• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.303-310
• /
• 2007

Named Entity Recognition (NER) is always limited by its lower recall resulting from the asymmetric data distribution where the NONE class dominates the entity classes. This paper presents an approach that exploits non-local information to improve the NER recall. Several kinds of non-local features encoding entity token occurrence, entity boundary and entity class are explored under Conditional Random Fields (CRFs) framework. Experiments on SIGHAN 2006 MSRA (CityU) corpus indicate that non-local features can effectively enhance the recall of the state-of-the-art NER systems. Incorporating the non-local features into the NER systems using local features alone, our best system achieves a 23.56% (25.26%) relative error reduction on the recall and 17.10% (11.36%) relative error reduction on the F1 score; the improved F1 score 89.38% (90.09%) is significantly superior to the best NER system with F1 of 86.51% (89.03%) participated in the closed track.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.14-19
• /
• 2016

본 논문은 문장에서의 어절 간 의존관계가 성립될 때 의존소와 지배소가 어떠한 관계를 가지는지 의존 관계명을 부착하는 모델을 제안한다. 국내에서 한국어 의존구문분석에 관한 연구가 활발히 진행되고 있지만 의존 관계만을 결과로 제시하고 의존 관계명을 제공하지 않는 경우가 많았다. 따라서 본 논문에서는 의존 경로(Dependency Path)와 음절의 의존 관계명 분포를 반영하는 음절 임베딩를 이용한 의존 관계명 부착 모델을 제안한다. 문장에서 나올 수 있는 최적의 입력 열인 의존 경로(Dependency Path)를 순차 레이블링에서 좋은 성능을 나타내고 있는 bidirectional LSTM-CRFs의 입력 값으로 사용하여 의존 관계명을 결정한다. 제안된 기법은 자질에 대한 많은 노력 없이 의존 경로에 따라 어절 및 음절 단어표상(word embedding)만을 사용하여 순차적으로 의존 관계명을 부착한다. 의존 경로를 사용하지 않고 전체 문장의 어절 순서를 바탕으로 자질을 추출하여 CRFs로 분석한 기존 모델보다 의존 경로를 사용했을 때 4.1%p의 성능향상을 얻었으며, 의존 관계명 분포를 반영하는 음절 임베딩을 사용한 bidirectional LSTM-CRFs는 의존 관계명 부착에 최고의 성능인 96.01%(5.21%p 개선)를 내었다.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.321-323
• /
• 2016

최근 연구에서 기계학습 중 지도학습 방법으로 개체명 인식을 하고 있다. 그러나 지도 학습 방법은 데이터를 만드는 비용과 시간이 많이 필요로 한다. 본 연구에서는 주석 된 말뭉치를 사용하여 지도 학습 방법을 사용 한다. 의생명 개체명 인식은 Protein, RNA, DNA, Cell type, Cell line 등을 포함한 텍스트 처리에 중요한 기초 작업입니다. 그리고 의생명 지식 검색에서 가장 기본과 핵심 작업 중 하나이다. 본 연구에서는 순환형 신경망과 워드 임베딩을 자질로 사용한 조건적 임의 필드에 대한 성능을 비교한다. 조건적 임의 필드에 N_Gram만을 자질로 사용한 것을 기준점으로 설정 하였고, 기준점의 결과는 70.09% F1 Score이다. RNN의 jordan type은 60.75% F1 Score, elman type은 58.80% F1 Score의 성능을 보여준다. 조건적 임의 필드에 CCA, GLOVE, WORD2VEC을 사용 한 결과는 각각 72.73% F1 Score, 72.74% F1 Score, 72.82% F1 Score의 성능을 얻을 수 있다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.1
• /
• pp.82-91
• /
• 2009

Sign language spotting is the task of detecting and recognizing the signs in a signed utterance. The difficulty of sign language spotting is that the occurrences of signs vary in both motion and shape. Moreover, the signs appear within a continuous gesture stream, interspersed with transitional movements between signs in a vocabulary and non-sign patterns(which include out-of-vocabulary signs, epentheses, and other movements that do not correspond to signs). In this paper, a novel method for designing a threshold model in a conditional random field(CRF) model is proposed. The proposed model performs an adaptive threshold for distinguishing between signs in the vocabulary and non-sign patterns. A hand appearance-based sign verification method, a short-sign detector, and a subsign reasoning method are included to further improve sign language spotting accuracy. Experimental results show that the proposed method can detect signs from continuous data with an 88% spotting rate and can recognize signs from isolated data with a 94% recognition rate, versus 74% and 90% respectively for CRFs without a threshold model, short-sign detector, subsign reasoning, and hand appearance-based sign verification.

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.47-52
• /
• 2018

Named Entity Recognition is a system that extracts entity names such as Persons(PS), Locations(LC), and Organizations(OG) that can have a unique meaning from a document and determines the categories of extracted entity names. Recently, Bi-LSTM-CRF, which is a combination of CRF using the transition probability between output data from LSTM-based Bi-LSTM model considering forward and backward directions of input data, showed excellent performance in the study of object name recognition using deep-learning, and it has a good performance on the efficient embedding vector creation by character and word unit and the model using CNN and LSTM. In this research, we describe the Bi-LSTM-CNN-CRF model that enhances the features of the Korean named entity recognition system and propose a method for constructing the traditional culture corpus. We also present the results of learning the constructed corpus with the feature augmentation model for the recognition of Korean object names.

• Journal of the Korea Convergence Society
• /
• v.9 no.1
• /
• pp.233-240
• /
• 2018

The aim of this study was to investigate the cardiometabolic risk factors (CRF) of community dwelling women based on a combination of body mass index (BMI) and waist circumference (WC). This cross-sectional study was based on 1,447 subjects between 30 and 60 years of age. Subjects were categorized into 4 groups by BMI and WC [group 1, BMI<$25kg/m^2$ and WC<85 cm; group 2, BMI<$25kg/m^2$ and WC>85 cm; group 3, BMI>$25kg/m^2$ and WC<85 cm; and group 4 (BMI>$25kg/m^2$ and WC>85 cm. Logistic regression analyses showed that subjects in group 2 had 1.75 times increased risk of clustering of 2 or more CRFs compared with subjects in group 1 (p<0.001). In conclusion, early detection of people with normal weight but high waist circumference may prevent them from getting worse by implementation of lifestyle intervention, consisting of regular exercise and healthy eating. In addition, further studies on appropriate exercise contents for them should be examined.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.555-562
• /
• 2016

Semantic Role Labeling (SRL) is to determine the semantic relation of a predicate and its argu-ments in a sentence. But Korean semantic role labeling has faced on difficulty due to its different language structure compared to English, which makes it very hard to use appropriate approaches developed so far. That means that methods proposed so far could not show a satisfied perfor-mance, compared to English and Chinese. To complement these problems, we focus on suffix information analysis, such as josa (case suffix) and eomi (verbal ending) analysis. Korean lan-guage is one of the agglutinative languages, such as Japanese, which have well defined suffix structure in their words. The agglutinative languages could have free word order due to its de-veloped suffix structure. Also arguments with a single morpheme are then labeled with statistics. In addition, machine learning algorithms such as Support Vector Machine (SVM) and Condi-tional Random Fields (CRF) are used to model SRL problem on arguments that are not labeled at the suffix analysis phase. The proposed method is intended to reduce the range of argument instances to which machine learning approaches should be applied, resulting in uncertain and inaccurate role labeling. In experiments, we use 15,224 arguments and we are able to obtain approximately 83.24% f1-score, increased about 4.85% points compared to the state-of-the-art Korean SRL research.

• Journal of Life Science
• /
• v.23 no.2
• /
• pp.228-236
• /
• 2013

This study was aimed at investigating whether dietary therapy using medicinal enzyme powder is effective in reducing constipation caused by loperamide in rats. Nine-week-old male Sprague Dawley were subdivided into 4 groups: normal diet group (C), loperamide treatment and normal diet (CL), medicinal enzyme powder diet (E), and loperamide treatment and medicinal enzyme powder diet (EL). Constipation was induced by subcutaneous injection of loperamide (1.5 mg/kg) 3 days prior to sacrifice. The treatment with loperamide led to an increase in weight gain, a decrease in the number and wet weight of fecal pellets, and a decrease in intestinal motility. The administration of the medicinal enzyme powder significantly reduced weight gain but increased intestinal mobility compared with the loperamide-treated group. The treatment with loperamide in the normal diet group reduced the activities of both suggesting that constipation may be involved in the low level of glutamic oxaloacetic transaminase (GOT) and glutamic pyruvic transaminase (GPT). Additionally, the loperamide treatment in the medicinal enzyme powder diet group increased the level of GOT, but reduced the level of GPT. Loperamide treatment also reduced cholesterol and increased the atherogenic index (AI) and cardiac risk factors (CRFs). Interestingly, the treatment with the medicinal enzyme powder effectively attenuated both the increase in AI and the reduction in high density lipopretein (HDL)-cholesterol, caused by the treatment with loperamide. Although there were no significant differences in the blood protein level, including hemoglobin and hematocrit, between the normal diet group and the loperamide-treated group, the administration of the medicinal enzyme powder to the loperamide-treated group effectively increased the levels of both hemoglobin and hematocrit. Collectively, the results demonstrate that the medicinal enzyme powder can help to combat the negative events caused by constipation.