-
[in Japanese]
Article type: Preface
1994 Volume 9 Issue 4 Pages
477
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese], [in Japanese]
Article type: Cover article
1994 Volume 9 Issue 4 Pages
478
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
G. Hiroshi OKUNO
Article type: Special issue
1994 Volume 9 Issue 4 Pages
479-486
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Mitsuru IKEDA
Article type: Special issue
1994 Volume 9 Issue 4 Pages
487-496
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Kazuo HIRAKI
Article type: Special issue
1994 Volume 9 Issue 4 Pages
497-504
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Cover article
1994 Volume 9 Issue 4 Pages
505
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Masayuki YAMAMURA, Shigenobu KOBAYASHI
Article type: Special issue
1994 Volume 9 Issue 4 Pages
506-511
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Hitoshi IBA
Article type: Special issue
1994 Volume 9 Issue 4 Pages
512-517
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Tatsuo UNEMI
Article type: Special issue
1994 Volume 9 Issue 4 Pages
518-523
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Yukinori KAKAZU
Article type: Special issue
1994 Volume 9 Issue 4 Pages
524-529
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Makoto NAGAO
Article type: Corner article
1994 Volume 9 Issue 4 Pages
530-536
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Noritaka NISHIHARA, Ken-ichi MORITA, Fumio SAITO
Article type: Technical paper
1994 Volume 9 Issue 4 Pages
537-547
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
Term logic is a logic system where the meanings and the derivation relations of sentences can be directly described as relations among terms (which correspond to nouns of natural language). Previously, we proposed the term logic system LVPM which can deal with compound terms corresponding to noun phrases modified by adjectives or relative clauses. This system was constructed as an axiomatic one, and its completeness under a set theoretical semantics was proved. In the system LVPM, a compound term is directly represented by an expression composed of terms and verb symbols. Thus, it has a unique character different from predicate logic where expressions are represented based on relations among individuals. In this paper, we consider a reasoning method for natural language sentences based on this logic system. Firstly, we provide a mechanical inference procedure for LVPM. Then, we construct a question-answering system by Japanese sentences based on LVPM. In this system, an input sentence is translated into an expression of the term logic, then if it is a declarative sentence, the expression for it is stored in the knowledge base, and if it is an interrogative one, an appropriate answer for it is produced by applying the inference procedure. Since this system is based on the term logic, the reasoning can be treated as direct operations for terms without decomposing into relations of individuals like as predicate logic.
View full abstract
-
Masaki SUWA, Hiroshi MOTODA
Article type: Technical paper
1994 Volume 9 Issue 4 Pages
548-558
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
An advantage of diagrammatic reasoning is that it avoids traversing irrelevant paths of inference by controlling search using visual scanning on diagrams. An effective procedure for this in the domain of geometry problem solving is to visually recognize relevant perceptual-chunks in the diagrams of problems, and to use such chunks to guide problem solving. In spite of this beneficial role of perceptual-chunks in diagrammatic reasoning, however, past research has not addressed the issues of acquiring a useful set of perceptual-chunks specific to the target domain, and demonstrating the utility of acquired chunks. This paper addresses these issues by devising a mechanism for learning perceptual-chunks from problem solving episodes. Its basic concept is that the learner acquires, from the problem diagram perceptual chunks each of which is an assembly of diagram elements that can be visually recognized and grouped together. Recognition rules implement this chunking criterion in the learning system PCLEARN. We show the feasibility of the criterion by presenting experimental data on the operationality and cost-effective utility of the learned perceptual chunks in the geometry domain.
View full abstract
-
Satoru IKEHARA, Satoshi SHIRAI, Kentarou OGURA
Article type: Technical paper
1994 Volume 9 Issue 4 Pages
569-579
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
This paper describes the design of a set of 6200 Japanese-English sentence pairs for testing Japanese to English MT systems. Japanese expressions are organized into 600 test items with consideration for the characteristics of both Japanese and English, an average of 10 sentence pairs were then made for each item. In machine translation, translations between two very different languages (e.g. Japanese and English) are more difficult than between two similiar languages (e.g. Japanese and Korean). This is believed to be due to differences in morphology and in how things are conceived in different language groups. Therefore, we have focused our attention beyond morphological differences to cover differences in perception and concepts. The process of constructing Japanese texts is examined at 5 levels (part of speech, phrase, expression, sentence and text). Based on these 5 levels and considering the differences between the two languages, about 600 test items were chosen to test the basic functions of Japanese to English machine translation systems. Finally examples of these test items were extracted from various documents and publications and combined with specially constructed sentences to make the test set of 6200 sentence pairs.
View full abstract
-
Kazuteru MIYAZAKI, Masayuki YAMAMURA, Shigenobu KOBAYASHI
Article type: Technical paper
1994 Volume 9 Issue 4 Pages
580-587
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
Reinforcement learning is a kind of machine learning. It aims to adapt a system to a given environment according to rewards. We consider profit sharing that is a representative reinforcement learning method. A rule sequence applied between reward and reward is called an episode. Profit sharing reinforce rules at each episode. A function that shares the reward between rules of an episode is called a reinforcement function. Conventional work has used ad hoc functions. This paper analyzes reinforcement functions theoretically. First, we examine what a reinforcement function is locally reasonable. We call a rule is ineffective if and only if it is on a detour for any episodes. It is locally reasonable that ineffective rules are suppressed than any effective rules. We have derived the necessary and sufficient condition to suppress any ineffective rules as following inequality ; <LΣ>^^^w___<j=i><f_<i-1> (i=1,…,W). where, L is the maximum number of conflicting effective rules, W is the maximum length of episodes, and f_j is the value of reinforcement for the j-th previous rule applied before the reward. We call this as the ineffective rule suppression theorem. We demonstrate that a profit sharing can learn ineffective rules when the condition is violated. Second, we examine whether reinforcement functions satisfying the condition are globally reasonable. We call a collection of effective rules as a rule selection plan if and only if it selects at most one effective rule per one state. It is globally reasonable that a plan gains reward continuously. We show that the condition is also necessary and sufficient to learn a rewardfull plan. We call this as the rewardfull plan acquisition theorem. We also demonstrate that a profit sharing can learn rewardless plans when the condition is violated.
View full abstract
-
Somkiat TANGKITVANICH, Masamichi SHIMURA
Article type: Technical paper
1994 Volume 9 Issue 4 Pages
588-594
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
This paper presents an approach to a new learning problem, the problem of learning from an approximate theory and a set of noisy examples. This problem requires a new learning approach since it cannot be satisfactorily solved by either inductive, or analytic learning algorithms or their existing combinations. Our approach can be viewed as an extension of the minimum description length (MDL) principle, and is unique in that it is based on the encoding of the refinement required to transform the given theory into a better theory rather than on the encoding of the resultant theory as in traditional MDL. Experimental results show that, based on our approach, the theory learned from an approximate theory and a set of noisy examples is more accurate than either the approximate theory itself or a theory learned from the examples alone. This suggests that our approach can combine useful information from both the theory and the training set even though both of them are only partially correct.
View full abstract
-
Nobuo DOMAE, Mitsuru ISHIZUKA
Article type: Technical paper
1994 Volume 9 Issue 4 Pages
595-603
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
A logic-based hypothetical reasoning system, which employs the mechanism of abduction, is a useful knowledge processing framework applicable to many practical problems including diagnosis, design, etc. However, it has a crucial problem of slow inference-speed due to its nonmonotonic inference nature. Knowledge-base reformation, which can be executed before the actual use of the knowledge-base, is one way to overcome this problem. This paper presents a knowledge-base reformation method consisting of two phases. The first phase is the partial compilation of knowledge-base, which is an extension of the compilation of propositional knowledge into prime implicates. The second phase is the transformation of the compiled knowledge into multi-level logical knowledge, which makes it possible to avoid redundant inference caused by the direct use of the compiled knowledge. A speedup effect obtained by the knowledge reformation is shown experimentally.
View full abstract
-
Haruhiko KIMURA, Ryuichi ARAI, Shinya KOBAYASHI, Tsuyoshi TAKEBE
Article type: Corner article
1994 Volume 9 Issue 4 Pages
604-610
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
This paper demonstrates by experiment the efficiency of a proposed method for dealing with expensive productions in production systems. Production systems are an established method for encoding knowledge in an expert system. Expensive productions are rules which would be required the extraordinary time and space to match (for each rule, compare the left-hand side against the current working memory). The method for dealing with expensive productions in this paper exploits a simple notation expressing plural instantiations satisfying a rule's left-hand side, using direct products combining subsets of working memory elements. We compare the proposed match algorithm with RETE match algorithm in both the execution time and space. Evaluation results demonstrate the proposed method is more efficient than RETE match algorithm.
View full abstract
-
[in Japanese]
Article type: Other
1994 Volume 9 Issue 4 Pages
611-612
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1994 Volume 9 Issue 4 Pages
613-614
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1994 Volume 9 Issue 4 Pages
615
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1994 Volume 9 Issue 4 Pages
616
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Other
1994 Volume 9 Issue 4 Pages
617
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1994 Volume 9 Issue 4 Pages
618-619
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1994 Volume 9 Issue 4 Pages
620-624
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1994 Volume 9 Issue 4 Pages
625-626
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1994 Volume 9 Issue 4 Pages
b001-b010
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Cover page
1994 Volume 9 Issue 4 Pages
c004
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Cover page
1994 Volume 9 Issue 4 Pages
c004_2
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Table of contents
1994 Volume 9 Issue 4 Pages
i004
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Table of contents
1994 Volume 9 Issue 4 Pages
i004_2
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Other
1994 Volume 9 Issue 4 Pages
o001
Published: July 01, 1994
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS