, Yuichiro ANZAI
Article type: Technical paper
1994 Volume 9 Issue 6 Pages
882-889
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
There has been research for intelligent robots that has focused on improving robot's performance and making robots execute several tasks reliably. This research is important ; however, the research for human-robot intelligent interaction will also be needed for the application of intelligent robots in the future. People expect to communicate with intelligent robots via natural language. However, because the mearning of many abstract symbolic representations changes according to the situation, it is difficult to make a robot understand the representation and execute several tasks according to the situation. This paper proposes Acorn-II, a system that learns relational behavior and situations. The system incrementally learns algebraic expressions that represent the constraints among sensors and actuators from positive and negative instances of sensor/actuator data. Information for recognizing external situations can not be perceived directly from primitive features. It can be perceived from new features constructed from primitive features. So, this system learns algebraic expressions that represent the constraints among primitive features by combining a "Feature Construction" method and a "Generalization To Interval" method. The paper evaluates this system with empirical results and shows that it can learn robot commands more accurately than the famous learning systems CN2 and C4. It has been implemented in an autonomous mobile robot Einstein I.
View full abstract
-
Teruaki ITO, Shuichi FUKUDA
Article type: Technical paper
1994 Volume 9 Issue 6 Pages
890-898
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
A new concept of Hypergraph proposed that creates an improved designing environment for graph structured object with dynamic perspective and perspective-oriented shifting methodology. The objective of this research is to create a modeling environment under Hypergraph concept in which creative idea processing is enhanced, for example, in synthesis route planning for molecular designing process. Combination of Hypertext navigation functionality and dynamic activation of Hypergraph anchor with perspective-oriented shifting capabilities presents a new environment for creative thinking in designing molecular structure.
View full abstract
-
Takeshi FUCHI, Akinori YONEZAWA
Article type: Technical paper
1994 Volume 9 Issue 6 Pages
899-907
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
An utterance has implied meanings. Hence, a computer has to infer implied meanings to communicate with humans smoothly. This paper deals with some of implied meanings which occur when a speaker gives a hearer an insufficient answer for a question. We assumes that the implied meanings are derived from an utterance with the following factors : relation between the utterance and its context, the speaker and hearer's knowledge of the utterance, their loss and gain, their evaluation of the utterance, their hierarchy, their friendship, and the form of the utterance. We give formal descriptions of the factors and their rules to obtain the implied meanings. The knowledge of an utterance is expressed with a modal logic based on KD45_<(M)>. The hearer infers the implied meanings of the speaker's insufficient answer with the following rules. (l) Default Unknown Rule : The speaker does not know the lacked information when it is not clear that the speaker knows the information. (2) Affect Ignorance Rule : The speaker affects ignorance of the lacked information if it is clear that the speaker knows the information and it is loss to him. (3) Embarrassed Rule : The speaker is embarrassed with the lacked information if it is clear that the speaker knows the information and it is gain to him. (4) Hesitation Rule : The speaker hesitates to speak the lacked information if it is clear that the speaker knows the information and it is loss to the hearer. (5) Default Negation Rule : The speaker negates the lacked information if it is clear that the speaker knows the information and it is neither loss nor gain to both the speaker and the hearer. (6) Unpleasantness Rule : The speaker feels unhappy to talk about the lacked information if the hearer cannot infer the lacked information with the above-mentioned rules.
View full abstract
-
Satoshi HORI, Hiromitsu SUGIMATSU, Kiichiro AZUMA, Hirokazu TAKI
Article type: Technical paper
1994 Volume 9 Issue 6 Pages
908-916
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
We have prototyped a diagnostic system, Doctor, which employs case-based reasoning (CBR). The objective of the Doctor is to support service persons to repair home appliances, e.g., room airconditioners. The Doctor asks several questions to collect symptoms when an end-user asks for repair. Then defect candidates for the repair are listed up by retrieving previous cases which are similar to the collected Symptomns. Good casebases are essential to obtain accurate results in CBR. The Doctor has casebases, called ByType casebases, which are assorted according to product types. Therefore the diagnostic output of our system can reflect the defect trend of each product type. The ByType casebases are initailly built from the generic casebase which collects diagnostic rules experienced service persons have. The ByType casebases are afterword updated by adding service reports which consist of observed symptoms and repair actions, i.e., what was done to fix a fault. Our method is one way of integrating two knowledge sources, rules and cases. An advantage of our method is that a diagnostic system needs only one reasoning mechanism, CBR, to exploit the two knowledge sources because they are combined into a ByType casebase in advance. One of development items of a CBR system is the design of a heuristic function which evaluates the similarity of two cases. We introduced a metric Possibility which values how much effective a previous case is to repair a malfunction. The Possibility function considers the similarity of two sets of symptoms and the frequency of a previous case, i.e. how often a repair action was taken to fix the same set of symptoms. Therefore the doctor can list up defect candidates with their probability. In this paper, we describe how to build a generic casebase and the retrieval algorithm of our system. We also demonstrate the effectiveness of the Doctor with some experimental results of room air-conditioner diagnosis.
View full abstract
-
Tetsuro ITO, Lin-Ju YEH, Makoto NAKASHIMA
Article type: Technical paper
1994 Volume 9 Issue 6 Pages
917-926
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
A new learning model called SCNC, working in structured domains consisting of objects with many components, is presented to induce concepts under the situation where no attributes are prespecified. Model SCNC receives observed data about the components, and outputs a concept hierarchy and attributes for describing concepts. The needed attributes are generated in the course of concept formation. One important problem in treating structured objects is what kind of description is to be employed. If any description is expressed in a combination of various literals for each component as seen in the previous models, the results should be understood via relations among the components. We here propose to employ descriptions with a single attribute for some specified components, and discuss the benefits of employing them in getting a compact and easy understandable concept hierarchy. The applicability of SCNC to the real world data is also examined from viewpoints of the costs and the resultant qualities.
View full abstract
-
[in Japanese]
Article type: Other
1994 Volume 9 Issue 6 Pages
927
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese], [in Japanese]
Article type: Corner article
1994 Volume 9 Issue 6 Pages
928-931
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1994 Volume 9 Issue 6 Pages
932
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1994 Volume 9 Issue 6 Pages
933
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1994 Volume 9 Issue 6 Pages
934
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Other
1994 Volume 9 Issue 6 Pages
935
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1994 Volume 9 Issue 6 Pages
936
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1994 Volume 9 Issue 6 Pages
937-939
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1994 Volume 9 Issue 6 Pages
940-944
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1994 Volume 9 Issue 6 Pages
945-946
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1994 Volume 9 Issue 6 Pages
b001-b010
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Cover page
1994 Volume 9 Issue 6 Pages
c006
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Cover page
1994 Volume 9 Issue 6 Pages
c006_2
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Table of contents
1994 Volume 9 Issue 6 Pages
i006
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Table of contents
1994 Volume 9 Issue 6 Pages
i006_2
Published: November 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS