• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.50-55
• /
• 2023

속성 기반 감정 분석은 텍스트 내에서 감정과 해당 감정이 특정 속성, 예를 들어 제품의 특성이나 서비스의 특징에 어떻게 연결되는지를 분석하는 태스크이다. 본 논문에서는 속성 기반 감정 분석 데이터를 사용한 다중 작업-토큰 레이블링 문제에 프롬프트 튜닝 기법을 적용하기 위한 포괄적인 방법론을 소개한다. 이러한 방법론에는 토큰 레이블링 문제를 시퀀스 레이블링 문제로 일반화하기 위한 감정 표현 영역 검출 파이프라인이 포함된다. 또한 분리된 시퀀스들을 속성과 감정에 대해 분류 하기 위한 템플릿을 선정하고, 데이터셋 특성에 맞는 레이블 워드를 확장하는 방법을 제안함으써 모델의 성능을 최적화한다. 최종적으로, 퓨샷 세팅에서의 속성 기반 감정 분석 태스크에 대한 몇 가지 실험 결과와 분석을 제공한다. 구축된 데이터와 베이스라인 모델은 AIHUB(www.aihub.or.kr)에 공개되어 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.82-85
• /
• 2024

코딩 규칙 준수는 대규모 프로젝트에서 프로그램의 버그를 줄이기 위해, 또 효과적인 유지보수를 위해 필수적이나 코딩 규칙을 학습하기 위한 초보자용 도구는 거의 없는 실정이다. 본 논문에서는 Python 프로그래밍 수업에서 코딩 규칙을 학습할 수 있도록 도와주는 시스템을 제안한다. 제안된 시스템은 학습자를 위해 별도의 설치 없이 Python 코딩 규칙 검사 결과를 영어와 한글을 병행하여 출력하는 규칙 검사 뷰어를 통해 학습자의 편의성을 제공한다. 또한, 품질 점수를 계산하여 학습자의 코딩 규칙 학습의 동기를 부여한다. 제안 시스템의 성능을 평가하기 위해 SonarQube와 검출 기능을 비교하였다. 2023년도 1학기 Python 프로그래밍 수업의 제출 코드를 검사한 결과, 제안 시스템이 SonarQube보다 247% 더 많은 종류의 규칙을, 또 235% 더 많은 개수의 규칙을 검사하는 것으로 나타났다. 이러한 비교 연구 결과를 고려할 때, 제안 시스템은 학습자에게 더 나은 코딩 규칙 학습 기회를 제공할 수 있을 것으로 기대된다.

• The Journal of the Korea Contents Association
• /
• v.12 no.2
• /
• pp.105-115
• /
• 2012

In this paper, we propose a correction method using phoneme unit segmentation to solve misrecognition of Korean Texts in signboard images using weighted Disassemble Levenshtein Distance. The proposed method calculates distances of recognized texts which are segmented into phoneme units and detects the best matched texts from signboard text database. For verifying the efficiency of the proposed method, a database dictionary is built using 1.3 million words of nationwide signboard through removing duplicated words. We compared the proposed method to Levenshtein Distance and Disassemble Levenshtein Distance which are common representative text string comparison algorithms. As a result, the proposed method based on weighted Disassemble Levenshtein Distance represents an improvement in recognition rates 29.85% and 6% on average compared to that of conventional methods, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.6
• /
• pp.29-35
• /
• 2010

While diversification of the use of video in the prevalence of cheap video equipment, augmented reality can print additional real-world images and video image. Although many recent advent augmented reality techniques, currently attempting to correct the character recognition is performed. In this paper characters marked with a visual marker recognition, and the color to match the marker color of the characters finds. And, it was shown on the screen by the character recognition. In this paper, by applying the phoneme pattern segmentation algorithm by the horizontal projection, we propose to segment the phoneme to match the six types of Hangul representation. Throughout the experiment sample of phoneme segmentation using augmented reality showed proceeding result at each step, and the experimental results was found to be that detection rate was above 90%.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.361-368
• /
• 2014

The LPR(License plate recognition) system has been developed to efficient control for complex traffic environment and currently be used in many places. However, because of light, noise, background changes, environmental changes, damaged plate, it only works limited environment, so it is difficult to use in real-time. This paper presents a heuristic segmentation algorithm for robust to noise and illumination changes and introduce a real-time license plate recognition system using it. In first step, We detect the plate utilized Haar-like feature and Adaboost. This method is possible to rapid detection used integral image and cascade structure. Second step, we determine the type of license plate with adaptive histogram equalization, bilateral filtering for denoise and segment accurate character based on adaptive threshold, pixel projection and associated with the prior knowledge. The last step is character recognition that used histogram of oriented gradients (HOG) and multi-layer perceptron(MLP) for number recognition and support vector machine(SVM) for number and Korean character classifier respectively. The experimental results show license plate detection rate of 94.29%, license plate false alarm rate of 2.94%. In character segmentation method, character hit rate is 97.23% and character false alarm rate is 1.37%. And in character recognition, the average character recognition rate is 98.38%. Total average running time in our proposed method is 140ms. It is possible to be real-time system with efficiency and robustness.

• Smart Media Journal
• /
• v.6 no.1
• /
• pp.16-21
• /
• 2017

Long time has passed since computers which used to be a means of research were commercialized and available for the general public. People used writing instruments to write before computer was commercialized. However, today a growing number of them are using computers to write instead. Computerized word processing helps write faster and reduces fatigue of hands than writing instruments, making it better fit to making long texts. However, word processing programs are more likely to cause spelling errors by the mistake of users. Spelling errors distort the shape of words, making it easy for the writer to find and correct directly, but those caused due to users' lack of knowledge or those hard to find may make it almost impossible to produce a document free of spelling errors. However, spelling errors in important documents such as theses or business proposals may lead to falling reliability. Consequently, it is necessary to conduct research on high-level spelling error correction programs for the general public. This study was designed to produce a system to correct sentence-level spelling errors to normal words with Korean alphabet similarity algorithm. On the basis of findings reported in related literatures that corrected words are significantly similar to misspelled words in form, spelling errors were extracted from a corpus. Extracted corrected words were replaced with misspelled ones to correct spelling errors with spelling error detection algorithm.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.4
• /
• pp.79-86
• /
• 2016

About 75% of software security incidents are caused by software vulnerability. In addition, the after-market repairing cost of the software is higher by more than 30 times than that in the design stage. In this background, the secure coding has been proposed as one of the ways to solve this kind of maintenance problems. Various institutions have addressed the weakness patterns of the standard software. A new Korean programming language Saesark has been proposed to resolve the security weakness on the language level. However, the previous study on Saesark can not resolve the security weakness caused by the API. This paper proposes a way to resolve the security weakness due to the API. It adopts a static analyzer inspecting dangerous methods. It classifies the dangerous methods of the API into two groups: the methods of using tainted data and those accepting in-flowing tainted data. It analyses the security weakness in four steps: searching for the dangerous methods, configuring a call graph, navigating a path between the method for in-flowing tainted data and that uses tainted data on the call graph, and reporting the security weakness detected. To measure the effectiveness of this method, two experiments have been performed on the new version of Saesark adopting the static analysis. The first experiment is the comparison of it with the previous version of Saesark according to the Java Secure Coding Guide. The second experiment is the comparison of the improved Saesark with FindBugs, a Java program vulnerability analysis tool. According to the result, the improved Saesark is 15% more safe than the previous version of Saesark and the F-measure of it 68%, which shows the improvement of 9% point compared to 59%, that of FindBugs.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.205-211
• /
• 2009

The Weightless Neural Network(WNN) has the advantage of the processing speed, less computability than weighted neural network which readjusts the weight. Especially, The behavior information such as sequential gesture has many serial correlation. So, It is required the high computability and processing time to recognize. To solve these problem, Many algorithms used that added preprocessing and hardware interface device to reduce the computability and speed. In this paper, we proposed the Ram based Sequential Cumulative Neural Network(SCNN) model which is sign language recognition system without preprocessing and hardware interface. We experimented with using compound words in continuous korean sign language which was input binary image with edge detection from camera. The recognition system of sign language without preprocessing got 93% recognition rate.

• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.217-225
• /
• 2017

Recently, the interest in predicting hot topics has grown significantly as it has become more important to find and analyze meaningful information from a large amount of data flowing in social networking services. Existing hot topic detection schemes do not consider a temporal property, so they are not suitable to predict hot topics that are rapidly issued in a changing society. This paper proposes a hot topic prediction scheme that uses a modified TF-IDF in social networking environments. The modified TF-IDF extracts a candidate set of keywords that are momentarily issued. The proposed scheme then calculates the hot topic prediction scores by assigning weights considering user influence and professionality to extract the candidate keywords. The superiority of the proposed scheme is shown by comparing it to an existing detection scheme. In addition, to show whether or not it predicts hot topics correctly, we evaluate its quality with Korean news articles from Naver.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.120-125
• /
• 1989

음성 신호에는 언어정보이외에 여러 요인에 의한 정보가 포함되어 있어서, 문자와 일대일로 대응되는 분절을 정확하게 검출하기가 어렵다. 본 연구에서는 선형 예측계수 (LPC) 스펙트럼의 첨두 부분을 강조한 이진 (binary) 스펙트럼을 제안하고, 이를 바탕으로 음의 안정영역과 천이영역을 통합하여 음향특징을 추출하고자 한다. 각 영역의 특징은 이진 스펙트럼을 누적하여 구하며, 통합적인 특징은 각 영역의 특징을 결합한 관계적 특징으로 나타낸다. 제 2 차 포르만트 주파수의 궤적을 관계적 특징으로 하여, 양순 비음과 치조 비음을 구별한 결과, 모음의 문맥과 화자에 비교적 독립적인 인식결과를 얻을 수 있었다. 또한 이진 스펙트럼이 원래의 스펙트럼에 포함된 정보를 유지하는지 검토하기 위해, 같은 거리척도 (distance measure) 에 의해 인식 실험한 결과 이진 스펙트럼의 성능이 오히려 우수하게 나타났으며, 관계적 이진 스펙트럼의 경우 화자에 따른 변화가 더욱 적었다. 음성에 백색 잡음 (Gaussian white noise)을 더하여 잡음음성 (noisy speech) 을 만든 뒤, 같은 방법으로 실험한 결과도 유사한 인식결과를 얻을 수 있어 제안된 이진 스펙트럼의 유효성을 확인하였다.