• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.57-67
• /
• 2024

This research investigates training methods for large language models to accurately identify sentiments and comprehend information about increasing and decreasing fluctuations in the financial domain. The main goal is to identify suitable datasets that enable these models to effectively understand expressions related to financial increases and decreases. For this purpose, we selected sentences from Wall Street Journal that included relevant financial terms and sentences generated by GPT-3.5-turbo-1106 for post-training. We assessed the impact of these datasets on language model performance using Financial PhraseBank, a benchmark dataset for financial sentiment analysis. Our findings demonstrate that post-training FinBERT, a model specialized in finance, outperformed the similarly post-trained BERT, a general domain model. Moreover, post-training with actual financial news proved to be more effective than using generated sentences, though in scenarios requiring higher generalization, models trained on generated sentences performed better. This suggests that aligning the model's domain with the domain of the area intended for improvement and choosing the right dataset are crucial for enhancing a language model's understanding and sentiment prediction accuracy. These results offer a methodology for optimizing language model performance in financial sentiment analysis tasks and suggest future research directions for more nuanced language understanding and sentiment analysis in finance. This research provides valuable insights not only for the financial sector but also for language model training across various domains.

• Journal of The Korean Society of Inherited Metabolic disease
• /
• v.23 no.1
• /
• pp.25-30
• /
• 2023

Leigh syndrome is a rare progressive neurodegenerative mitochondrial disorder with clinical and genetic heterogeneity. Recently, balletic IARS2 variants have been identified in a number of patients presenting broad clinical phenotypes from Leigh and West syndrome to a rare syndrome CAGSSS characterized by cataracts, growth hormone deficiency, sensory neuropathy, sensorineural hearing loss, and skeletal dysplasia syndrome (OMIM#616007). We describe a child with Korean Leigh syndrome with urologic manifestations resulting from a compound heterozygote mutation in IARS2. A 5-year-old girl visited the emergency room with a complaint of abdominal pain accompanied by abdominal distension. Abdominal-pelvic CT showed a markedly distended urinary bladder without definite obstructive lesions. She was diagnosed with neurogenic bladder dysfunction based on a urodynamic study. She had global delayed development due to neurologic regression after 6 months of age and a history of bilateral cataract surgery at the age of 2 years. Her brain magnetic resonance imaging showed symmetrically increased signal intensities in the bilateral putamen and caudate nuclei with diffuse cerebral atrophy. No gene variants were identified through whole-mitochondrial genome analysis. Whole exome sequencing was performed for diagnosis, and compound heterozygous pathogenic variants were identified in IARS2: c.2446C>T (p. Arg816Ter) and c.2450G>A (p. Arg817His). To the best of our knowledge, this is the first case report of bladder dysfunction manifestation in a patient with IARS2-related Leigh syndrome. Thus, it broadens the clinical and genetic spectrum of IARS2-associated diseases.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.97-113
• /
• 2016

Due to the growth of internet data and the rapid development of internet technology, "big data" analysis is actively conducted to analyze enormous data for various purposes. Especially in recent years, a number of studies have been performed on the applications of text mining techniques in order to overcome the limitations of existing structured data analysis. Various studies on sentiment analysis, the part of text mining techniques, are actively studied to score opinions based on the distribution of polarity of words in documents. Usually, the sentiment analysis uses sentiment dictionary contains positivity and negativity of vocabularies. As a part of such studies, this study tries to construct sentiment dictionary which is customized to specific data domain. Using a common sentiment dictionary for sentiment analysis without considering data domain characteristic cannot reflect contextual expression only used in the specific data domain. So, we can expect using a modified sentiment dictionary customized to data domain can lead the improvement of sentiment analysis efficiency. Therefore, this study aims to suggest a way to construct customized dictionary to reflect characteristics of data domain. Especially, in this study, movie review data are divided by genre and construct genre-customized dictionaries. The performance of customized dictionary in sentiment analysis is compared with a common sentiment dictionary. In this study, IMDb data are chosen as the subject of analysis, and movie reviews are categorized by genre. Six genres in IMDb, 'action', 'animation', 'comedy', 'drama', 'horror', and 'sci-fi' are selected. Five highest ranking movies and five lowest ranking movies per genre are selected as training data set and two years' movie data from 2012 September 2012 to June 2014 are collected as test data set. Using SO-PMI (Semantic Orientation from Point-wise Mutual Information) technique, we build customized sentiment dictionary per genre and compare prediction accuracy on review rating. As a result of the analysis, the prediction using customized dictionaries improves prediction accuracy. The performance improvement is 2.82% in overall and is statistical significant. Especially, the customized dictionary on 'sci-fi' leads the highest accuracy improvement among six genres. Even though this study shows the usefulness of customized dictionaries in sentiment analysis, further studies are required to generalize the results. In this study, we only consider adjectives as additional terms in customized sentiment dictionary. Other part of text such as verb and adverb can be considered to improve sentiment analysis performance. Also, we need to apply customized sentiment dictionary to other domain such as product reviews.

• (The) Research of the performance art and culture
• /
• no.37
• /
• pp.249-293
• /
• 2018

The Musical Theatre was a popular art genre that originated from the western musical tradition represented by the European opera. In the twentieth century, it bloomed around Broadway in the United States. It is also one of the commercial arts which is popularly loved by the public in the field of performing arts all over the world at present. Due to the nature of this genre, the development of dramas and the expression of characters use music, not words or gestures, as the main medium. And the style of music reacts sensitively to the taste of the public, not to a particular class. When Japan colonized Korea, the empire strongly believed modernization equaled westernization and Japan was the one who could awaken Korean. The Japanese colonial music education was intended to bring cooperation and obedience to Japan by forcibly injecting Japanese ideology and culture into Joseon people. The music education of colonialism with the textbook of the "Songs for public education(보통교육 창가집)" compiled by the Japanese government was a sparkstone for the conversion of the Korean musical identity to Japanese and Western music. In addition to the capitalistic economical mechanism for establishing a South Korean government friendly with the United States during the Cold War after liberation, and the rush of American Pop culture represented by 'the show stage in 8th US Arm' and 'movies' which are to be the influence of invisible 'new cultural imperialism', our traditional music was confined to the meaning of 'Korean music', meaning 'past music'. In Korea, after the liberation, the musical was introduced by the influx of American popular culture. In accordance with the cultural policy of Park Jeong-hee regime, which aimed to spread the 'healthy culture' through the modernization of traditional arts, 'The Yegreen(예그린악단)' was founded. However, the plan to create a contemporary performing art based on Korean national arts showed the possibility of success in 1966 with the success of , but soon after, they have been destined to fall into an institution that has lost their ability to operate on their own due to the suspension of the sponsorship of the regime. Due to the cultural imperialist strategy of the influence of Japanese imperialism's colonial music education and influx of American popular culture after liberation, in the early days of Korean musicals, our traditional aesthetic style brought about the situation of the 1960 's, which did not become an independent ethnic art through the exchange and expansion with Western music. This is the background of the western licensed musicals led by the Korean musical market in the 21st century as well as the main cause of musical creation based on western music.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.

• (The) Research of the performance art and culture
• /
• no.23
• /
• pp.37-61
• /
• 2011

The Noh(能) performance is a traditional drama that represents Japan. The Noh performance was approved in the background of religious thought such as Shintoism(神道), Buddhisms(佛敎), and Syugendo(修驗道). Especially, the influence from Shugendo is large. Shugendo was active in the Middle Ages. Especially, the influence from Shugendo is large. Shugendo was active in the Middle Ages. The Noh was approved while receiving a large influence from Shugendo. It can know the feature of the Shugen(修驗) culture in the Middle Ages through the consideration of . Moreover, the appearance of the training of 'Yamabusi(山伏)' can be seen. "Yamabusi" has not been paid to attention up to now in the research of . And, the focus was appropriated to Yamabusi and it researched in this text. Moreover, the problem of "Chigo(稚子)" is thought through . "Chigo culture" was general in the Middle Ages. It is thought that "Chigo culture" is reflected in . is an Noh performance for the boy named 'Wakamatsu' to enter the mountain and to train. It is because mother's sickness was cured. However, the boy gets sick while it is training. It was dropped to the valley according to the law of Shugendo, and it died. However, it revives by the Yamabusi's prayers. 'Taniko' is to drop to the valley and to bury it when the Yamabusi gets sick while lived. The title of the Noh originated in here. has elements of history, content of training of Shugendo, "Filial piety", and the Chigo culture, etc. These are features of the culture in the Middle Ages. It is not only a sad content though this is a content of the cruel remainder. It is because of the revival though waited rapidly at the end. As for the difficulty of training is drawn in the round, and the appearance of the training at that time is understood well. The essence of Shugendo is to train in the mountain. Supernatural power can be obtained through training. Moreover, it was thought that it was able to be newly reborn through training. The leading part of Shugendo is an Yamabusi. The Yamabusi took an active part in not only the mountain but also the village. The Yamabusi is ordinary people's lives and because the relation is deep, an important factor it knows the folk customs of Japan. The word 'Chigo' is not written in . However, a spectator at that time is 'Chigo' Wakamatsu and is already sure to have understood 'Chigo'. Because everyone knew the Chigo culture in the Middle Ages. A religion at that time and knowledge of the society are necessary to understand the play of Nho well.

• Sim-seong Yeon-gu
• /
• v.28 no.1
• /
• pp.50-87
• /
• 2013

C. G. Jung believed that universal and basic condition of human's Unconscious comes out from Märchen or mythology. We can easily experience these universality of human nature in dreams. Therefore, It is very important to interpret mythogens that appear in myths and märchen in analytical psychology to understand these 'big dreams' which could be seen in clinical practice. As I was interested in interpreting myths in analytic psychology, I tried to find universality of archetypes in Korea's traditional folk tales and took note of the birth myth of Hyeokgeose, the founder of Shilla dynasty, while examining the chater of the Unsual in history in the Heritage of the Three Kingdoms. Shilla was founded earlier than two other countries, but it was located in the very south of the Korean Peninsula, and it was behind times in politically, militarily, and culturally compare to Goguryeo and Baekje. However, Shilla achieved unifying the Three Kingdoms and it lasted 1000 years, the longest unified history in Korean history. I tried to examine archetypes in the birth myth if there are any backgrounds that are related to finding a Shilla Kingdom. It is noted that myth of the founder of Korean Peninsula's small Kingdom Shilla has complete story from before the birth to birth, birth of spouse, growth, marriage, accession, governing, death, after death, and succession. Symbols such as numbers 1, 3, 5, 6, 7, 13 and 61, various azimuthes including north, west, south, east, and central, animals like tiger, white horse, hen, dragon, phoenix, and snakes, natures like main symbol egg, rock, gourd, lightening, spring water, stream, tree, forest, mountain, iron and goddess-image like seon-do Holy Mother gradually appears in the myth. These symbols could show a meaning of human experience such as birth of Conscious, growth and development of paternal and maternal love, and story of regeneration and extinction. Moreover, It could be seen as these progress eternally continues in next generation. I have found out that a word, a sentence or stories that looks meaningless in myth revealed its true symbolical meaning. In addition, interaction between Unconscious and Conscious repeats in different forms, and expressed in layered.