• Korean Journal of Cognitive Science
• /
• v.18 no.1
• /
• pp.1-14
• /
• 2007

In a goal-oriented dialogue, speakers' intentions can be represented by domain actions that consist of pairs of a speech act and a concept sequence. Therefore, if we plan to implement an intelligent dialogue system, it is very important to correctly infer the domain actions from surface utterances. In this paper, we propose a statistical model to determine speech acts and concept sequences using conditional random fields at the same time. To avoid biased learning problems, the proposed model uses low-level linguistic features such as lexicals and parts-of-speech. Then, it filters out uninformative features using the chi-square statistic. In the experiments in a schedule arrangement domain, the proposed system showed good performances (the precision of 93.0% on speech act classification and the precision of 90.2% on concept sequence classification).

• Annual Conference on Human and Language Technology
• /
• 2008.10a
• /
• pp.58-62
• /
• 2008

인터넷 상에서 상품을 구입할 때 고려하는 부분 중의 하나가 상품평이다. 하지만 이러한 상품평들을 개인이 일일이 확인 하는데에는 상당한 시간이 소요된다. 이러한 문제점을 줄이기 위해서 본 논문에서는 인터넷 상의 상품평에 대한 의견을 긍정, 부정, 일반으로 나누는 시스템을 제안한다. 제안 시스템은 CRFs 기계학습모델을 기반으로 하며, 연결어미, 형태소 유니그램, 슬라이딩 윈도우 기법의 형태소 바이그램을 자질로 사용한다. 실험을 위해서 가격비교 사이트의 모니터 카테고리에서 561개의 상품평을 수집하였다. 이 중 465개의 상품평을 학습 문서로 사용하였고 96개의 상품평을 실험 문서로 사용하였다. 제안 시스템은 실험결과 79% 정도의 정확도를 보였다. 추가 실험으로 제안 시스템이 사람들과 얼마나 비슷한 성능을 보이는지 알아보기 위해서 카파 테스트를 실시하였다. 카파 테스트를 실시한 결과, 사람간의 카파 계수는 0.6415였으며, 제안 시스템과 사람 간의 카파 계수는 평균 0.5976이였다. 결론적으로 제안 시스템이 사람보다는 떨어지지만 유사한 정도의 성능을 보임을 알 수 있었다.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1326-1334
• /
• 2019

Knowledge base means a library stored in computer system providing useful information or appropriate solutions to specific area. Knowledge base associated with autism is the complex multidimensional information set related to the disease autism for its pathogenic factor and therapy. This paper focuses on the knowledge of biological molecular information extracted from massive biomedical texts with the aid of widespread used machine learning methods. Six classes of biological molecular information (such as protein, DNA, RNA, cell line, cell component, and cell type) are concerned and the probability statistics method, conditional random fields (CRFs), is utilized to discover these knowledges in this work. The knowledge base can help biologists to etiological analysis and pharmacists to drug development, which can at least answer four questions in question-answering (QA) system, i.e., which proteins are most related to the disease autism, which DNAs play important role to the development of autism, which cell types have the correlation to autism and which cell components participate the process to autism. The work can be visited by the address http://134.175.110.97/bioinfo/index.jsp.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.163-166
• /
• 2017

딥러닝은 모델이 복잡해질수록 Train 시간이 오래 걸리는 작업이다. Layer Normalization은 Train 시간을 줄이고, layer를 정규화 함으로써 성능을 개선할 수 있는 방법이다. 본 논문에서는 한국어 의미역 결정을 위해 Layer Normalization이 적용 된 Bidirectional LSTM CRF 모델을 제안한다. 실험 결과, Layer Normalization이 적용 된 Bidirectional LSTM CRF 모델은 한국어 의미역 결정 논항 인식 및 분류(AIC)에서 성능을 개선시켰다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.163-166
• /
• 2017

딥러닝은 모델이 복잡해질수록 Train 시간이 오래 걸리는 작업이다. Layer Normalization은 Train 시간을 줄이고, layer를 정규화 함으로써 성능을 개선할 수 있는 방법이다. 본 논문에서는 한국어 의미역 결정을 위해 Layer Normalization이 적용 된 Bidirectional LSTM CRF 모델을 제안한다. 실험 결과, Layer Normalization이 적용 된 Bidirectional LSTM CRF 모델은 한국어 의미역 결정 논항 인식 및 분류(AIC)에서 성능을 개선시켰다.

• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.213-218
• /
• 2009

본 논문에서는 무제한 텍스트 입력이 가능한 파서에서 오류분석을 통한 성능 향상을 이루고자 한다. 우선 코퍼스로부터 자동학습에 의해서 구문 분석 모델을 만들고 이를 평가하여 발생하는 오류를 분석한다. 오류를 감소시킬 수 있는 언어 특성이 반영된 자질을 추가하여 성능을 향상시키고자 한다. 세종 코퍼스를 10-fold cross validation으로 평가할 때, 한국어의 특성을 반영한 자질 추가로 1%이상의 성능 향상을 이루었다.

• Journal of KIISE
• /
• v.43 no.6
• /
• pp.678-685
• /
• 2016

Named Entity Recognition and Classification (NERC) is a task for recognition and classification of named entities such as a person's name, location, and organization. There have been various studies carried out on Korean NERC, but they have some problems, for example lacking some features as compared with English NERC. In this paper, we propose a method that uses word embedding as features for Korean NERC. We generate a word vector using a Continuous-Bag-of-Word (CBOW) model from POS-tagged corpus, and a word cluster symbol using a K-means algorithm from a word vector. We use the word vector and word cluster symbol as word embedding features in Conditional Random Fields (CRFs). From the result of the experiment, performance improved 1.17%, 0.61% and 1.19% respectively for TV domain, Sports domain and IT domain over the baseline system. Showing better performance than other NERC systems, we demonstrate the effectiveness and efficiency of the proposed method.

• Journal of KIISE:Software and Applications
• /
• v.37 no.11
• /
• pp.837-844
• /
• 2010

Prediction of the prosodic phrase boundary is one of the most important natural language processing tasks. We propose, for the natural prediction of the Korean prosodic phrase boundary, a statistical approach incorporating efficient learning features. These new features reflect the factors that affect generation of the prosodic phrase boundary better than existing learning features. Notably, moreover, such learning features, extracted according to the hand-crafted prosodic phrase boundary prediction rule, impart higher accuracy. We developed a statistical model for Korean prosodic phrase boundaries based on the proposed new features. The results were 86.63% accuracy for three levels (major break, minor break, no break) and 81.14% accuracy for six levels (major break with falling tone/rising tone, minor break with falling tone/rising tone/middle tone, no break).

• Journal of KIISE:Software and Applications
• /
• v.35 no.5
• /
• pp.306-312
• /
• 2008

In a goal-oriented dialogue, speaker's intention can be approximated by a semantic structure that consists of a pair of a speech act and a concept sequence. Therefore, it is very important to correctly identify the semantic structure of an utterance for implementing an intelligent dialogue system. In this paper, we propose a model to efficiently analyze the semantic structures based on an active teaming method. To reduce the burdens of high-level linguistic analysis, the proposed model only uses morphological features and previous semantic structures as input features. To improve the precisions of semantic structure analysis, the proposed model adopts CRFs(Conditional Random Fields), which show high performances in natural language processing, as an underlying statistical model. In the experiments in a schedule arrangement domain, we found that the proposed model shows similar performances(92.4% in speech act analysis and 89.8% in concept sequence analysis) to the previous models although it uses about a third of training data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.10
• /
• pp.1830-1840
• /
• 2011

CDISC (Clinical Data Interchanging Standards Consortium) standards are to support the acquisition, exchange, submission and archival of clinical trial and research data. SDTM (Study Data Tabulation Model) for Case Report Forms (CRFs) was recommended for U.S. Food and Drug Administration (FDA) regulatory submissions since 2004. Although the SDTM Implementation Guide gives a standardized and predefined collection of submission metadata 'domains' containing extensive variable collections, transforming CRFs to SDTM files for FDA submission is still a very hard and time-consuming task. For addressing this issue, we developed metadata based SDTM mapping rules. Using these mapping rules, we also developed a semi-automatic tool, named CDISC Transformer, for transforming clinical trial data to CDISC standard compliant data. The performance of CDISC Transformer with or without MDR support was evaluated using CDISC blank CRF as the 'gold standard'. Both MDR and user inquiry-supported transformation substantially improved the accuracy of our transformation rules. CDISC Transformer will greatly reduce the workloads and enhance standardized data entry and integration for clinical trial and research in various healthcare domains.