• Korean Journal of Cognitive Science
• /
• v.15 no.2
• /
• pp.23-31
• /
• 2004

Latent Semantic Analysis (LSA Landauer ＆ Dumais, 1997) is a technique to represent the meanings of words using co-occurrence information of words appearing in he same context, which is usually a sentence or a document. In LSA, a word is represented as a point in multidimensional space where each axis represents a context, and a word's meaning is determined by its frequency in each context. The space is reduced by singular value decomposition (SVD). The present study elaborates upon LSA for use of representation of ambiguous words. The proposed LSA applies rotation of axes in the document space which makes possible to interpret the meaning of un. A simulation study was conducted to illustrate the performance of LSA in representation of ambiguous words. In the simulation, first, the texts which contain an ambiguous word were extracted and LSA with rotation was performed. By comparing loading matrix, we categorized the texts according to meanings. The first meaning of an ambiguous wold was represented by LSA with the matrix excluding the vectors for the other meaning. The other meanings were also represented in the same way. The simulation showed that this way of representation of an ambiguous word can identify the meanings of the word. This result suggest that LSA with axis rotation can be applied to representation of ambiguous words. We discussed that the use of rotation makes it possible to represent multiple meanings of ambiguous words, and this technique can be applied in the area of web searching.

• (The)Study of the Eastern Classic
• /
• no.67
• /
• pp.69-104
• /
• 2017

This paper examines the aspect of the novel which appeared in the union of the male and female relationship of "OkSuki", one of the novels of the 19th century. "Oksuki" is a work focusing on the relationship between men and women. It takes a narrative structure based on the relationship. It shows various aspects of the relationship through the structure in which the pluralities of plural persons are repeated. Other events and illustrations, except for the talk, are both an occasion of the alliance and an auxiliary role. At the beginning of the work, the main character's parents are described in detail.By arranging the prophecies related to the relationship between the protagonist and the brothers, it suggests that subsequent narratives will flow into the center of the relationship. The male characters that make up the alliance are characteristically trained and have a good taste, and the Caines are colorfully colored. It is believed that the marriage pattern faithfully follows the medieval status order. The reason why the figure of the person who becomes his wife and the person of the concubine are set differently is because the image of the wife and the concubine are different from each other ideally. The characters who are going to be hungry are emphasized on the clause, efficacy, knowledge, and inner peace, and are actively involved in. On the other hand, conciliatory characters emphasize talent and craftsmanship, and their role is reduced after marriage. The wife is a person who has both Confucian culture and knowledge and is able to care for her husband and family well. Concultation is shaped as a person who can enjoy joyful life and emphasize more affection in relation with his wife.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.195-204
• /
• 2023

In this study, prompt engineering that improves prompts was explored to improve the performance of teaching and learning materials recommendations using generative artificial intelligence such as GPT and Stable Diffusion. Picture materials were used as the types of teaching and learning materials. To explore the impact of the prompt composition, a Zero-Shot prompt, a prompt containing learning target grade information, a prompt containing learning goals, and a prompt containing both learning target grades and learning goals were designed to collect responses. The collected responses were embedded using Sentence Transformers, dimensionalized to t-SNE, and visualized, and then the relationship between prompts and responses was explored. In addition, each response was clustered using the k-means clustering algorithm, then the adjacent value of the widest cluster was selected as a representative value, imaged using Stable Diffusion, and evaluated by 30 elementary school teachers according to the criteria for evaluating teaching and learning materials. Thirty teachers judged that three of the four picture materials recommended were of educational value, and two of them could be used for actual classes. The prompt that recommended the most valuable picture material appeared as a prompt containing both the target grade and the learning goal.