• 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.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.19 no.5
• /
• pp.1129-1136
• /
• 2005

The writer reports the conclusions gained from study about the cause of the hypersensitive large intestine syndrome with Dongeuibogam as the central figure through researching the disharmony among Body Essence, Vital Energy, Mentality, and Blood, mutual action of five viscera and six bowels, and external shapes. The hypersensitive large intestine syndrome is generally chronic and recurred in many cases, so it is more efficacious than symptomatic to treat according to find the contradictions of individual shapes. The shapes and cases suffering frequently the hypersensitive large intestine syndrome are Gi-kwa and Sin-kwa, having a long nose, having a bruised spot on Triple warmer, man with inclined mouth, Taeeum type, man with congested fluids, man with colic symptoms. The hypersensitive large intestine syndrome in Oriental medicine is recognized of diarrhea, constipation, abdominal pain, abdominal distention and fullness caused by seven emotions. In Dongeuibogam it can be found out the similarity in depressive symptoms due to disorder of Gi, stagnation of Gi, dysphasia due to disorder of Gi, diarrhea due to disorder of Gi, fullness of due to Gi, diarrhea due to phlegm-retention, retention of undigested food, immoderate drinking, hypo-function of the spleen, or deficiency, abdominal pain from colic symptom, and difficulty in defecation and urination, internal injury, diarrhea due to weakness and fatigue. If the Jung, Gi, Sin, and Hyul composed the human body is broken harmony, the function of large intestinal transmission would be fallen, so similar symptoms like the hypersensitive large intestine syndrome are gotten. Especially Gi-kwa suffers diarrhea, constipation abdominal pain, and abdominal distention and fullness due to depressive symptoms from disorder of Seven emotions or Seven Gi. And Sin-kwa suffers from the hypersensitive large intestine syndrome due to emotional restlessness having an influence on rhythmic movement of abdomen. Examining between five viscera and six bowels and the hypersensitive large intestine syndrome, Liver cannot disperse well having influence on mutual relation of Liver-Large intestine, Heart reduces the function of defecation and urination not to control the seven emotions, Lung having exterior and interior relation with intestine has an influence on primordial energy and let the main symptoms occur, Spleen circulating the body fluid let the main symptoms occur due to malfunction of circulation, Kidney locating in lower part of the body has deep connection with intestine, so let the disorder. Urinary bladder is connected with intestine in moisture metabolism, Stomach is connected in receive and transmission, Small intestine is connected in absorption and excretion, from small intestine pain disturbing the abdominal movement, Samcho managing the catharsis of lower heater if declined its function causes the hypersensitive large intestine syndrome. The colic symptoms of Front private parts which disorder in lower abdomen give rise to abdominal pains, difficulty in defecation and urination due to Cold are similar to the hypersensitive large intestine syndrome. The treatments of applying the shapes of colic syndrome advocated by Master Park can be efficacious cure in clinic. Researching after the clinical cases of Master Park advocating Hyungsang medicine, we came to know that plenty of prescriptions of internal injury are applied and take good effects.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.167-183
• /
• 2023

In the recent field of recommendation systems, various studies have been conducted to model sparse data effectively. Among these, GLocal-K(Global and Local Kernels for Recommender Systems) is a research endeavor combining global and local kernels to provide personalized recommendations by considering global data patterns and individual user characteristics. However, due to its utilization of kernel tricks, GLocal-K exhibits diminished performance on highly sparse data and struggles to offer recommendations for new users or items due to the absence of side information. In this paper, to address these limitations of GLocal-K, we propose the GEase-K (Global and EASE kernels for Recommender Systems) model, incorporating the EASE(Embarrassingly Shallow Autoencoders for Sparse Data) model and leveraging side information. Initially, we substitute EASE for the local kernel in GLocal-K to enhance recommendation performance on highly sparse data. EASE, functioning as a simple linear operational structure, is an autoencoder that performs highly on extremely sparse data through regularization and learning item similarity. Additionally, we utilize side information to alleviate the cold-start problem. We enhance the understanding of user-item similarities by employing a conditional autoencoder structure during the training process to incorporate side information. In conclusion, GEase-K demonstrates resilience in highly sparse data and cold-start situations by combining linear and nonlinear structures and utilizing side information. Experimental results show that GEase-K outperforms GLocal-K based on the RMSE and MAE metrics on the highly sparse GoodReads and ModCloth datasets. Furthermore, in cold-start experiments divided into four groups using the GoodReads and ModCloth datasets, GEase-K denotes superior performance compared to GLocal-K.