• Annual Conference on Human and Language Technology
• /
• 2012.10a
• /
• pp.29-34
• /
• 2012

본 연구는 한국어 어순재배치(scrambling) 문장의 이해 과정에서 발생되는 대뇌 활동을 사건관련전위(event-related Potentials; ERPs) 이용하여 살펴보기 위하여 실시되었다. 네 개의 어절로 구성된 표준 어순 문장(일년만에 마님이 영감을 만났어요.)과 어순재배치 문장(일년만에 영감을 마님이 만났어요.)을 어절별로 제시하고 첫 번째 명사구(NP1), 두 번째 명사구(NP2), 동사(Verb)의 시작점(onset)에서 측정한 뇌파를 비교하였다. 뇌파의 분석은 대뇌 영역을 중심선(midline), 중앙(medial), 편측(lateral)로 나누어 전후 분포(anterior-posterior distribution)와 정중선(midline)의 열에 의해 좌우 반구(hemisphere)로 분리하여 분석하였다. 분석 결과 중심선 영역에서 표준 어순에 비해 뒤섞기 어순에서 300-500ms 시간 창(time window)에서 큰 부적 전위(negative potential)가 관찰되었으며 이는 어순재배치로 인한 N400효과로 해석되며 P600효과는 관찰되지 않았다. 특히 첫 번째 명사구에서 문장유형(표준 어순 vs. 어순재배치)의 차이가 가장 크게 관찰되었으며 두 번째 명사구에서는 중앙에서 문장유형과 반구(좌우반구)의 상호작용이 관찰되었고, 동사에서는 문장유형과 반구, 문장유형과 전극 위치의 전후 분포와의 상호작용이 관찰되었다. 본 연구 결과에서 관찰된 N400효과는 독일어와 일본어를 대상으로 한 어순재배치 연구 결과와 유사하며 한국어 어순재배치 문장에 관한 사건관련 전위를 고찰하였다는 점에서 의의가 있다.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.183-203
• /
• 2018

News articles are the most suitable medium for examining the events occurring at home and abroad. Especially, as the development of information and communication technology has brought various kinds of online news media, the news about the events occurring in society has increased greatly. So automatically summarizing key events from massive amounts of news data will help users to look at many of the events at a glance. In addition, if we build and provide an event network based on the relevance of events, it will be able to greatly help the reader in understanding the current events. In this study, we propose a method for extracting event networks from large news text data. To this end, we first collected Korean political and social articles from March 2016 to March 2017, and integrated the synonyms by leaving only meaningful words through preprocessing using NPMI and Word2Vec. Latent Dirichlet allocation (LDA) topic modeling was used to calculate the subject distribution by date and to find the peak of the subject distribution and to detect the event. A total of 32 topics were extracted from the topic modeling, and the point of occurrence of the event was deduced by looking at the point at which each subject distribution surged. As a result, a total of 85 events were detected, but the final 16 events were filtered and presented using the Gaussian smoothing technique. We also calculated the relevance score between events detected to construct the event network. Using the cosine coefficient between the co-occurred events, we calculated the relevance between the events and connected the events to construct the event network. Finally, we set up the event network by setting each event to each vertex and the relevance score between events to the vertices connecting the vertices. The event network constructed in our methods helped us to sort out major events in the political and social fields in Korea that occurred in the last one year in chronological order and at the same time identify which events are related to certain events. Our approach differs from existing event detection methods in that LDA topic modeling makes it possible to easily analyze large amounts of data and to identify the relevance of events that were difficult to detect in existing event detection. We applied various text mining techniques and Word2vec technique in the text preprocessing to improve the accuracy of the extraction of proper nouns and synthetic nouns, which have been difficult in analyzing existing Korean texts, can be found. In this study, the detection and network configuration techniques of the event have the following advantages in practical application. First, LDA topic modeling, which is unsupervised learning, can easily analyze subject and topic words and distribution from huge amount of data. Also, by using the date information of the collected news articles, it is possible to express the distribution by topic in a time series. Second, we can find out the connection of events in the form of present and summarized form by calculating relevance score and constructing event network by using simultaneous occurrence of topics that are difficult to grasp in existing event detection. It can be seen from the fact that the inter-event relevance-based event network proposed in this study was actually constructed in order of occurrence time. It is also possible to identify what happened as a starting point for a series of events through the event network. The limitation of this study is that the characteristics of LDA topic modeling have different results according to the initial parameters and the number of subjects, and the subject and event name of the analysis result should be given by the subjective judgment of the researcher. Also, since each topic is assumed to be exclusive and independent, it does not take into account the relevance between themes. Subsequent studies need to calculate the relevance between events that are not covered in this study or those that belong to the same subject.

• Annual Conference on Human and Language Technology
• /
• 1993.10a
• /
• pp.261-267
• /
• 1993

Barwise & Cooper (1991)는 Hans Kamp(1981)의 DRS(Discourse Representation structure)를 기초로 EKN(Extended Kamp Notation)을 개발하였다. 본 논문은 EKN을 통해 실제 자연언어의 의미를 분석하는 데 그 목적이었다. 특히 이 논문은 양화사 의미해석의 기본개념이 되는 자원상황(resource situation), 치역(range), 사건(event) 등의 개념을 구체화하여 영어나 한국어 명사구의 누적성과 의존성에 관련된 의미를 분석한다. '세명의 학생이 (비디오 가게에서) 영화 일곱편을 빌렸다'라는 표현은 '학생'과 '영화'의 배분성 ${\pm}$ 과 집합성 ${\pm}$ 에 의한 일곱가지 해석 이외에 '세명의 학생이 각자 빌린 영화들이 일곱가지'라는 누적적 해석도 가능하다. 이러한 명사구의 누적적 해석에 대하여 분석하고, 'John always wears a tie,. They, were all silk,'에서 'a tie'와 'they'가 공지표화(i) 되기 위한 통사적 요건(성, 수의 일치)을 충족하지 않는 의존적 복수에 대하여도 분석한다.

• Journal of the Society of Disaster Information
• /
• v.7 no.2
• /
• pp.140-150
• /
• 2011

Life Environment is rapidly changing and large scale disasters are increasing from the global warming. Although the disaster repair resources are deployed to the disaster fields, the prevention of the disasters is the most effective countermeasures. the disaster sign data is based on the rule of Heinrich. Automatic extraction of the disaster sign data from the web is the focused issues in this paper. We defined the automatic extraction processes and applied information, such as accident nouns, disaster filtering nouns, disaster sign nouns and rules. Using the processes, we implemented the disaster sign data management system. In the future, the applied information must be continuously updated, because the information is only the extracted and analytic result from the some disaster data.

• Journal of the Korean Society for information Management
• /
• v.25 no.4
• /
• pp.227-243
• /
• 2008

This study investigates an event detection method with the aim of generating an event-focused news summary from a set of news articles on a certain event using a multi-document summarization technique. The event detection method first classifies news articles into the event related topic categories by employing a SVM classifier and then creates event clusters containing news articles on an event by a modified single pass clustering algorithm. The clustering algorithm applies a time penalty function as well as cluster partitioning to enhance the clustering performance. It was found that the event detection method proposed in this study showed a satisfactory performance in terms of both the F-measure and the detection cost.

• 건강소식
• /
• v.24 no.11 s.264
• /
• pp.2-5
• /
• 2000

국회의원 5선 역임, 김대중 내란음모사건 변호인……, 적지 않은 기간동안 정치의 길을 걸으면서 민주ㆍ평화에 대한 확고한 신념을 체득한 허경만 지사는 정치 발전 못지 않게 지역 발전도 중요하다고 강조한다. 그는, 도 예산의 상당부분을 사회복지 부문에 투입하는 등 도민 모두의 보건 복지에 주력하는 동시에 전남도의 대내외적 성장을 위한 사업의 연구와 추진에 전념하고 있다. 한번 세운 바른 뜻은 굽히지 않는다는 그의 소신에서 전남의 발전된 모습이 묻어나는 시간이었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.881-884
• /
• 2017

스마트 디바이스가 대중화 되면서 각종 사건 사고에 대한 데이터가 SNS 상에 실시간으로 업데이트 된다. SNS의 이런 특성을 이용하여 이용자 개개인이 사고감지센서의 역할을 하면 빠른 사고감지가 가능하다. 하지만 기존 연구들은 단순히 키워드의 출현 빈도로 사고를 판단하는 방식과, 문법파괴 요소가 많은 트위터의 특성으로 인해 정확성에서 한계를 보인다. 본 연구에서는 사고감지의 정확도를 높이기 위해 형태소로 분석한 트윗을 벡터화하여 다층퍼셉트론신경망으로 학습시키는 모델을 구현하였다. 연구 결과 일반명사로 이루어진 40개의 단어를 사용했을 때 가장 높은 82.58%의 정확도를 얻었다.

• Annual Conference on Human and Language Technology
• /
• 2010.10a
• /
• pp.94-99
• /
• 2010

This paper is to present how a network between words is formed. Not only have we looked at the distributivity, frequency and strength in connections between related words, but we have also presented some way to shed lights on what this network means to linguistic and social studies. The target source is morpho-analysis components of Trends 21 corpus which cover all newspaper articles from lour major newspapers, including Chosun, Joongang, Donga, and Hankyoreh, issued between 2000 and 2008. Based on nodes, links, and their connectivity indexes - density, degree, and centralizations, we have been able to retrieve and cluster related words forming the network with 20 event nouns. To reduce noise, we have considered the words whose t-score is above 1.64. By conducting both network and statistical analyses, we have presented the network of each event noun.

• Koreanishche Zeitschrift fur Deutsche Sprachwissenschaft
• /
• v.1
• /
• pp.119-139
• /
• 1999

일상어는 한 사회의 모든 구성원이 쉽게 이해할 수 있고 사회생활에서 아무런 어려움이 없이 상호간에 의사소통을 할 수 있는 언어의 표현 수단이다. 이에 반하여 학술어는 각각의 전문분야에서 사용되고 있는 언어의 한 형태이다. 학술적 텍스트에서 나타나는 일반적인 특징은 글이 객관적이면서도 명확하게 기술된다는 점이다. 일반독자는 자주 사용되는 전문어휘를 통하여 학술적 텍스트를 가장 쉽게 인식할 수 있으며, 또한 텍스트의 구성에 있어서도 학술적 텍스트가 일반 텍스트와 다르다는 사실을 알 수 있다. 이 외에도 독일어에서는 일정한 문법적 현상들이 학술적 전문어의 요소로서 사용되고 있다. 예를 들면 삼인칭 단수, 부사구, 명사화 경향, 기능동사구의 선호, 수동구문 등등이 있다. 일반적으로 학술적 전문어에 자주 사용되고 있는 문법적 요소 중의 하나가 수동구문이다. 학술어의 요소로서 수동구문이 갖는 언어적 기능은 다음과 같다: 1. 수동구문에서는 일반적으로 행위자가 언급되지 않음으로써 사실이 객관적으로 표현되며, 동시에 행위자의 억제는 언어의 경제성에 기여한다. 2. 경우에 따라서 행위자가 표현될 때, 직접적인 행위의 주체를 나타내는 von-전치사구 혹은 매개체나 원인을 표현하는 durch-전치사구를 통하여 사건을 정확하게 기술할 수 있다. 3. 테마-레마 구조와 관련하여 살펴보면 문장구성 혹은 문장연결을 위한 표현수단으로도 수동구문은 활용된다. 4. 수동구문을 사용함으로써 문체상의 단조롭고 획일적인 점을 회피할 수도 있다. 본 논문은 이와 같이 수동구문이 지니고 있는 언어적 기능을 살펴봄으로써 학술적 전문어의 특징과 전문어를 이해하는데 기여한다.

• Journal of Digital Convergence
• /
• v.10 no.10
• /
• pp.491-496
• /
• 2012

This study tried to analyze symbolism of the work from the title by looking into its linguistic meaning. The title not only exposes artist's thoughts but also speaks for the work subject. Also, it designates the world composed of characters in the work, and further it can be said as endowing overall meaning on the entire work by suggesting possibility of limitless meaning invention as well. As a result of reviewing the symbolism shown at the title after analyzing such points through linguistic contexts, the title named with Adam's language was used for just expressing the essence of characters in the work by transcending time and space, and the title meaning exposed relational aspects between characters and occurred accidents through the association process on 'signifiant' and 'signifie.' These relational aspects are expressed to mutual contraposition, but their relations finally show another one orientation too. In case of the title made by the arbitrary nature of language, a fact could be known that it was results of customs completely unrelated with the practical work and depended on the experience by any accident as being appeared from cultural background of the country where the work was produced. Also, the signification of language occurred in unique regulations and systems, and it was relevant to seeing things through concepts. The proper noun was disappeared, and the symbolism was given again from relational aspects accordingly. It was turn out that similarity between the work and title contained contents of entire work, and played a role of expressing greed in the narrative briefly.