• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.421-426
• /
• 2020

다중 도메인 목적 지향 대화에서 기존 딥 러닝을 이용한 대화 상태 추적(Dialog state tracking)은 여러 턴 동안 누적된 사용자와 시스템 간 대화를 입력 받아 슬롯 밸류(Slot value)를 추출하는 모델들이 연구되었다. 하지만 이 모델들은 대화가 길어질수록 연산량이 증가한다. 이에 본 논문에서는 다중 도메인 대화에서 누적된 대화의 history 없이 슬롯 밸류를 추출하는 방법을 제안한다. 하지만, 단순하게 history를 제거하고 현재 턴의 발화만 입력 받는 방법은 문맥 정보의 손실로 이어진다. 따라서 본 논문에서는 도메인 상태(Domain state)를 도입하여 매 턴 마다 대화 상태와 함께 추적하는 모델을 제안한다. 도메인 상태를 같이 추적함으로써 현재 어떠한 도메인에 대하여 대화가 진행되고 있는지를 파악한다. 또한, 함축된 문맥 정보를 담고 있는 이전 턴의 대화 상태와 도메인 상태를 현재 턴의 발화와 같이 입력 받아 정보의 손실을 줄였다. 대표적인 데이터 셋인 MultiWOZ 2.0과 MultiWOZ 2.1에서 실험한 결과, 대화의 history를 사용하지 않고도 대화 상태 추적에 있어 좋은 성능을 보이는 것을 확인하였다. 또한, 시스템 응답과 과거 발화에 대한 의존성을 제거하여 end-to-end 대화 시스템으로의 확장이 좀 더 용이할 것으로 기대된다.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.617-623
• /
• 2024

Identifying emotions through speech poses a significant challenge due to the complex relationship between language and emotions. Our paper aims to take on this challenge by employing feature engineering to identify emotions in speech through a multimodal classification task involving both speech and text data. We evaluated two classifiers-Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM)-both integrated with a BERT-based pre-trained model. Our assessment covers various performance metrics (accuracy, F-score, precision, and recall) across different experimental setups). The findings highlight the impressive proficiency of two models in accurately discerning emotions from both text and speech data.

• Journal of the Korea Convergence Society
• /
• v.12 no.5
• /
• pp.23-29
• /
• 2021

Recent deep learning-based natural language processing studies are conducting research to improve performance by training large amounts of data from various sources together. However, there is a possibility that the methodology of learning by combining data from various sources into one may prevent performance improvement. In the case of machine translation, data deviation occurs due to differences in translation(liberal, literal), style(colloquial, written, formal, etc.), domains, etc. Combining these corpora into one for learning can adversely affect performance. In this paper, we propose a new Corpus Weight Balance(CWB) method that considers the balance between parallel corpora in machine translation. As a result of the experiment, the model trained with balanced corpus showed better performance than the existing model. In addition, we propose an additional corpus construction process that enables coexistence with the human translation market, which can build high-quality parallel corpus even with a monolingual corpus.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.5
• /
• pp.1197-1207
• /
• 2018

PowerShell is command line shell and scripting language, built on the .NET framework, and it has several advantages as an attack tool, including built-in support for Windows, easy code concealment and persistence, and various pen-test frameworks. Accordingly, malwares using PowerShell are increasing rapidly, however, there is a limit to cope with the conventional malware detection technique. In this paper, we propose an improved monitoring method to observe commands executed in the PowerShell and a deep learning based malware classification model that extract features from commands using Convolutional Neural Network(CNN) and send them to Recurrent Neural Network(RNN) according to the order of execution. As a result of testing the proposed model with 5-fold cross validation using 1,916 PowerShell-based malwares collected at malware sharing site and 38,148 benign scripts disclosed by an obfuscation detection study, it shows that the model effectively detects malwares with about 97% True Positive Rate(TPR) and 1% False Positive Rate(FPR).

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.98-98
• /
• 2023

ChatGPT(Chat과 Generative Pre-trained Transformer의 합성어)는 사용자와 주고받는 대화의 과정을 통해 질문에 답하도록 설계된 대형언어모델로, 지도학습과 강화학습을 모두 사용하여 세밀하게 조정된 인공지능 챗봇이다. ChatGPT는 주고받은 대화와 대화의 문맥을 기억할 수 있으며, 보고서나 실제로 작동하는 파이썬 코드를 비롯한 인간과 유사하게 상세하고 논리적인 글을 만들어 낼 수 있다고 알려져있다. 본 연구에서는 수자원시스템분야의 문제해결에 있어 ChatGPT의 적용가능성을 사례기반으로 확인하고, ChatGPT의 올바른 활용을 위해 필요한 사항에 대해 고찰하였다. 수자원시스템분야의 대표적인 연구주제인 상수관망시스템의 누수인지와 수리해석을 통한 문제해결에 ChatGPT를 활용하였다. 즉, 딥러닝 기반의 데이터분석을 활용한 누수인지와 오픈소스기반의 수리해석 모델을 활용한 관망시스템 적정 분석을 목표로 ChatGPT와 대화를 진행하고, ChatGPT에 의해 제안된 코드를 구동하여 결과를 분석하였다. ChatGPT가 제시한 코드의 구동결과를 사전에 연구자가 직접 구현한 코드구동 결과와 비교분석하였다. 분석결과 ChatGPT가 제시한 코드가 보다 더 간결할 수 있으며, 상대적으로 경쟁력 있는 결과를 도출하는 것을 확인하였다. 다만, 상대적으로 간결한 코드와 우수한 구동결과를 획득하기 위해서는 해당 도메인의 전문적 지식을 바탕으로 적절한 다수의 질문을 해야 하며, ChatGPT에 의해 작성된 코드의 의미를 명확히 해석하거나 비판적 분석을 하기 위해서는 전문가지식이 반드시 필요함을 알 수 있었다.

• Journal of the Korea Convergence Society
• /
• v.11 no.9
• /
• pp.7-13
• /
• 2020

With the recent World Health Organization (WHO) Declaration of Pandemic for Coronavirus Disease-19 (COVID-19), COVID-19 is a global concern and many deaths continue. To overcome this, there is an increasing need for sharing information between countries and countermeasures related to COVID-19. However, due to linguistic boundaries, smooth exchange and sharing of information has not been achieved. In this paper, we propose a Neural Machine Translation (NMT) model specialized for the COVID-19 domain. Centering on English, a Transformer based bidirectional model was produced for French, Spanish, German, Italian, Russian, and Chinese. Based on the BLEU score, the experimental results showed significant high performance in all language pairs compared to the commercialization system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.869-876
• /
• 2021

In the field of music, various AI composition methods using machine learning have recently been attempted. However, most of this research has been centered on Western music, and little research has been done on Korean traditional music. Therefore, in this paper, we will create a data set of Korean traditional music, create a melody using three algorithms based on the data set, and compare the results. Three models were selected based on the similarity between language and music, LSTM, Music Transformer and Self Attention. Using each of the three models, a melody generator was modeled and trained to generate melodies. As a result of user evaluation, the Self Attention method showed higher preference than the other methods. Data set is very important in AI composition. For this, a Korean traditional music data set was created, and AI composition was attempted with various algorithms, and this is expected to be helpful in future research on AI composition for Korean traditional music.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.662-667
• /
• 2022

Semantic role labeling task(SRL) is to extract predicate and arguments such as agent, patient, place, time. In the previously SRL task studies, a pipeline method extracting linguistic features of sentence has been proposed, but in this method, errors of each extraction work in the pipeline affect semantic role labeling performance. Therefore, methods using End-to-End neural network model have recently been proposed. In this paper, we propose a neural network model using the Biaffine Average Attention model for SRL task. The proposed model consists of a structure that can focus on the entire sentence information regardless of the distance between the predicate in the sentence and the arguments, instead of LSTM model that uses the surrounding information for prediction of a specific token proposed in the previous studies. For evaluation, we used F1 scores to compare two models based BERT model that proposed in existing studies using F1 scores, and found that 76.21% performance was higher than comparison models.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.488-495
• /
• 2021

We propose a speech recognition system based on conformer. Conformer is known to be convolution-augmented transformer, which combines transfer model for capturing global information with Convolution Neural Network (CNN) for exploiting local feature effectively. The baseline system is developed to be a transfer-based speech recognition using Long Short-Term Memory (LSTM)-based language model. The proposed system is a system which uses conformer instead of transformer with transformer-based language model. When Electronics and Telecommunications Research Institute (ETRI) speech corpus in AI-Hub is used for our evaluation, the proposed system yields 5.7 % of Character Error Rate (CER) while the baseline system results in 11.8 % of CER. Even though speech corpus is extended into other domain of AI-hub such as NHNdiguest speech corpus, the proposed system makes a robust performance for two domains. Throughout those experiments, we can prove a validation of the proposed system.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.11-22
• /
• 2022

Recently, research and development using various Artificial Intelligence (AI) technologies are being conducted in the field of education. Among the AI in Education (AIEd), conversational agents are not limited by time and space, and can learn more effectively by combining them with various AI technologies such as voice recognition and translation. This paper conducted a trend analysis on platforms that have a large number of users and used conversational agents for English learning among commercialized application. Currently commercialized educational platforms using conversational agent through trend analysis has several limitations and problems. To analyze specific problems and limitations, a comparative experiment was conducted with the latest pre-trained large-capacity dialogue model. Sensibleness and Specificity Average (SSA) human evaluation was conducted to evaluate conversational human-likeness. Based on the experiment, this paper propose the need for trained with large-capacity parameters dialogue models, educational data, and information retrieval functions for effective English conversation learning.