• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.203-212
• /
• 2021

To eliminate ambiguities in the existing methods to simplify Chinese pronunciation learning, we propose a model that can predict the pronunciation of Chinese characters automatically. The proposed model relies on a statistical machine translation (SMT) framework. In particular, we consider the components of Chinese characters as the basic unit and consider the pronunciation prediction as a machine translation procedure (the component sequence as a source sentence, the pronunciation, pinyin, as a target sentence). In addition to traditional features such as the bidirectional word translation and the n-gram language model, we also implement a component similarity feature to overcome some typos during practical use. We incorporate these features into a log-linear model. The experimental results show that our approach significantly outperforms other baseline models.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.357-366
• /
• 2022

Artificial intelligence (AI) is the replication of human intelligence by computer systems and machines using tools like machine learning, deep learning, expert systems, and natural language processing. AI can be applied in administrative settings to automate repetitive processes, analyze and forecast data, foster social communication skills among staff, reduce costs, and boost overall operational effectiveness. In order to understand how AI is being used for administrative duties in various organizations, this paper gives a critical dialogue on the topic and proposed a framework for using artificial intelligence in organizations. Additionally, it offers a list of specifications, attributes, and requirements that organizations planning to use AI should consider.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1014-1017
• /
• 2020

Many natural language processing (NLP) models utilize pre-trained word embeddings to leverage latent information. One of the most successful word embedding model is the Skip-gram (SG). In this paper, we propose a Skipgram drop (SG-Drop) model, which is a variation of the SG model. The SG-Drop model is designed to reduce training time efficiently. Furthermore, the SG-Drop allows controlling training time with its hyperparameter. It could train word embedding faster than reducing training epochs while better preserving the quality.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.493-495
• /
• 2023

Deep learning methods and attention mechanisms have been incorporated to improve facial emotion recognition, which has recently attracted much attention. The fusion approaches have improved accuracy by combining various types of information. This research proposes a fusion network with self-attention and local attention mechanisms. It uses a multi-layer perceptron network. The network extracts distinguishing characteristics from facial images using pre-trained models on RAF-DB dataset. We outperform the other fusion methods on RAD-DB dataset with impressive results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.678-680
• /
• 2023

본 논문은 정확하면서도 효율적인 한국어 문장 분류 기법에 대해서 논의한다. 최근 자연어처리 분야에서 사전 학습된 언어 모델(Pre-trained Language Models, PLM)은 미세조정(fine-tuning)을 통해 문장 분류 하위 작업(downstream task)에서 성공적인 결과를 보여주고 있다. 하지만, 이러한 미세조정은 하위 작업이 바뀔 때마다 사전 학습된 언어 모델의 전체 매개변수(model parameters)를 학습해야 한다는 단점을 갖고 있다. 본 논문에서는 이러한 문제를 해결할 수 있도록 도메인 적응기(domain adapter)를 활용한 한국어 문장 분류 프레임워크인 DAKS(Domain Adaptation-based Korean Sentence classification framework)를 제안한다. 해당 프레임워크는 학습되는 매개변수의 규모를 크게 줄임으로써 효율적인 성능을 보였다. 또한 문장 분류를 위한 특징(feature)으로써 한국어 사전학습 모델(KLUE-RoBERTa)의 다양한 은닉 계층 별 은닉 상태(hidden states)를 활용하였을 때 결과를 비교 분석하고 가장 적합한 은닉 계층을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.496-498
• /
• 2023

Brain tumor segmentation problem has challenges in the tumor diversity of location, imbalance, and morphology. Attention mechanisms have recently been used widely to tackle medical segmentation problems efficiently by focusing on essential regions. In contrast, the fusion approaches enhance performance by merging mutual benefits from many models. In this study, we proposed a 3D dual fusion attention network to combine the advantages of fusion approaches and attention mechanisms by residual self-attention and local blocks. Compared to fusion approaches and related works, our proposed method has shown promising results on the BraTS 2018 dataset.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.820-821
• /
• 2023

본 프로젝트는 Azure OpenAI Service (large language models and generative AI) 를 이용하여 IT 기술 및 현황을 생성형 AI (GPT-4)를 활용한 IT 카드 뉴스 서비스로서 업계 현직자들에게 정보를 제공하는 시스템을 구현하였다. IT 카드 뉴스 서비스의 부재와 뉴스 제작의 비용 및 시간 소요의 문제를 해결하기 위해 생성형 AI 시스템을 고안하였다. 해당 서비스를 통해 IT 업계에 관심이 많은 사용자에게 정리된 뉴스를 한 번에 제공하는 효과를 가져올 것으로 예상한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.428-429
• /
• 2023

개체명 인식은 자연어 처리의 핵심적인 작업으로, 특정 범주의 명칭을 문장에서 식별하고 분류한다. 이러한 기술은 헬스케어 분야에서 진단 지원 및 데이터 관리에 필수적이다. 그러나 기존의 사전 학습된 모델을 특정 도메인에 대해 전이학습하는 방법은 대량의 데이터에 크게 의존하는 한계를 가지고 있다. 본 연구는 방대한 데이터로 학습된 거대 언어 모델(LLM) 활용을 중심으로, 한국어의 교착어 특성을 반영하여 형태소 정보를 활용한 Few-Shot 프롬프트를 통해 한국어 헬스케어 도메인에서의 개체명 인식 방법을 제안한다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.4
• /
• pp.53-71
• /
• 2023

This study explores the relationship between various user factors and the level of trust in ChatGPT, a sophisticated language model exhibiting human-like capabilities. Specifically, we considered demographic characteristics such as age, education, gender, and major, along with factors related to previous AI experience, including duration, frequency, proficiency, perception, and familiarity. Through a survey of 140 participants, comprising 71 females and 69 males, we collected and analyzed the data to see how these user factors have a relationship with trust in ChatGPT. Both descriptive and inferential statistical methods, encompassing multiple linear regression models, were employed in our analysis. Our findings reveal significant relationships between user factors such as gender, the perception of prior AI interactions, self-evaluated proficiency, and Trust in ChatGPT. This research not only enhances our understanding of trust in artificial intelligence but also offers valuable insights for AI developers and practitioners in the field.

• Journal of Information Technology Applications and Management
• /
• v.30 no.4
• /
• pp.11-28
• /
• 2023

This paper proposes a method of integrating ChatGPT with traditional chatbot systems to enhance conversational artificial intelligence(AI) and create more efficient conversational systems. Traditional chatbot systems are primarily based on classification models and are limited to intent classification and simple response generation. In contrast, ChatGPT is a state-of-the-art AI technology for natural language generation, which can generate more natural and fluent conversations. In this paper, we analyze the business service areas that can be integrated with ChatGPT and traditional chatbots, and present methods for conducting conversational scenarios through case studies of service types. Additionally, we suggest ways to integrate ChatGPT with traditional chatbot systems for intent recognition, conversation flow control, and response generation. We provide a practical implementation example of how to integrate ChatGPT with traditional chatbots, making it easier to understand and build integration methods and actively utilize ChatGPT with existing chatbots.