-
[in Japanese]
Article type: Preface
1993 Volume 8 Issue 2 Pages
139
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1993 Volume 8 Issue 2 Pages
140-141
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Cover article
1993 Volume 8 Issue 2 Pages
142
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Mitsuteru YUKISHITA, Yukihiro NAKAMURA
Article type: Special issue
1993 Volume 8 Issue 2 Pages
143-147
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Fumihiro MARUYAMA
Article type: Special issue
1993 Volume 8 Issue 2 Pages
148-153
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Yoichi SHIRAISHI, Jun'ya SAKEMI
Article type: Special issue
1993 Volume 8 Issue 2 Pages
154-158
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Kazuo TAKI
Article type: Special issue
1993 Volume 8 Issue 2 Pages
159-165
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Hideo FUJIWARA
Article type: Special issue
1993 Volume 8 Issue 2 Pages
166-172
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Yoshiyuki KOSEKI
Article type: Special issue
1993 Volume 8 Issue 2 Pages
173-178
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Kazuyuki AIHARA, Toshifumi YOSHIKAWA
Article type: Corner article
1993 Volume 8 Issue 2 Pages
179-183
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Kiyoshi KOGURE
Article type: Corner article
1993 Volume 8 Issue 2 Pages
184-191
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Akira UTSUMI, Koichi HORI, Setsuo OHSUGA
Article type: Technical paper
1993 Volume 8 Issue 2 Pages
192-200
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
This paper describes a primitive-based representation for adjective meaning. The meanings of words are roughly divided into two parts : core meaning and connotative meaning. The core meaning is independent of context, situation, and the speaker's emotions. On the other hand, the connotative meaning is strongly dependent on the speaker's emotions and feelings. However, the boundary of two parts for adjectives is less clear than for nouns or verbs. This is why most research in natural language processing has centered on the analysis of the meanings of nouns and verbs. But when natural language is regarded as a method for human communication, the analysis of adjective meaning is indispensable for natural language processing because adjectives represent human emotions, perception, and attributes of objects. We have analyzed about 700 Japanese adjectives and decomposed the meanings of these adjectives into approximately 400 semantic primitives. The essential points of this primitive-based representation are the following. 1) Core meaning is represented by one semantic primitive and connotative meaning is represented by additional primitives. Moreover, in order to clarify the differences among adjectives which have similar meanings, additional information (e.g. subjective/objective, positive/negative evaluation) is used. 2) Semantic relations between primitives are also used for representing the meaning relations among adjectives. 3) Selectional restrictions are made available for semantic disambiguation. This representation can provide much information useful for natural language processing.
View full abstract
-
Akira UTSUMI, Koichi HORI, Setsuo OHSUGA
Article type: Technical paper
1993 Volume 8 Issue 2 Pages
201-211
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
Metaphorical or figurative expressions are easily found in our daily life. Studying how to understand figurative language is necessary for the development of both cognitive science and natural language processing. This paper presents a method for understanding figurative adjective-noun combinations by using the primitive-based representation of adjectives described in our previous paper. Understanding adjective-noun phrases can be modeled as applying the adjective meaning to refine an attribute value in the prototype-represented target noun concept. Our method can interpret both literal and figurative phrases without the need for advance discrimination. Our method consists of three parts. The first part is a disambiguation algorithm for choosing among an adjective's senses. This algorithm calculates the probability for each sense of an adjective by using Dempster-Shafer Theory. If these calculated probabilities pass two criterion for ambiguity and vagueness, the phrase is determined to be literal. The second part is the interpretation of figurative adjective meaning. This can be done by two methods, one is by means of the primitive relations described in our previous paper, and the other is by topological primitive matching. Topological primitive matching is the method to select candidate primitives. Each attribute has its own two-dimensional space. All primitives are placed at the point in the space of attributes to which it corresponds. This topological representation is psychologically plausible. The third is an attribute-value mapping algorithm. This algorithm decides which attribute value to mapped when two or more candidates have same attribute. This part also handles the processing of connotative meaning. Moreover, we show that "A is (like) B" metaphors can be interpreted using the same method.
View full abstract
-
Katsuya SHIMAZAKI, Kenji OKUHATA, Ken'ichi SAKANE, Yasuo NOMURA, Yoshi ...
Article type: Technical paper
1993 Volume 8 Issue 2 Pages
212-221
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
To realize an intelligent tutor on a computer, we must clarify two types of knowledge such as a set of primitive tutoring behaviors and scheduling knowledge for tutoring. We have already formalized twenty-two tutoring strategies which are independent of the teaching materials. Those tutoring strategies are designed as primitives of appropriate grainsize. Sequences of tutoring behaviors are generated by combining one or more such primitives. Realization of sophisticated scheduling requires well-organized knowledge concerning student model, tutoring history, effects of tutoring actions taken and so on. Among them, special attention should be paid on tutoring goals. In this paper, we discuss the hierarchical structure of tutoring goals, the mechanism and the knowledge to make them operational, which properly capture the relationship among the tutoring goals, the tutoring strategies, and characteristics of the domain knowledge. Some concrete examples of the knowledge to operate tutoring strategies and the generated tutoring discourses are also presented.
View full abstract
-
Tomoki OKAMOTO, Mitsuru ISHIZUKA
Article type: Technical paper
1993 Volume 8 Issue 2 Pages
222-229
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
A hypothetical reasoning is an important knowledge system's framework because of its theoretical basis and its usefulness for practical problems including diagnosis, design, etc. The most crucial problem with the hypothetical reasoning is, however, its slow inference speed. In order to achieve practical inference speed, we present a fast inference method employing an approximate solution method of 0-1 integer programming. In this method, we regard all described knowledge as constraints. To narrow down the search space, we first find restricted knowledge relevant to the proof of a given goal. Then, we transform the restricted knowledge into inequations to apply 0-1 integer programming. While the computational complexity of hypothetical reasoning is NP-complete or NP-hard, this method allows mean-time inference speed below exponential order by relaxing the condition to find a quasioptimal solution rather than quasi-optimal one.
View full abstract
-
Masahiko ARAI
Article type: Technical paper
1993 Volume 8 Issue 2 Pages
230-234
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
We consider a sufficient condition on the number of hidden units in multilayer perceptrons for two-category classification (TCC) problems. Multilayer perceptrons considered here have one hidden layer and units take binary values. The outputs of the input units are represented by vertices of a hypercube. A sufficient number of hidden units for TCC problems is estimated by studying the number of vertices belonging to the same category and being placed between two parallel hyperplanes. We show that 2[(I(A)+2)/3]-1 or 2[(I(A)+2/3] hidden units are sufficient in the case of I(A)=3n+1, n=O,1,2,…, or I(A)≠3n+1, respectively, where I(A) means the number of input patterns belonging to category A and [x] is the largest integer not larger than x. We also show that the above result is the best one when we estimate the number of hidden units by the number of vertices placed between two parallel hyperplanes.
View full abstract
-
[in Japanese], [in Japanese]
Article type: Other
1993 Volume 8 Issue 2 Pages
235
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1993 Volume 8 Issue 2 Pages
236-238
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1993 Volume 8 Issue 2 Pages
239-241
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1993 Volume 8 Issue 2 Pages
242
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
[in Japanese]
Article type: Corner article
1993 Volume 8 Issue 2 Pages
243
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Other
1993 Volume 8 Issue 2 Pages
244
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1993 Volume 8 Issue 2 Pages
245-246
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1993 Volume 8 Issue 2 Pages
247-256
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1993 Volume 8 Issue 2 Pages
257-260
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1993 Volume 8 Issue 2 Pages
261-262
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Activity report
1993 Volume 8 Issue 2 Pages
b001-b010
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Cover page
1993 Volume 8 Issue 2 Pages
c002
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Cover page
1993 Volume 8 Issue 2 Pages
c002_2
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Table of contents
1993 Volume 8 Issue 2 Pages
i002
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS
-
Article type: Table of contents
1993 Volume 8 Issue 2 Pages
i002_2
Published: March 01, 1993
Released on J-STAGE: September 29, 2020
MAGAZINE
FREE ACCESS