Image estimation of words based on adjective co‐occurrences

Abstract

SUMMARYIn natural language, words convey various impressions such as "kurai (dark)-akarui (bright)" or "kitanai (dirty)-utsukushii (beautiful)." Impressions play an important role in inferring the speaker's intentions or feelings. Systems that use natural language to support conceptualization or retrieve information by teaching the computer the impressions of words are growing significantly. Therefore, in this paper, the authors propose a technique for estimating the impressions or images that words convey. The proposed technique consists of two processes: similarity measurement and spatial positioning. Similarity measurement uses the enormous amount of text on the Internet to obtain similarities by measuring the co-occurrence frequency of words. Co-occurrence conditions, which are limited to the joint co-occurrences of adjectives or adjectival nouns, are applied to image estimation. Spatial positioning positions words in space by quantifying the similarities that were obtained according to images. The authors used a simulation of an electrical circuit for quantification. The results of evaluation experiments verified that the proposed system could estimate the images of words with high precision. It was also apparent that the proposed system could estimate the images with sufficient precision even for words that were difficult to analyze because of the insufficient number of samples in an existing corpus, including new words and colloquial words or slang.

Musical expression generation in several music genres by fuzzy rules

“…In a score + 1 : performing note for a longer length than the note value in a score (7) And LengthBase is the parameter showing the change of the note length from the note value in a score having a value in [1.5, 10.0]. LengthRatei, the deviation rate of length of every note at LengthBase = 1.0, is defined by Eq.…”

“…An inputted image word is mapped into a Kansei space and the coordinates values in this Kansei space are obtained through the image estimation procedure according to [7], [8]. Hereafter, the image estimation procedure is explained by taking example of estimation of coordinates values on the elegant factor axis for image word Bright.…”

Construction of English composition support system based on conveying emotion

“…web search API [10] was used for our method. As the method for relevance calculation between keywords Shimizu [11] et al, proposed a co-occurrence coefficient using the frequency of each word and the co-occurrence frequency of the two words. This method used the co-occurrence frequency of adjective/adjectival noun and noun as a co-occurrence condition of each word.…”

Phrase animation generation based on impressions of phrase motion and color scheme

“…Impressions Factors of Color Scheme 1) Subject experiments: Subject experiments are performed in order to obtain the structure of impressions factors given by the color schemes. In the experiments, 300 kinds of color schemes are presented to subjects, which consist of phrase color and background color based on Munsell color system [1], and subjects evaluate each color scheme using 36 kinds of pairs of impression words and 5-points scale, where these impression words are chosen referring to [10] and [11]. The number of subjects is 12, all in twenties, and each subject evaluates 50 color schemes.…”

“…A phrase animation is one kind of kinetic typography that introduces motion to phrases through CG animation, and gives intuitive impressions of a phrase by the use of this phrase's motion. Although studies on the generation of a kinetic typography have also been performed [8][9][10], many of these studies consider only phrase motion. With the introduction of a color scheme to a kinetic typography, it is necessary to consider impressions of both phrase motion and color since it is not only phrase motion but also phrase color scheme that have an influence on the impressions of a phrase animation.…”