• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.35 no.5
• /
• pp.20-26
• /
• 2017

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.172-175
• /
• 2018

환자의 병력을 서술하는 임상문서에서 임상 개체명들은 그들 사이에 개체명이 아닌 단어들이 위치하기 때문에 거리상으로 서로 떨어져 있고, 임상 개체명인식에 많이 사용되는 조건부무작위장(conditional random fields; CRF) 모델은 Markov 속성을 따르기 때문에 서로 떨어져 있는 개체명 라벨 간의 전이 정보는 모델의 계산에서 무시된다. 본 논문에서는 라벨링 모델에 서로 떨어진 개체명 간 전이 관계를 표현하기 위하여 CRF 모델의 구조를 변경하는 방법론을 소개한다. 제안된 CRF 모델 디자인에서는 모델의 계산효율성을 빠르게 유지하기 위하여 Markov 속성을 유지하는 1차 모델 구조를 유지한다. 모델은 선행하는 개체명의 라벨 정보를 후행하는 개체명 엔터티에게 전달하기 위하여 선행 개체명의 라벨을 뒤 따르는 비개체명 라벨에 전이시키고 이를 통해 후행하는 개체명은 선행하는 개체명의 라벨 정보를 알 수 있게 된다. 라벨의 고차 전이 정보를 전달함에도 모델의 구조는 1차 전이 구조를 유지함으로 n차 구조의 모델보다 빠른 계산 속도를 유지할 수 있게 된다. 모델의 성능 평가를 위하여 서울대학교병원 류머티즘내과에서 퇴원한 환자들의 퇴원요약지에 병력과 관련된 엔터티가 태깅된 평가 데이터와 i2b2 2012/VA 임상자연어처리 shared task의 임상 개체명 추출 데이터를 사용하였고 기본 CRF 모델들(1차, 2차)과 비교하였다. 피처 조합에 따라 모델들을 평가한 결과 제안한 모델이 거의 모든 경우에서 기본 모델들에 비하여 F1-score의 성능을 향상시킴을 관찰할 수 있었다.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.365-372
• /
• 2021

The purpose of this study was to examine the statements characteristics of the pressure ulcer nursing record by natural langage processing and assess the prediction accuracy for each pressure ulcer stage. Nursing records related to pressure ulcer were analyzed using descriptive statistics, and word cloud generators (http://wordcloud.kr) were used to examine the characteristics of words in the pressure ulcer prevention nursing records. The accuracy ratio for the pressure ulcer stage was calculated using deep learning. As a result of the study, the second stage and the deep tissue injury suspected were 23.1% and 23.0%, respectively, and the most frequent key words were erythema, blisters, bark, area, and size. The stages with high prediction accuracy were in the order of stage 0, deep tissue injury suspected, and stage 2. These results suggest that it can be developed as a clinical decision support system available to practice for nurses at the pressure ulcer prevention care.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.362-365
• /
• 2021

이 논문에서는 자연어로 구성된 수학 문장제 문제를 자동으로 풀이하기 위한 Transformer 기반의 생성 모델인 KoEPT를 제안한다. 수학 문장제 문제는 일상 상황을 수학적 형식으로 표현한 자연어 문제로, 문장제 문제 풀이 기술은 실생활에 응용 가능성이 많아 국내외에서 다양하게 연구된 바 있다. 한국어의 경우 지금까지의 연구는 문제를 유형으로 분류하여 풀이하는 기법들이 주로 시도되었으나, 이러한 기법은 다양한 수식을 포괄하여 분류 난도가 높은 데이터셋에 적용하기 어렵다는 한계가 있다. 본 논문은 이를 해결하기 위해 우선 현존하는 한국어 수학 문장제 문제 데이터셋인 CC, IL, ALG514의 분류 난도를 측정한 후 5겹 교차 검증 기법을 사용하여 KoEPT의 성능을 평가하였다. 평가에 사용된 한국어 데이터셋들에 대하여, KoEPT는 CC에서는 기존 최고 성능과 대등한 99.1%, IL과 ALG514에서 각각 89.3%, 80.5%로 새로운 최고 성능을 얻었다. 뿐만 아니라 평가 결과 KoEPT는 분류 난도가 높은 데이터셋에 대해 상대적으로 개선된 성능을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.550-551
• /
• 2018

바이오마커는 체내의 상태 및 변화를 파악할 수 있는 지표이다. 이는 암을 비롯한 다양한 질병에 대하여 진단하는데 활용도가 높은 것으로 알려져 있으나, 새로운 바이오마커를 찾아내기 위한 임상 실험은 많은 시간과 비용을 소비되며, 모든 바이오마커가 실제 질병을 진단하는데 유용하게 사용되는 것은 아니다. 따라서 본 연구에서는 자연어처리 기술을 활용해 바이오마커를 발굴할 때 요구되는 많은 시간과 비용을 줄이고자 한다. 이 때 다양한 의미를 가진 어휘들이 해당 질병과 연관성이 높은 것으로 나타나며, 이들을 분류하는 것은 매우 어렵다. 따라서 우리는 Word2Vec과 가우시안 혼합 모델을 사용하여 바이오마커를 분류하고자 한다. 실험 결과, 대다수의 바이오마커 어휘들이 하나의 군집에 나타나는 것을 확인할 수 있었다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.315-324
• /
• 2022

In this paper, we propose KoEPT, a Transformer-based generative model for automatic math word problems solving. A math word problem written in human language which describes everyday situations in a mathematical form. Math word problem solving requires an artificial intelligence model to understand the implied logic within the problem. Therefore, it is being studied variously across the world to improve the language understanding ability of artificial intelligence. In the case of the Korean language, studies so far have mainly attempted to solve problems by classifying them into templates, but there is a limitation in that these techniques are difficult to apply to datasets with high classification difficulty. To solve this problem, this paper used the KoEPT model which uses 'expression' tokens and pointer networks. To measure the performance of this model, the classification difficulty scores of IL, CC, and ALG514, which are existing Korean mathematical sentence problem datasets, were measured, and then the performance of KoEPT was evaluated using 5-fold cross-validation. For the Korean datasets used for evaluation, KoEPT obtained the state-of-the-art(SOTA) performance with 99.1% in CC, which is comparable to the existing SOTA performance, and 89.3% and 80.5% in IL and ALG514, respectively. In addition, as a result of evaluation, KoEPT showed a relatively improved performance for datasets with high classification difficulty. Through an ablation study, we uncovered that the use of the 'expression' tokens and pointer networks contributed to KoEPT's state of being less affected by classification difficulty while obtaining good performance.

• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.109-131
• /
• 2014

As the demand of nuclear power plant equipment is continuously growing worldwide, the importance of handling nuclear strategic materials is also increasing. While the number of cases submitted for the exports of nuclear-power commodity and technology is dramatically increasing, preadjudication (or prescreening to be simple) of strategic materials has been done so far by experts of a long-time experience and extensive field knowledge. However, there is severe shortage of experts in this domain, not to mention that it takes a long time to develop an expert. Because human experts must manually evaluate all the documents submitted for export permission, the current practice of nuclear material export is neither time-efficient nor cost-effective. Toward alleviating the problem of relying on costly human experts only, our research proposes a new system designed to help field experts make their decisions more effectively and efficiently. The proposed system is built upon case-based reasoning, which in essence extracts key features from the existing cases, compares the features with the features of a new case, and derives a solution for the new case by referencing similar cases and their solutions. Our research proposes a framework of case-based reasoning system, designs a case-based reasoning system for the control of nuclear material exports, and evaluates the performance of alternative keyword extraction methods (full automatic, full manual, and semi-automatic). A keyword extraction method is an essential component of the case-based reasoning system as it is used to extract key features of the cases. The full automatic method was conducted using TF-IDF, which is a widely used de facto standard method for representative keyword extraction in text mining. TF (Term Frequency) is based on the frequency count of the term within a document, showing how important the term is within a document while IDF (Inverted Document Frequency) is based on the infrequency of the term within a document set, showing how uniquely the term represents the document. The results show that the semi-automatic approach, which is based on the collaboration of machine and human, is the most effective solution regardless of whether the human is a field expert or a student who majors in nuclear engineering. Moreover, we propose a new approach of computing nuclear document similarity along with a new framework of document analysis. The proposed algorithm of nuclear document similarity considers both document-to-document similarity (${\alpha}$) and document-to-nuclear system similarity (${\beta}$), in order to derive the final score (${\gamma}$) for the decision of whether the presented case is of strategic material or not. The final score (${\gamma}$) represents a document similarity between the past cases and the new case. The score is induced by not only exploiting conventional TF-IDF, but utilizing a nuclear system similarity score, which takes the context of nuclear system domain into account. Finally, the system retrieves top-3 documents stored in the case base that are considered as the most similar cases with regard to the new case, and provides them with the degree of credibility. With this final score and the credibility score, it becomes easier for a user to see which documents in the case base are more worthy of looking up so that the user can make a proper decision with relatively lower cost. The evaluation of the system has been conducted by developing a prototype and testing with field data. The system workflows and outcomes have been verified by the field experts. This research is expected to contribute the growth of knowledge service industry by proposing a new system that can effectively reduce the burden of relying on costly human experts for the export control of nuclear materials and that can be considered as a meaningful example of knowledge service application.