• Annual Conference on Human and Language Technology
• /
• 2004.10d
• /
• pp.35-39
• /
• 2004

본 논문은 실용적인 구문분석기의 전단계로서, 자동 구축된 구문패턴사전과 규칙을 이용하여 구묶음하는 방법을 제안한다. 우선 규칙은 구문분석 말뭉치(30,875어절)를 대상으로 자동 추출된 고빈도의 규칙(Rewriting Rule)을 본 논문에 맞게 수동으로 구축하였다. 규칙은 조건부, 행위부로 이루어진 이진 규칙(binary rule)의 형태를 이루며, 명사구(NP), 수식어구(AP, DP), 인용구(X), 용언구(VP, VC)을 대상으로 15개를 구축하였다. 그리고 구문패턴은 중심어와 중심어 선행 요소의 특성뿐만 아니라 중심어 후행 요소도 고려하여 형식화시킨 것으로, 중심어의 복합용언 여부에 따라 일반용언패턴과 본+보조용언패턴으로 구분한다. 부분적인 언어 현상의 처리보다는 실세계에서 사용되는 수많은 문장들에 내재되어 있는 매우 광범위한 언어 현상의 처리를 하기 위해, 구문패턴은 형태소주석 말뭉치(460만 어절)을 대상으로 자동 구축하였다. 구축된 구문패턴사전과 규칙을 이용하여 구묶음을 수행한 결과 정확율 83.09%가 나타났다.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.185-197
• /
• 2023

This study was conducted using text mining and network theory to extract useful information for application for occupancy and performance of permit tasks contained in the permit contents from the permit register, which is used only for the simple purpose of recording occupancy permit information. Based on text mining, we analyzed and compared the frequency of vocabulary occurrence and topic modeling in five regions, including Seoul, Gyeonggi, Gyeongsang, Jeolla, Chungcheong, and Gangwon, as well as normalization processes such as stopword removal and morpheme analysis. By applying four types of centrality algorithms, including stage, proximity, mediation, and eigenvector, which are widely used in network theory, we looked at keywords that are in a central position or act as an intermediary in the network. Through a comprehensive analysis of vocabulary appearance frequency, topic modeling, and network centrality, it was found that the 'installation' keyword was the most influential in all regions. This is believed to be the result of the Ministry of Environment's permit management office issuing many permits for constructing facilities or installing structures. In addition, it was found that keywords related to road facilities, flood control facilities, underground facilities, power/communication facilities, sports/park facilities, etc. were at a central position or played a role as an intermediary in topic modeling and networks. Most of the keywords appeared to have a Zipf's law statistical distribution with low frequency of occurrence and low distribution ratio.

• Journal of Digital Convergence
• /
• v.12 no.6
• /
• pp.655-667
• /
• 2014

This paper has identified five major categories of the T2D patients' concerns based on an online forum where the patients voluntarily verbalized their naturally occurring emotional reactions and concerns related to T2D. We have emphasized the fact that the lexical and phrasal analysis brought to the forefront the prevailing negative reactions and desires for clear information, professional advice, and emotional support. This study used lexical and phrasal analysis based on text-mining tools to estimate the potential of using a large sample of patient conversation of a specific disease posted on the internet for clinical features and patients' emotions. As a result, the study showed that quantitative analysis based on text-mining is a viable method of generalizing the psychological concerns and features of T2D patients.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.393-398
• /
• 2007

본 논문은 작업 현장에서 청각장애인의 의사소통을 보조하는 한국 수화 메시지 보드의 개발에 대하여 다룬다. 청각 장애인은 일상적인 직업 현장에서 의사소통이 자유롭지 못하여 업무에 잘 적응하지 못하고 사내의 인간관계에 많은 어려움을 겪고 있다. 문자를 이용한 정보 전달을 통해 모든 의사소통을 대체할 수 있을 것이라는 일반적인 생각과는 달리, 청각장애인의 경우 비장애인과 비교하여 사물의 개념 습득에 어려움이 있을 수 있으며 마찬가지로 사용하는 어휘수도 제한적인 경우가 많아 문자를 통한 의사소통에는 명확한 한계가 존재한다. 실제로 청각 장애 근로자가 이직하는 사유로 의사소통이나 인간관계가 높은 비중을 차지한다. 수화 메시지 보드는 크게 사내 네트워크를 이용한 공지 사항 전달을 위한 용도와 복수 개의 메시지 보드 간 문자 송수신의 용도로 사용 가능하다. 비장애인이 청각장애인에게 문자 입력으로 의사를 전달하면, 전달된 문자는 문자-수화 번역기를 통해 자동으로 수화로 번역되어 아바타의 수화 동작으로 화면에 출력된다. 전체 시스템은 수화 아바타를 포함한 그래픽 유저 인터페이스 (GUI), 수화 데이터베이스 및 한글 형태소/문장 분석기를 포함하는 문자-수화 번역기, 그리고 TCP/IP 기반의 문자 전송기의 세 부분으로 나뉜다. 본 논문에서는 수화 데이터베이스의 단어 선정을 위한 대상 작업 현장을 청각 장애 근로자가 타 직업에 비해 많은 비중을 차지하는 전자 부품 조립 업체로 한정하였다. 수화 데이터베이스는 자음 14종, 모음 17종, 숫자 15종, 일상생활 용어 1000종, 전자 부품 조립 업체에 특화된 단어 50종 및 직업 교육 관련 용어 50종으로 이루어진 총 1146종의 수화 단어를 포함하며, 수화 데이터베이스에 등록되지 않은 단어에 대해서는 지화로 표현하도록 한다. 이 중 전자 부품 조립 업체 특화 단어와 관련하여서는, 현재 동일한 분야의 작업 현장이라 하더라도 각 사업장 간 사용되는 수화가 통일되지 않아 문헌 조사 및 현장 조사를 통해 사용 빈도가 높고 형태가 공통적인 50종을 추려내었다. 본 연구는 실제 업무현장에서 청각장애인이 겪는 의사소통의 문제를 효과적으로 해결함으로써, 청각장애인이 직업 현장에 보다 쉽게 적응하도록 도움을 줄 뿐만 아니라, 일을 통해 자아 실현을 하도록 돕는 방안이 될 수 있다는 점에서 중요한 의의를 갖는다.

• Journal of the Korea Convergence Society
• /
• v.11 no.11
• /
• pp.33-39
• /
• 2020

In the field of Natural Language Processing, Various research such as Translation, POS Tagging, Q&A, and Sentiment Analysis are globally being carried out. Sentiment Analysis shows high classification performance for English single-domain datasets by pretrained sentence embedding models. In this thesis, the classification performance is compared by Korean E-commerce online dataset with various domain attributes and 6 Neural-Net models are built as BOW (Bag Of Word), LSTM[1], Attention, CNN[2], ELMo[3], and BERT(KoBERT)[4]. It has been confirmed that the performance of pretrained sentence embedding models are higher than word embedding models. In addition, practical Neural-Net model composition is proposed after comparing classification performance on dataset with 17 categories. Furthermore, the way of compressing sentence embedding model is mentioned as future work, considering inference time against model capacity on real-time service.

• Annual Conference on Human and Language Technology
• /
• 2007.10a
• /
• pp.84-90
• /
• 2007

일반적인 어휘망이 의미 관계에 의한 연결 구조를 중심으로 연구 개발된 것과는 달리, U-WIN은 의미관계를 비롯하여 개념 관계, 형태 관계, 구문 관계 등과 같이 의미 관계의 범위를 확장한 어휘 관계를 적용하여 구축하고 있다. 본 연구에서는 U-WIN의 어휘 관계 중의 하나인 구문관계를 자동으로 구축하는 방법을 제시하고자 한다. 먼저, 용언의 용례에서 문형정보를 기준으로 구문관계를 형성할 수 있는 후보명사를 추출하였으며, 추출한 후보명사는 용언의 세분화된 의미별로 정확하고 다양하게 추출할 수 있었다. 그러나 U-WIN은 다의어의 뜻풀이 하나하나를 개별적인 어휘로 구분하여 구축하였으므로, 어휘 간의 구문관계를 설정하기 위해서는 후보명사의 여러 의미 중에서 하나의 의미로 결정해야 한다. 그래서 본 연구에서는 용례 매칭 규칙, 구문패턴, 의미 유사도 등을 차례로 적용하여 후보명사의 의미를 분별하였으며, 또한 구문패턴의 빈도 정보를 이용하여 용례에 나타나지 않지만 구문관계를 형성할 수 있는 명사를 추출하여 구문관계를 확장하고자 하였다. 이러한 연구는 명사 중심의 어휘망이 용언과의 구문관계 구축을 통해 형태소 분석, 구문 분석, 의미 분석 등에 광범위하게 활용할 수 있는 어휘망의 기반을 다지는 작업이 될 수 있을 것이다.

• 재활복지
• /
• v.21 no.1
• /
• pp.193-212
• /
• 2017

The elderly often produce irrelevant speech and get off-topic more easily than the young; the former also has difficulty generating fewer syntactic structures and makes errors of grammatical morphemes. In particular, the elderly might have more difficulty writing since it requires more complex cognitive processes than storytelling. The participants in this study were 32 young people and 32 older people. They were asked to write a short story of Korean fairy tale('Heungbu Nolbu'). The data was analyzed in narrative composition and syntactic structures. The study revealed the following: First, in composition aspects, the elderly group showed significantly lower total number of story grammar and episodes. In addition, the elderly produced more off topic statements. Second, in syntactic aspects, although there was no significant difference in the number of producing complex sentences between two groups, the elderly group generated more inadequate cohesive devices and used fewer relative and adverbial clauses. These findings suggest that the elderly have a tendency to perform tasks by producing more off-topic statements and shows decreasing coherence by using lower number of relative and adverbial clauses. However, this study also uncovers that the elderly were able to write more complex and longer sentences using visual feedback.

• Journal of The Korean Association For Science Education
• /
• v.44 no.3
• /
• pp.231-248
• /
• 2024

This study developed a chatbot for first-year high school students, employing open-source software and the Korean Sentence-BERT model for AI-powered document classification. The chatbot utilizes the Sentence-BERT model to find the six most similar Q&A pairs to a student's query and presents them in a carousel format. The initial dataset, built from online resources, was refined and expanded based on student feedback and usability throughout over the operational period. By the end of the 2023 academic year, the chatbot integrated a total of 30,819 datasets and recorded 3,457 student interactions. Analysis revealed students' inclination to use the chatbot when prompted by teachers during classes and primarily during self-study sessions after school, with an average of 2.1 to 2.2 inquiries per session, mostly via mobile phones. Text mining identified student input terms encompassing not only science-related queries but also aspects of school life such as assessment scope. Topic modeling using BERTopic, based on Sentence-BERT, categorized 88% of student questions into 35 topics, shedding light on common student interests. A year-end survey confirmed the efficacy of the carousel format and the chatbot's role in addressing curiosities beyond integrated science learning objectives. This study underscores the importance of developing chatbots tailored for student use in public education and highlights their educational potential through long-term usage analysis.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.163-176
• /
• 2014

Social media is becoming the platform for users to communicate their activities, status, emotions, and experiences to other people. In recent years, microblogs, such as Twitter, have gained in popularity because of its ease of use, speed, and reach. Compared to a conventional web blog, a microblog lowers users' efforts and investment for content generation by recommending shorter posts. There has been a lot research into capturing the social phenomena and analyzing the chatter of microblogs. However, measuring television ratings has been given little attention so far. Currently, the most common method to measure TV ratings uses an electronic metering device installed in a small number of sampled households. Microblogs allow users to post short messages, share daily updates, and conveniently keep in touch. In a similar way, microblog users are interacting with each other while watching television or movies, or visiting a new place. In order to measure TV ratings, some features are significant during certain hours of the day, or days of the week, whereas these same features are meaningless during other time periods. Thus, the importance of features can change during the day, and a model capturing the time sensitive relevance is required to estimate TV ratings. Therefore, modeling time-related characteristics of features should be a key when measuring the TV ratings through microblogs. We show that capturing time-dependency of features in measuring TV ratings is vitally necessary for improving their accuracy. To explore the relationship between the content of microblogs and TV ratings, we collected Twitter data using the Get Search component of the Twitter REST API from January 2013 to October 2013. There are about 300 thousand posts in our data set for the experiment. After excluding data such as adverting or promoted tweets, we selected 149 thousand tweets for analysis. The number of tweets reaches its maximum level on the broadcasting day and increases rapidly around the broadcasting time. This result is stems from the characteristics of the public channel, which broadcasts the program at the predetermined time. From our analysis, we find that count-based features such as the number of tweets or retweets have a low correlation with TV ratings. This result implies that a simple tweet rate does not reflect the satisfaction or response to the TV programs. Content-based features extracted from the content of tweets have a relatively high correlation with TV ratings. Further, some emoticons or newly coined words that are not tagged in the morpheme extraction process have a strong relationship with TV ratings. We find that there is a time-dependency in the correlation of features between the before and after broadcasting time. Since the TV program is broadcast at the predetermined time regularly, users post tweets expressing their expectation for the program or disappointment over not being able to watch the program. The highly correlated features before the broadcast are different from the features after broadcasting. This result explains that the relevance of words with TV programs can change according to the time of the tweets. Among the 336 words that fulfill the minimum requirements for candidate features, 145 words have the highest correlation before the broadcasting time, whereas 68 words reach the highest correlation after broadcasting. Interestingly, some words that express the impossibility of watching the program show a high relevance, despite containing a negative meaning. Understanding the time-dependency of features can be helpful in improving the accuracy of TV ratings measurement. This research contributes a basis to estimate the response to or satisfaction with the broadcasted programs using the time dependency of words in Twitter chatter. More research is needed to refine the methodology for predicting or measuring TV ratings.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.53-77
• /
• 2012

This study analyses the difference of contents and tones of arguments among three Korean major newspapers, the Kyunghyang Shinmoon, the HanKyoreh, and the Dong-A Ilbo. It is commonly accepted that newspapers in Korea explicitly deliver their own tone of arguments when they talk about some sensitive issues and topics. It could be controversial if readers of newspapers read the news without being aware of the type of tones of arguments because the contents and the tones of arguments can affect readers easily. Thus it is very desirable to have a new tool that can inform the readers of what tone of argument a newspaper has. This study presents the results of clustering and classification techniques as part of text mining analysis. We focus on six main subjects such as Culture, Politics, International, Editorial-opinion, Eco-business and National issues in newspapers, and attempt to identify differences and similarities among the newspapers. The basic unit of text mining analysis is a paragraph of news articles. This study uses a keyword-network analysis tool and visualizes relationships among keywords to make it easier to see the differences. Newspaper articles were gathered from KINDS, the Korean integrated news database system. KINDS preserves news articles of the Kyunghyang Shinmun, the HanKyoreh and the Dong-A Ilbo and these are open to the public. This study used these three Korean major newspapers from KINDS. About 3,030 articles from 2008 to 2012 were used. International, national issues and politics sections were gathered with some specific issues. The International section was collected with the keyword of 'Nuclear weapon of North Korea.' The National issues section was collected with the keyword of '4-major-river.' The Politics section was collected with the keyword of 'Tonghap-Jinbo Dang.' All of the articles from April 2012 to May 2012 of Eco-business, Culture and Editorial-opinion sections were also collected. All of the collected data were handled and edited into paragraphs. We got rid of stop-words using the Lucene Korean Module. We calculated keyword co-occurrence counts from the paired co-occurrence list of keywords in a paragraph. We made a co-occurrence matrix from the list. Once the co-occurrence matrix was built, we used the Cosine coefficient matrix as input for PFNet(Pathfinder Network). In order to analyze these three newspapers and find out the significant keywords in each paper, we analyzed the list of 10 highest frequency keywords and keyword-networks of 20 highest ranking frequency keywords to closely examine the relationships and show the detailed network map among keywords. We used NodeXL software to visualize the PFNet. After drawing all the networks, we compared the results with the classification results. Classification was firstly handled to identify how the tone of argument of a newspaper is different from others. Then, to analyze tones of arguments, all the paragraphs were divided into two types of tones, Positive tone and Negative tone. To identify and classify all of the tones of paragraphs and articles we had collected, supervised learning technique was used. The Na$\ddot{i}$ve Bayesian classifier algorithm provided in the MALLET package was used to classify all the paragraphs in articles. After classification, Precision, Recall and F-value were used to evaluate the results of classification. Based on the results of this study, three subjects such as Culture, Eco-business and Politics showed some differences in contents and tones of arguments among these three newspapers. In addition, for the National issues, tones of arguments on 4-major-rivers project were different from each other. It seems three newspapers have their own specific tone of argument in those sections. And keyword-networks showed different shapes with each other in the same period in the same section. It means that frequently appeared keywords in articles are different and their contents are comprised with different keywords. And the Positive-Negative classification showed the possibility of classifying newspapers' tones of arguments compared to others. These results indicate that the approach in this study is promising to be extended as a new tool to identify the different tones of arguments of newspapers.