-
[in Japanese]
Article type: Preface
1991 Volume 6 Issue 6 Pages
787
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese], [in Japanese], [in Japanese]
Article type: Cover article
1991 Volume 6 Issue 6 Pages
788
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Takahira YAMAGUCHI
Article type: Special issue
1991 Volume 6 Issue 6 Pages
789-793
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Keinosuke MATSUMOTO, Toshiaki SAKAGUCHI
Article type: Special issue
1991 Volume 6 Issue 6 Pages
794-799
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Hiroshi TSUMURA, Teruo KOYAMA
Article type: Special issue
1991 Volume 6 Issue 6 Pages
800-805
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Tadashi HIROSE, Fumihiko MORI
Article type: Special issue
1991 Volume 6 Issue 6 Pages
806-810
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Yutaka MIYABE, Osamu DAIRIKI
Article type: Special issue
1991 Volume 6 Issue 6 Pages
811-816
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Fumimaro SEKINE
Article type: Special issue
1991 Volume 6 Issue 6 Pages
817-822
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Takao TERANO, Osamu DAIRIKI, Tadashi HIROSE, Hiroshi TSUMURA, Takahira ...
Article type: Special issue
1991 Volume 6 Issue 6 Pages
823-833
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Yoshio MIYAKE
Article type: Corner article
1991 Volume 6 Issue 6 Pages
834-842
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Masao MUKAIDONO
Article type: Corner article
1991 Volume 6 Issue 6 Pages
843-850
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Harukazu IGARASHI
Article type: Technical paper
1991 Volume 6 Issue 6 Pages
851-860
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
The classical relaxation labeling method proposed by Rosenfeld, Hummel, and Zucker is very simple and widely used for solving various labeling problems. Its updating rule for labeling weights can be obtained from a transition rule of a linear Hopfield's analog neuron model by using a discrete time approximation. This neuron model, however, is not a natural neural network model because a time constant for each neuron should be modified at each time step according to a state of the system. In this paper, a more powerful relaxation method ("Neural Relaxation Labeling Method") based on a neural network model with a nonlinear output function is proposed and applied to problems of matching and recognizing patterns which consist of several straight line segments. Compatibility coefficients are calculated by a linear combination of several feature functions which represent disagreements between two pairs of primitives. Parameters including proportional coefficients with which the feature functions are multiplied can be learned by using a steepest descent method for decreasing the value of an error function. Our simulations indicate that the present method with the parameters above has achieved more correct matching ability and a higher level of recognition ratio than those by the classical relaxation method.
View full abstract
-
Satoshi SATO
Article type: Technical paper
1991 Volume 6 Issue 6 Pages
861-871
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
Example-Based Translation is a new approach to machine translation. The basic idea is very simple : translation by using or imitating translation examples. An essential problem of example-based translation is how to utilize more than one translation example for translating one source sentence. This paper proposes MBT2, which is a method to solve this problem. We introduce the representation, called matching expression, which represents the combination of fragments of translation examples. The translation process consists of three steps : (1) Make the source matching expression from the source sentence. (2) Transfer the source matching expression into the target matching expression. (3) Construct the target sentence from the target matching expression. This mechanism generates some translation candidates. To select the best translation from them, we define the score of a translation. We implemented MBT2 in English-Japanese translation.
View full abstract
-
Yasuharu DEN, Makoto NAGAO
Article type: Technical paper
1991 Volume 6 Issue 6 Pages
872-880
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
In the current researches in natural language processing and formal semantics, several studies have been made for modeling discourse processing. One of the powerful approaches is to build a model based on the relation theory of meaning, in which utterances are interpreted as mappings between situations or beliefs. In this paper, we construct the model of discourse processing based on the Discourse Management Theory (DMT), which is a kind of semantic theory inspired by the idea of the relation theory of meaning. As is discussed in detail in DMT, some natural language expressions, for instance, Japanese noun phrase expressions such as 'Tanaka', 'Tanaka-toiu-hito (a man named Tanaka)', 'ano-hito (that man)', and 'sono-hito (also that man)', are used selectively depending on the contents of the speaker's and hearer's knowledge, that is, the context when those expressions are uttered. A principle for choosing an appropriate expression to a context is formalized by considering constraints which those expressions have. These constraints are processed uniformly according to the same schema of DMT. Context processing, both context analysis and generation, is modelled as the mapping between contexts using constraints ; that is, the schema of DMT. Using each constraint one context is mapped to another, and the whole context processing is constituted by the composition of these mappings. In this model, no specific procedures, such as analysis and generation of anaphoric expressions, are used. All contextual processes, for instance, identifying the antecedent of an anaphora in context analysis and deciding which expression to use for a description in context generation, are done by the mapping using concerned constraints as a part of the course of the whole context processing according to the DMT schema. We will illustrate these processes with some example dialogues.
View full abstract
-
Tetsuro ITO
Article type: Technical paper
1991 Volume 6 Issue 6 Pages
881-890
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
Clustering can be viewed as a basic approach to concept learning. Previous methods of conceptual clustering select, based on the criteria of maximizing the quality of clustering, appropriate attributes from the a priori given set of ones in order to produce a generalized description for each concept. We here propose a new learning model CNC, consisting of numerical and conceptual parts, which can form concepts by the cooperative tasks of two parts even under the circumstance of giving no prespecified attributes. The numerical part in CNC produces similarity-based clusters by the quantitative treatment of the objects and assists the conceptual part in getting the generalized descriptions for specifying clusters and discriminating different clusters, conceptually. Needed attributes for the descriptions are generated in the course of learning by forming recursively a conceptual structure for simplified versions of the original objects. Computational experiments are also examined to see how CNC works well for the real world color data. As a result several concepts, to which we give the names, red, pink, orange, brown, etc., were formed together with a few color attributes for characterizing them.
View full abstract
-
Keisuke SHIDA, Kiyoshi ITOH, Shin-ichi HON-IDEN
Article type: Technical paper
1991 Volume 6 Issue 6 Pages
891-903
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
This paper describes a qualitative method by Bottleneck Diagnosis Expert System for Synchronized queueing network (BDES-S). On the basis of qualitative reasoning, BDES-S can carry out parameter tuning by diagnosing bottlenecks of synchronized queueing networks and by producing several alternative qualitative improvement plans. This paper also analyzes the differences betweeen ordinary and synchronized queueing networks.
View full abstract
-
Masamitsu TAKAHASHI, Yasuhito SASAKI, Kiyoshi ITOH
Article type: Technical paper
1991 Volume 6 Issue 6 Pages
904-911
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
Pseudo Boolean Algebraic Solution can be applied to automatic construction of all polyhedra from the given orthographic views. The orthographic views are called ambiguous if one or more polyhedra can be constructed from the views. Even if ambiguous orthographic views are given, personnel can construct a unique polyhedron with the use of their heuristics. Such heuristics can be also formalized by Pseudo Boolean Algebraic nonlinear integer programming in order to construct a unique polyhedron automatically from the ambiguouns orthographic views.
View full abstract
-
Shigeyoshi WATANABE, Yoshihiro SHIBUSAWA
Article type: Technical paper
1991 Volume 6 Issue 6 Pages
912-919
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
This paper presents a script-based tutor installed in an intelligent computer-aided instruction system. We assumed that knowledge is first acquired declaratively through instruction and that it has to be converted into and recognized as procedures through experience. The assumption suggests that learning by doing problem-solving allows students, who at first must have gained the declarative knowledge in lectures, to strengthen the declarative knowledge and acquire the procedural knowledge or skills. The tutoring system can offer students such a practicing environment. Primitive knowledge in the system is composed of declarative knowledge of electrical circuit analysis. Scripts incorporate compiled expertise of primitive knowledge and procedures for solving electrical circuit problems. A script is an ideal model of a problem-solving plan represented by correct knowledge and procedures. A script is a collection of slots for events that provides conceptual dependency between them. The events are caused by the student's activities in his own problem-solving attempt. For example, when he describes his actions by sentences and equations. Actions are evaluated by a rule-based diagnosis module, and the slots of the script are filled with the results. Therefore the student model in the system is formed as an overlay on the script. The script-based tutor uses a direct tutorial strategy that consists of local tactics and global tactics. The direct tutor guides the student's behavior by direct indication of errors and explanation of procedures. In addition, the student's abilities are improved via practice. The local tactics provide students with immediate feedback on incorrect actions and requests for assistance. The feedback merely confirms the student's correct action and gives the remedies for his errors. When the errors or impasses in the student's problem-solving attempt are originated in misunderstanding or forgetfulness, he can request for explanation of primitive knowledge and procedures. This tutoring tactic is similar to Anderson's model tracing, because the student is made to follow one of the system's ideal models quite closely. The global tactics provide a global evaluation of the script of the just-completed problem and an assessment of the student's problem-solving performance. In addition, the next problem is chosen from the problem file, where the sequence can be tailored depending on each student's understanding. In this way, adaptive tutoring is achieved.
View full abstract
-
Masayuki NUMAO, Masamichi SHIMURA
Article type: Technical paper
1991 Volume 6 Issue 6 Pages
920-927
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
Program synthesis by examples is more convenient than using conventional techniques, since it only requires examples instead of a detailed specification. In spite of this convenience, relatively little research in this type of synthesis has so far been carried out. A major obstacle is that, due to the similarity-based and data-driven features of this technique, many examples and considerable computation power are required to synthesize a complex program. To overcome this difficulty, such systems require some useful heuristics given by their programmer. This paper proposes a method for automatically acquiring such heuristics based on explanations of synthesis processes, in which the system explains how other similar programs are synthesized from given examples and transfers the explanation to the target. To synthesize a program by examples, we write a reversible meta-interpreter. In addition to obtaining a result from a program and data, the interpreter can conversely derive a program from data and a user-specified result. For the synthesis, this interpreter explains how other programs are computed, and then synthesize a new program from given examples by transferring the explanations. Since the programming know-how involved in the similar programs is already available, new programs are easily synthesized using only a small number of examples.
View full abstract
-
[in Japanese]
Article type: Other
1991 Volume 6 Issue 6 Pages
928-929
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Other
1991 Volume 6 Issue 6 Pages
930
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese], [in Japanese], [in Japanese], [in Japanese]
Article type: Corner article
1991 Volume 6 Issue 6 Pages
931-935
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1991 Volume 6 Issue 6 Pages
935-936
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese], [in Japanese], [in Japanese], [in Japanese]
Article type: Corner article
1991 Volume 6 Issue 6 Pages
936-940
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1991 Volume 6 Issue 6 Pages
941-942
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1991 Volume 6 Issue 6 Pages
943-944
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1991 Volume 6 Issue 6 Pages
945
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Other
1991 Volume 6 Issue 6 Pages
946
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1991 Volume 6 Issue 6 Pages
947-949
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1991 Volume 6 Issue 6 Pages
950-952
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1991 Volume 6 Issue 6 Pages
953-957
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1991 Volume 6 Issue 6 Pages
958-962
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1991 Volume 6 Issue 6 Pages
963-964
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1991 Volume 6 Issue 6 Pages
b001-b012
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Cover page
1991 Volume 6 Issue 6 Pages
c006
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Cover page
1991 Volume 6 Issue 6 Pages
c006_2
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Table of contents
1991 Volume 6 Issue 6 Pages
i006
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Table of contents
1991 Volume 6 Issue 6 Pages
i006_2
Published: November 01, 1991
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS