• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.278-284
• /
• 2003

Speech act is the speaker's intentions indicated through utterances. It is important for understanding natural language dialogues and generating responses. This paper proposes the method of two stage that increases the performance of the korean speech act decision. The first stage is to select features from the part of speech results in sentence and from the context that uses previous speech acts. We use x$^2$ statistics(CHI) for selecting features that have showed high performance in text categorization. The second stage is to determine speech act with selected features and Neural Network. The proposed method shows the possibility of automatic speech act decision using only POS results, makes good performance by using the higher informative features and speed up by decreasing the number of features. We tested the system using our proposed method in Korean dialogue corpus transcribed from recording in real fields, and this corpus consists of 10,285 utterances and 17 speech acts. We trained it with 8,349 utterances and have test it with 1,936 utterances, obtained the correct speech act for 1,709 utterances(88.3%). This result is about 8% higher accuracy than without selecting features.

• Journal of Korean Biological Nursing Science
• /
• v.4 no.2
• /
• pp.79-92
• /
• 2002

This study was aimed to analyze the variables measuring stress and immune responses, to identify the relationship between stress and immune responses, and to find out the effect of nursing interventions associated with stress and immune responses by reviewing thirty-four published articles since 1970 in Korea. The articles were selected in the field of nursing, stress management, and masters or doctoral dissertations and limited to human subject. Among these, the thirty-one articles were published since 1996 and mainly distributed in nursing (44.1%) and medicine(44.1%). The prevailing research design was nonequivalent control pre-post experimental design(41.1%). The research subjects were 55.9% for patients and 44.1% for healthy general persons including 20.6% of university students. To evaluate stress, both physiologic and psychosocial measures were adapted together in 35.3% of the articles. The most frequent two variables measuring stress and immune response were cortisol level(15.9%) and number or activity of natural killer cell(25.9%). The relation between stress and immune responses was positive in 4 articles, negative in 9 cases, and none in 12 cases. Decreased stress and enhanced immune function have been found when massage, abdominal breathing, exercise, relaxation, and touch were provided as nursing interventions. The articles to investigate the relationship between stress and immune function were limited and the tested variables were diverse. Also there was no consistent evidence to correlate the stress and immune function at present. Further studies are needed to construct a valid research design and to investigate the relationship between stress and immune responses. Nursing interventions to decrease stress should be developed to result in the increased immune function and the effect of these interventions would be verified.

• Communications of Mathematical Education
• /
• v.34 no.1
• /
• pp.1-15
• /
• 2020

Today's healthcare, intelligent robots, smart home systems, and car sharing are already innovating with cutting-edge information and communication technologies such as Artificial Intelligence (AI), the Internet of Things, the Internet of Intelligent Things, and Big data. It is deeply affecting our lives. In the factory, robots have been working for humans more than several decades (FA, OA), AI doctors are also working in hospitals (Dr. Watson), AI speakers (Giga Genie) and AI assistants (Siri, Bixby, Google Assistant) are working to improve Natural Language Process. Now, in order to understand AI, knowledge of mathematics becomes essential, not a choice. Thus, mathematicians have been given a role in explaining such mathematics that make these things possible behind AI. Therefore, the authors wrote a textbook 'Basic Mathematics for Artificial Intelligence' by arranging the mathematics concepts and tools needed to understand AI and machine learning in one or two semesters, and organized lectures for undergraduate and graduate students of various majors to explore careers in artificial intelligence. In this paper, we share our experience of conducting this class with the full contents in http://matrix.skku.ac.kr/math4ai/.

• Journal of Internet Computing and Services
• /
• v.21 no.1
• /
• pp.127-135
• /
• 2020

As the importance of the use and analysis of big data is emerging, there is a growing interest in natural language processing techniques for unstructured data such as news articles and comments. Particularly, as the collection of big data becomes possible, data mining techniques capable of pre-processing and analyzing data are emerging. In this case study with a telecom company, we propose a methodology how to formalize unstructured data using text mining. The domain is determined as equipment failure and the data is about 2.2 million equipment check ledger data. Data on equipment failures by 800,000 per year is accumulated in the equipment check ledger. The equipment check ledger coexist with both formal and unstructured data. Although formal data can be easily used for analysis, unstructured data is difficult to be used immediately for analysis. However, in unstructured data, there is a high possibility that important information. Because it can be contained that is not written in a formal. Therefore, in this study, we study to develop digital transformation method for unstructured data in equipment check ledger.

• The Journal of Society for e-Business Studies
• /
• v.25 no.1
• /
• pp.13-33
• /
• 2020

This study proposes a Korean sentimental analysis algorithm that utilizes a letter-unit embedding and convolutional neural networks. Sentimental analysis is a natural language processing technique for subjective data analysis, such as a person's attitude, opinion, and propensity, as shown in the text. Recently, Korean sentimental analysis research has been steadily increased. However, it has failed to use a general-purpose sentimental dictionary and has built-up and used its own sentimental dictionary in each field. The problem with this phenomenon is that it does not conform to the characteristics of Korean. In this study, we have developed a model for analyzing emotions by producing syllable vectors based on the onset, peak, and coda, excluding morphology analysis during the emotional analysis procedure. As a result, we were able to minimize the problem of word learning and the problem of unregistered words, and the accuracy of the model was 88%. The model is less influenced by the unstructured nature of the input data and allows for polarized classification according to the context of the text. We hope that through this developed model will be easier for non-experts who wish to perform Korean sentimental analysis.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.3
• /
• pp.245-251
• /
• 2020

From the perspectives of grammaticalization and corpus, the purpose of this study is to examine the motivation of the emergence of the split infinitives in American English and to discuss the justification of the split infinitives based on the corpus empirical data such as COHA and COCA. The formerly ungrammatical split infinitives in the form of [to + adverb + verb] are now definitely grammatical forms in Present Day English (PDE). The corpus-based data confirms the legitimacy of the split infinitives with the empirical reasons like clarifying sentences (i.e., disambiguation) or strongly focused readings. In addition, the split infinitives are natural consequences caused by the grammaticalization of an infinitival particle to and most crucially by the loss of verb movement. When verb movement to T position does not occur in infinitival clauses, the word order results in [to + AdvP + V], thus forming the split infinitives. The split infinitives are no longer a matter of discussion and will continue to increase in both formal and informal contexts as being definitely grammatical forms.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.24 no.2
• /
• pp.107-111
• /
• 2013

Objectives : We developed two-dimensional (2D) scanning videokyomography to evaluate the mucosal wave of whole vocal cords in real time to overcome the limit of preexisting stroboscopy and line scanning videokymography which could not evaluate it. Methods : We implemented a continuous light source with high brightness, a high-definition CMOS camera, and capture board for saving the data. We created the software program to analyze the image data from the system. The test of the functionality of the 2D scanning videokymography camera was performed in one of the authors (P.H.J 32 years old male). Vocal cord images were obtained during normal phonation and falsetto phonation. Images were obtained also during cough, diplophonia. Results : The system made it possible to measure objective parameters, including fundamental frequency, amplitude, regularity, mucosal wave, and phase difference, medial and lateral peak, opening versus closing duration related to vocal fold vibration. Simultaneously, it enabled analysis of the whole mucosal wave of the entire vocal fold in real time. 2D scanning videokymography was also effective for evaluating the dynamic status of the vocal fold when the subject phonated aperiodic voice. Conclusion : In conclusion, 2D scanning videokymography can support the analysis of the whole mucosal wave of the entire vocal cord with objective vocal parameters, overcoming the limitations of stroboscopy and previous line scanning videokymography techniques.

• The Journal of Korean Association of Computer Education
• /
• v.14 no.2
• /
• pp.83-94
• /
• 2011

In the biomedical domain, the longest matching method is frequently used for recognizing named entity written in the literature. This method uses a dictionary as a resource for named entity recognition. If there exist appropriated dictionary about target domain, the longest matching method has the advantage of being able to recognize the entities of target domain quickly and exactly. However, the longest matching method is difficult to recognize the enumerated named entities, because these entities are frequently expressed as being omitted some words. In order to resolve this problem, we propose the partial matching method using a dictionary. The proposed method makes several candidate entities on the assumption that the ellipses may be included. After that, the method selects the most valid one among candidate entities through the optimization algorithm. We tested the longest and partial matching method about HLA entities: HLA gene, antigen, and allele entities, which are frequently enumerated among biomedical entities. As preparing for named entity recognition, we built two new resource, extended dictionary and tag-based dictionary about HLA entities. And later, we performed the longest and partial matching method using each dictionary. According to our experiment result, the longest matching method was effective in recognizing HLA antigen entities, in which the ellipses are rare, and the partial matching method was effective in recognizing HLA gene and allele entities, in which the ellipses are frequent. Especially, the partial matching method had a high F-score 95.59% about HLA alleles.

• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.2
• /
• pp.3-12
• /
• 2017

Leaving positive or negative comments of places where he or she visits on location-based services is being common in daily life. The sentiment analysis of place reviews written by actual visitors can provide valuable information to potential consumers, as well as business owners. To conduct sentiment analysis of a place, a spatial sentiment lexicon that can be used as a criterion is required; yet, lexicon of spatial sentiment words has not been constructed. Therefore, this study suggested a method to construct a spatial sentiment lexicon by analyzing the place review data written by Korean internet users. Among several location categories, theme parks were chosen for this study. For this purpose, natural language processing technique and statistical techniques are used. Spatial sentiment words included the lexicon have information about sentiment polarity and probability score. The spatial sentiment lexicon constructed in this study consists of 3 tables(SSLex_SS, SSLex_single, SSLex_combi) that include 219 spatial sentiment words. Throughout this study, the sentiment analysis has conducted based on the texts written about the theme parks created on Twitter. As the accuracy of the sentiment classification was calculated as 0.714, the validity of the lexicon was verified.

• Journal of KIISE:Software and Applications
• /
• v.32 no.5
• /
• pp.406-415
• /
• 2005

Prosperity of Internet led to the web containing huge number of documents. Thus increasing importance is given to the web information retrieval technology that can provide users with documents that contain the right information they want. This paper proposes several techniques that are effective for the improvement of web information retrieval. Similarity between a document and the query is a major source of information exploited by conventional systems. However, we suggest a technique to make use of similarity between a sentence and the query. We introduce a technique to compute the approximate score of the sentence-query similarity even without a mature technology of natural language processing. It was shown that the amount of computation for this task is linear to the number of documents in the total collection, which implies that practical systems can make use of this technique. The next important technique proposed in this paper is to use stratification of documents in re-ranking the documents to output. It was shown that it can lead to significant improvement in performance. We furthermore showed that using hyper links, anchor texts, and titles can result in enhancement of performance. To justify the proposed techniques we developed a large scale web information retrieval system and used it for experiments.