• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.437-442
• /
• 2023

최근에 등장한 대규모 언어 모델은 다양한 언어 처리 작업에서 놀라운 성능을 발휘하고 있다. 그러나 이러한 모델의 크기와 복잡성 때문에 모델 경량화의 필요성이 대두되고 있다. Pruning은 이러한 경량화 전략 중 하나로, 모델의 가중치나 연결의 일부를 제거하여 크기를 줄이면서도 동시에 성능을 최적화하는 방법을 제시한다. 본 논문에서는 한국어 언어 모델인 Polyglot-Ko에 Wanda[1] 기법을 적용하여 Pruning 작업을 수행하였다. 그리고 이를 통해 가중치가 제거된 모델의 Perplexity, Zero-shot 성능, 그리고 Fine-tuning 후의 성능을 분석하였다. 실험 결과, Wanda-50%, 4:8 Sparsity 패턴, 2:4 Sparsity 패턴의 순서로 높은 성능을 나타냈으며, 특히 일부 조건에서는 기존의 Dense 모델보다 더 뛰어난 성능을 보였다. 이러한 결과는 오늘날 대규모 언어 모델 중심의 연구에서 Pruning 기법의 효과와 그 중요성을 재확인하는 계기가 되었다.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.16-22
• /
• 2024

Robotic grasping in unstructured environments poses a significant challenge, demanding precise estimation of gripping positions for diverse and unknown objects. Generative Grasping Convolution Neural Network (GG-CNN) can estimate the position and direction that can be gripped by a robot gripper for an unknown object based on a three-dimensional depth map. Since GG-CNN uses only a depth map as an input, the precision of the depth map is the most critical factor affecting the result. To address the challenge of depth map precision, we integrate the Segment Anything Model renowned for its robust zero-shot performance across various segmentation tasks. We adjust the components corresponding to the segmented areas in the depth map aligned through external calibration. The proposed method was validated on the Cornell dataset and SurgicalKit dataset. Quantitative analysis compared to existing methods showed a 49.8% improvement with the dataset including surgical instruments. The results highlight the practical importance of our approach, especially in scenarios involving thin and metallic objects.

• Cartoon and Animation Studies
• /
• s.34
• /
• pp.105-128
• /
• 2014

This study was aimed to analyze the disparities of 3D stereoscopic images in four well-known American animation movies. After Avatar (2009), lots of stereoscopic movies were developed in Korean 3D production. Almost all 3D productions in Korea, however, focus on the display images or TV series animation yet. In order to make many well-made Korean stereoscopic 3D animations in future, analyzing and comparing the disparities of 3D stereoscopic images is necessary and even mandated. First, I chose 40 cuts from each four American stereoscopic 3D feature films, including Despicable me 2, Epic, Monster University, and Turbo. According to the classifications of shot angles by Vineyard (2008), secondly I analyze the 23 different angular disparities of 3D stereoscopic images and displayed in tables. Demonstrated shot angle disparities in each scene would provide numerical information to animators how to design and make the 3D stereoscopic images. Making successful stereoscopic 3D feature film will be a huge turning point in the Korean animation field in future. This study would be a first trial to seek a new method to set ahead an outlook of numerical values of 3D stereoscopic images for better visual effects.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.341-354
• /
• 2023

The title of a document is the brief summarization of the document. Readers can easily understand a document if we provide them with its title in their preferred styles and the languages. In this research, we propose a cross-lingual and style-based title generation model using multiple adapters. To train the model, we need a parallel corpus in several languages with different styles. It is quite difficult to construct this kind of parallel corpus; however, a monolingual title generation corpus of the same style can be built easily. Therefore, we apply a zero-shot strategy to generate a title in a different language and with a different style for an input document. A baseline model is Transformer consisting of an encoder and a decoder, pre-trained by several languages. The model is then equipped with multiple adapters for translation, languages, and styles. After the model learns a translation task from parallel corpus, it learns a title generation task from monolingual title generation corpus. When training the model with a task, we only activate an adapter that corresponds to the task. When generating a cross-lingual and style-based title, we only activate adapters that correspond to a target language and a target style. An experimental result shows that our proposed model is only as good as a pipeline model that first translates into a target language and then generates a title. There have been significant changes in natural language generation due to the emergence of large-scale language models. However, research to improve the performance of natural language generation using limited resources and limited data needs to continue. In this regard, this study seeks to explore the significance of such research.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.195-204
• /
• 2023

In this study, prompt engineering that improves prompts was explored to improve the performance of teaching and learning materials recommendations using generative artificial intelligence such as GPT and Stable Diffusion. Picture materials were used as the types of teaching and learning materials. To explore the impact of the prompt composition, a Zero-Shot prompt, a prompt containing learning target grade information, a prompt containing learning goals, and a prompt containing both learning target grades and learning goals were designed to collect responses. The collected responses were embedded using Sentence Transformers, dimensionalized to t-SNE, and visualized, and then the relationship between prompts and responses was explored. In addition, each response was clustered using the k-means clustering algorithm, then the adjacent value of the widest cluster was selected as a representative value, imaged using Stable Diffusion, and evaluated by 30 elementary school teachers according to the criteria for evaluating teaching and learning materials. Thirty teachers judged that three of the four picture materials recommended were of educational value, and two of them could be used for actual classes. The prompt that recommended the most valuable picture material appeared as a prompt containing both the target grade and the learning goal.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.12 no.3
• /
• pp.534-540
• /
• 1988

A study on the mixing process of fuel with ambient gas is necessary to verify combustion process of a diesel engine, especially the mechanism of its ignition delay. In this study, a single shot of diesel spray was injected through either a constant pressure injection system and bypass type injection system. Measurements were made on the flow characteristics of ambient gas and its time history using a hot wire anemometer and a high speed camera. The gas flow direction was determined by a smoke tracer method. (1) The ambient gas of spray flows away at the stagnation part where static pressure value is positive and flows in at the penetration part of a negative value with the steady entrainment length of 0.7. (2) The steady entertainment velocity around the spray in creases from the nozzle tip to the downstream, has the maximum value at the mixing boundary part, and represents zero at the stagnation boundary part after which the stream flows reversely at the stagnation part.

• Journal of Internet Computing and Services
• /
• v.23 no.2
• /
• pp.45-52
• /
• 2022

With the development of artificial intelligence analysis methods, especially machine learning, various fields are widely expanding their application ranges. However, in the case of classical music, there still remain some difficulties in applying machine learning techniques. Genre classification or music recommendation systems generated by deep learning algorithms are actively used in general music, but not in classical music. In this paper, we attempted to classify opera among classical music. To this end, an experiment was conducted to determine which criteria are most suitable among, composer, period of composition, and emotional atmosphere, which are the basic features of music. To generate emotional labels, we adopted zero-shot classification with four basic emotions, 'happiness', 'sadness', 'anger', and 'fear.' After embedding the opera libretto with the doc2vec processing model, the optimal number of clusters is computed based on the result of the elbow method. Decided four centroids are then adopted in k-means clustering to classify unsupervised libretto datasets. We were able to get optimized clustering based on the result of adjusted rand index scores. With these results, we compared them with notated variables of music. As a result, it was confirmed that the four clusterings calculated by machine after training were most similar to the grouping result by period. Additionally, we were able to verify that the emotional similarity between composer and period did not appear significantly. At the end of the study, by knowing the period is the right criteria, we hope that it makes easier for music listeners to find music that suits their tastes.

• Geophysics and Geophysical Exploration
• /
• v.9 no.1
• /
• pp.102-107
• /
• 2006

Recently, rapid developments in computer hardware have enabled reverse-time migration to be applied to various production imaging problems. As a wave-equation technique using the two-way wave equation, reverse-time migration can handle not only multi-path arrivals but also steep dips and overturned reflections. However, reverse-time migration causes unwanted artefacts, which arise from the two-way characteristics of the hyperbolic wave equation. Zero-lag cross correlation with diving waves, head waves and back-scattered waves result in spurious artefacts. These strong artefacts have the common feature that the correlating forward and backward wavefields propagate in almost the opposite direction to each other at each correlation point. This is because the ray paths of the forward and backward wavefields are almost identical. In this paper, we present several tactics to avoid artefacts in shot-domain reverse-time migration. Simple muting of a shot gather before migration, or wavefront migration which performs correlation only within a time window following first arriving travel times, are useful in suppressing artefacts. Calculating the wave propagation direction from the Poynting vector gives rise to a new imaging condition, which can eliminate strong artefacts and can produce common image gathers in the reflection angle domain.

• Communications of Mathematical Education
• /
• v.37 no.3
• /
• pp.545-567
• /
• 2023

This study investigates effective ChatGPT prompts for solving mathematical problems, focusing on the chapters of quadratic equations and quadratic functions. A structured prompt was designed, following a sequence of 'Role-Rule-Example Solution-Problem-Process'. In this study, an artificial intelligence model combining GPT-4, Wolfram plugin, and Advanced Data Analysis was utilized. Wolfram was used as the primary tool for calculations to reduce computational errors. When using the structured prompt, the accuracy rate for problems from nine high school mathematics textbooks on quadratic equations and quadratic functions was 91%, showing higher performance compared to zero-shot prompts. This confirmed the effectiveness of the structured prompts in solving mathematical problems. The structured prompts designed in this study can contribute to the development of intelligent information systems for personalized and customized education.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.648-653
• /
• 2023

관계 추출 태스크는 주어진 텍스트로부터 두 개체 간의 적절한 관계를 추론하는 작업이며, 지식 베이스 구축 및 질의응답과 같은 응용 태스크의 기반이 된다. 최근 자연어처리 분야 전반에서 생성형 거대 언어모델의 내재 지식을 활용하여 뛰어난 성능을 성취하면서, 대표적인 정보 추출 태스크인 관계 추출에서 역시 이를 적극적으로 활용 가능한 방안에 대한 탐구가 필요하다. 특히, 실 세계의 추론 환경과의 유사성에서 기인하는 저자원 특히, 제로샷 환경에서의 관계 추출 연구의 중요성에 기반하여, 효과적인 프롬프팅 기법의 적용이 유의미함을 많은 기존 연구에서 증명해왔다. 따라서, 본 연구는 한국어 관계 추출 분야에서 거대 언어모델에 다각적인 프롬프팅 기법을 활용하여 제로샷 환경에서의 추론에 관한 비교 연구를 진행함으로써, 추후 한국어 관계 추출을 위한 최적의 거대 언어모델 프롬프팅 기법 심화 연구의 기반을 제공하고자 한다. 특히, 상식 추론 등의 도전적인 타 태스크에서 큰 성능 개선을 보인 사고의 연쇄(Chain-of-Thought) 및 자가 개선(Self-Refine)을 포함한 세 가지 프롬프팅 기법을 한국어 관계 추출에 도입하여 양적/질적으로 비교 분석을 제공한다. 실험 결과에 따르면, 사고의 연쇄 및 자가 개선 기법 보다 일반적인 태스크 지시 등이 포함된 프롬프팅이 정량적으로 가장 좋은 제로샷 성능을 보인다. 그러나, 이는 두 방법의 한계를 지적하는 것이 아닌, 한국어 관계 추출 태스크에의 최적화의 필요성을 암시한다고 해석 가능하며, 추후 이러한 방법론들을 발전시키는 여러 실험적 연구에 의해 개선될 것으로 판단된다.