• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.479-483
• /
• 1996

본 논문은 구운 분석의 검색 영역 축소를 통한 구문 분석기의 성능 향상을 목적으로 connectionism을 이용한 부분 구문 인식기의 설계와 구현을 기술한다. 본 부분 구문 인식기는 형태소 분석된 문장으로부터 명사-주어부와 술어부를 인식함으로써 전체 검색 영역을 여러 부분으로 나누어 구문 분석문제를 축소시키는 것을 목적으로 하고 있다. Connectionist 모델은 입력층과 출력층으로 구성된 개선된 퍼셉트론 구조이며, 입/출력층 사이의 노드들을, 입력층 사이의 노드들을 연결하는 연결 강도(weight)가 존재한다. 명사-주어부 및 술어부 구문 태그를 connectionist 모델에 적용하며, 학습 알고리즘으로는 개선된 백프로퍼게이션 학습 알고리즘을 사용한다. 부분 구문 인식 실험은 112개 문장의 학습 코퍼스와 46개 문장의 실험 코퍼스에 대하여 85.7%와 80.4%의 정확한 명사-주어부 및 술어부 인식을, 94.6%와 95.7%의 명사-주어부와 술어부 사이의 올바른 경계 인식을 보여준다.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.32-46
• /
• 2023

Natural Language Processing (NLP) has grown tremendously in recent years. Typically, bilingual, and multilingual translation models have been deployed widely in machine translation and gained vast attention from the research community. On the contrary, few studies have focused on translating between spoken and sign languages, especially non-English languages. Prior works on Sign Language Translation (SLT) have shown that a mid-level sign gloss representation enhances translation performance. Therefore, this study presents a new large-scale Korean sign language dataset, the Museum-Commentary Korean Sign Gloss (MCKSG) dataset, including 3828 pairs of Korean sentences and their corresponding sign glosses used in Museum-Commentary contexts. In addition, we propose a translation framework based on self-supervised learning, where the pretext task is a text-to-text from a Korean sentence to its back-translation versions, then the pre-trained network will be fine-tuned on the MCKSG dataset. Using self-supervised learning help to overcome the drawback of a shortage of sign language data. Through experimental results, our proposed model outperforms a baseline BERT model by 6.22%.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.33 no.10
• /
• pp.48-52
• /
• 2015

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.631-653
• /
• 2020

Sign language is a natural, visually oriented and non-verbal communication channel between people that facilitates communication through facial/bodily expressions, postures and a set of gestures. It is basically used for communication with people who are deaf or hard of hearing. In order to understand such communication quickly and accurately, the design of a successful sign language translation system is considered in this paper. The proposed system includes object detection and classification stages. Firstly, Single Shot Multi Box Detection (SSD) architecture is utilized for hand detection, then a deep learning structure based on the Inception v3 plus Support Vector Machine (SVM) that combines feature extraction and classification stages is proposed to constructively translate the detected hand gestures. A sign language fingerspelling dataset is used for the design of the proposed model. The obtained results and comparative analysis demonstrate the efficiency of using the proposed hybrid structure in sign language translation.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.258-261
• /
• 2019

딥러닝을 이용한 Sequence to Sequence 모델의 등장과 Multi head Attention을 이용한 Transformer의 등장으로 기계번역에 많은 발전이 있었다. Transformer와 같은 성능이 좋은 모델들은 대량의 병렬 코퍼스를 가지고 학습을 진행하였는데 대량의 병렬 코퍼스를 구축하는 것은 시간과 비용이 많이 드는 작업이다. 이러한 단점을 극복하기 위하여 합성 코퍼스를 만드는 기법들이 연구되고 있으며 대표적으로 Back Translation 기법이 존재한다. Back Translation을 이용할 시 단일 언어 데이터를 가상 병렬 데이터로 변환하여 학습데이터의 양을 증가 시킨다. 즉 말뭉치 확장기법의 일종이다. 본 논문은 Back Translation 뿐만 아니라 Copied Translation 방식을 통한 다양한 실험을 통하여 데이터 증강기법이 기계번역 성능에 미치는 영향에 대해서 살펴본다. 실험결과 Back Translation과 Copied Translation과 같은 데이터 증강기법이 기계번역 성능향상에 도움을 줌을 확인 할 수 있었으며 Batch를 구성할 때 상대적 가중치를 두는 것이 성능향상에 도움이 됨을 알 수 있었다.

• Journal of the Korea Convergence Society
• /
• v.12 no.5
• /
• pp.1-7
• /
• 2021

In the latest trend of machine translation research, the model is pretrained through a large mono lingual corpus and then finetuned with a parallel corpus. Although many studies tend to increase the amount of data used in the pretraining stage, it is hard to say that the amount of data must be increased to improve machine translation performance. In this study, through an experiment based on the mBART model using parallel corpus filtering, we propose that high quality data can yield better machine translation performance, even utilizing smaller amount of data. We propose that it is important to consider the quality of data rather than the amount of data, and it can be used as a guideline for building a training corpus.

• Journal of Ocean Engineering and Technology
• /
• v.16 no.5
• /
• pp.61-65
• /
• 2002

The fault detection and diagnosis of rotating machinery widely used in plants including the ship are important for maintaining the performance of Plants. Recently, the wavelet transform has been recognized an efficient method to detect a little variation of physical quantities by the synchronous localization of time and frequency domains using the translation and dilation of signals. In this Paper, In order to develop efficient and reliable fault detection and diagnosis system rotating machines, the performance of wavelet transformation to detect a little variation of machine status and neural network to diagnose the cause of machine faults are investigated and experimented.

• Journal of Computing Science and Engineering
• /
• v.5 no.4
• /
• pp.305-313
• /
• 2011

Due to the expansion of high-speed Internet access, the need for secure and reliable networks has become more critical. The sophistication of network attacks, as well as their severity, has also increased recently. As such, more and more organizations are becoming vulnerable to attack. The aim of this research is to classify network attacks using neural networks (NN), which leads to a higher detection rate and a lower false alarm rate in a shorter time. This paper focuses on two classification types: a single class (normal, or attack), and a multi class (normal, DoS, PRB, R2L, U2R), where the category of attack is also detected by the NN. Extensive analysis is conducted in order to assess the translation of symbolic data, partitioning of the training data and the complexity of the architecture. This paper investigates two engines; the first engine is the back-propagation neural network intrusion detection system (BPNNIDS) and the second engine is the radial basis function neural network intrusion detection system (BPNNIDS). The two engines proposed in this paper are tested against traditional and other machine learning algorithms using a common dataset: the DARPA 98 KDD99 benchmark dataset from International Knowledge Discovery and Data Mining Tools. BPNNIDS shows a superior response compared to the other techniques reported in literature especially in terms of response time, detection rate and false positive rate.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.529-534
• /
• 2020

인공신경망 기반 기계번역(Neural Machine Translation, NMT)이란 딥러닝(Deep learning)을 이용하여 출발 언어의 문장을 도착 언어 문장으로 번역해주는 시스템을 일컫는다. NMT는 종단간 학습(end-to-end learning)을 이용하여 기존 기계번역 방법론의 성능을 앞지르며 기계번역의 주요 방법론으로 자리잡게 됐다. 이러한 발전에도 불구하고 여전히 개체(entity), 또는 전문 용어(terminological expressions)의 번역은 미해결 과제로 남아있다. 개체나 전문 용어는 대부분 명사로 구성되는데 문장 내 명사는 주체, 객체 등의 역할을 하는 중요한 요소이므로 이들의 정확한 번역이 문장 전체의 번역 성능 향상으로 이어질 수 있다. 따라서 본 논문에서는 지식그래프(Knowledge Graph)를 이용하여 심볼릭 지식을 NMT와 결합한 뉴럴심볼릭 방법론을 제안한다. 또한 지식그래프를 활용하여 NMT의 성능을 높인 선행 연구 방법론을 한영 기계번역에 이용할 수 있도록 구조를 설계한다.

• Journal of the Korea Convergence Society
• /
• v.12 no.7
• /
• pp.37-44
• /
• 2021

Quality estimation (QE) can evaluate the quality of machine translation output even for those who do not know the target language, and its high utilization highlights the need for QE. QE shared task is held every year at Conference on Machine Translation (WMT), and recently, researches applying Pretrained Language Model (PLM) are mainly being conducted. In this paper, we conduct a survey on the QE task and research trends, and we summarize the features of PLM. In addition, we used a multilingual BART model that has not yet been utilized and performed comparative analysis with the existing studies such as XLM, multilingual BERT, and XLM-RoBERTa. As a result of the experiment, we confirmed which PLM was most effective when applied to QE, and saw the possibility of applying the multilingual BART model to the QE task.