• 한국컴퓨터정보학회논문지
• /
• 제22권4호
• /
• pp.41-49
• /
• 2017

Word sense disambiguation(WSD) that determines the exact meaning of homonym which can be used in different meanings even in one form is very important to understand the semantical meaning of text document. Many recent researches on WSD have widely used NNLM(Neural Network Language Model) in which neural network is used to represent a document into vectors and to analyze its semantics. Among the previous WSD researches using NNLM, RNN(Recurrent Neural Network) model has better performance than other models because RNN model can reflect the occurrence order of words in addition to the word appearance information in a document. However, since RNN model uses only the forward order of word occurrences in a document, it is not able to reflect natural language's characteristics that later words can affect the meanings of the preceding words. In this paper, we propose a WSD scheme using Bidirectional RNN that can reflect not only the forward order but also the backward order of word occurrences in a document. From the experiments, the accuracy of the proposed model is higher than that of previous method using RNN. Hence, it is confirmed that bidirectional order information of word occurrences is useful for WSD in Korean language.

• 말소리와 음성과학
• /
• 제7권4호
• /
• pp.3-8
• /
• 2015

In this paper, we investigate an input dimension reduction method using continuous word vector in deep neural network language model. In the proposed method, continuous word vectors were generated by using Google's Word2Vec from a large training corpus to satisfy distributional hypothesis. 1-of-${\left|V\right|}$ coding discrete word vectors were replaced with their corresponding continuous word vectors. In our implementation, the input dimension was successfully reduced from 20,000 to 600 when a tri-gram language model is used with a vocabulary of 20,000 words. The total amount of time in training was reduced from 30 days to 14 days for Wall Street Journal training corpus (corpus length: 37M words).

• ETRI Journal
• /
• 제43권6호
• /
• pp.1038-1048
• /
• 2021

We propose an end-to-end neural coreference resolution for the Korean language that uses an attention mechanism to point to the same entity. Because Korean is a head-final language, we focused on a method that uses a pointer network based on the head. The key idea is to consider all nouns in the document as candidates based on the head-final characteristics of the Korean language and learn distributions over the referenced entity positions for each noun. Given the recent success of applications using bidirectional encoder representation from transformer (BERT) in natural language-processing tasks, we employed BERT in the proposed model to create word representations based on contextual information. The experimental results indicated that the proposed model achieved state-of-the-art performance in Korean language coreference resolution.

• 정보교육학회논문지
• /
• 제21권2호
• /
• pp.161-169
• /
• 2017

작성된 문서의 문법적 오류 교정을 할 때 맞춤법 검사기를 사용하는 것이 일반적이다. 그러나 초등학생들이 작성한 글 중에는 문법적으로는 옳더라도 자연스럽지 않은 문장이 있을 수 있다. 본 논문에서는 동일한 의미를 가진 2개의 문장이 주어졌을 때, 어떤 것이 더 자연스러운 문장인지 자동 판별할 수 있는 방법을 소개한다. 이 방법은 순환 신경망(recurrent neural network)을 이용하여 장기 의존성(long-term dependencies) 문제를 해결하고, 보조 단어(subword)를 사용하여 희소 단어(rare word) 문제를 해결한다. 약 200만 문장의 단일어 코퍼스를 통해 순환 신경망 기반 언어 모델을 학습하였다. 그 결과, 초등학생들이 주로 틀리는 표현들과 그에 대응하는 올바른 표현을 입력으로 주었을 때, 모든 경우에 대해 자연스러운 표현을 자동으로 선별할 수 있었다. 본 소프트웨어가 스마트 기기에 사용될 수 있는 형태로 구현된다면 실제 초등학교 현장에서 활용 가능할 것으로 기대된다.

• 한국빅데이터학회지
• /
• 제9권1호
• /
• pp.187-196
• /
• 2024

본 연구에서는 수어의 좌표를 압축하여 학습 시간을 획기적으로 단축시킬 수 있는 DNN (Deep Neural Network) 기반 수어 번역 모델을 제안하고 수어 좌표 압축 유무에 따른 정확도와 모델 학습 시간을 비교 분석하였다. 제안한 모델을 사용하여 수어를 번역한 결과, 수어 영상을 압축하기 전과 후의 정확도는 약 5.9% 감소한 반면, 학습 시간은 56.57% 감소하여 수어 번역 정확도 손실 대비 학습 시간에서 많은 이득을 얻는 것을 확인하였다.

• ETRI Journal
• /
• 제43권5호
• /
• pp.775-786
• /
• 2021

To translate in real time, a simultaneous translation system should determine when to stop reading source tokens and generate target tokens corresponding to a partial source sentence read up to that point. However, conventional attention-based neural machine translation (NMT) models cannot produce translations with adequate latency in online scenarios because they wait until a source sentence is completed to compute alignment between the source and target tokens. To address this issue, we propose a reinforced learning (RL)-based attention mechanism, the reinforced attention mechanism, which allows a neural translation model to jointly train the stopping criterion and a partial translation model. The proposed attention mechanism comprises two modules, one to ensure translation quality and the other to address latency. Different from previous RL-based simultaneous translation systems, which learn the stopping criterion from a fixed NMT model, the modules can be trained jointly with a novel reward function. In our experiments, the proposed model has better translation quality and comparable latency compared to previous models.

• International Journal of Advanced Culture Technology
• /
• 제7권4호
• /
• pp.327-333
• /
• 2019

Wind speed data constitute important weather information for aircrafts flying at low altitudes, such as drones. Currently, the accuracy of low altitude wind predictions is much lower than that of high-altitude wind predictions. Deep neural networks are proposed in this study as a method to improve wind speed forecast information. Deep neural networks mimic the learning process of the interactions among neurons in the brain, and it is used in various fields, such as recognition of image, sound, and texts, image and natural language processing, and pattern recognition in time-series. In this study, the deep neural network model is constructed using the wind prediction values generated by the numerical model as an input to improve the wind speed forecasts. Using the ground wind speed forecast data collected at the Boseong Meteorological Observation Tower, wind speed forecast values obtained by the numerical model are compared with those obtained by the model proposed in this study for the verification of the validity and compatibility of the proposed model.

• 정보과학회 논문지
• /
• 제43권8호
• /
• pp.878-882
• /
• 2016

이미지의 내용을 설명하는 캡션을 자동으로 생성하는 기술은 이미지 인식과 자연어처리 기술을 필요로 하는 매우 어려운 기술이지만, 유아 교육이나 이미지 검색, 맹인들을 위한 네비게이션 등에 사용될 수 있는 중요한 기술이다. 본 논문에서는 이미지 캡션 생성을 위해 Convolutional Neural Network(CNN)으로 인코딩된 이미지 정보를 입력으로 갖는 이미지 캡션 생성에 최적화된 Recurrent Neural Network(RNN) 모델을 제안하고, 실험을 통해 본 논문에서 제안한 모델이 Flickr 8K와 Flickr 30K, MS COCO 데이터 셋에서 기존의 연구들보다 높은 성능을 얻음을 보인다.

• Journal of information and communication convergence engineering
• /
• 제21권1호
• /
• pp.9-16
• /
• 2023

The natural language on social network platforms has a certain front-to-back dependency in structure, and the direct conversion of Chinese text into a vector makes the dimensionality very high, thereby resulting in the low accuracy of existing text classification methods. To this end, this study establishes a deep learning model that combines a big data ultra-deep convolutional neural network (UDCNN) and long short-term memory network (LSTM). The deep structure of UDCNN is used to extract the features of text vector classification. The LSTM stores historical information to extract the context dependency of long texts, and word embedding is introduced to convert the text into low-dimensional vectors. Experiments are conducted on the social network platforms Sogou corpus and the University HowNet Chinese corpus. The research results show that compared with CNN + rand, LSTM, and other models, the neural network deep learning hybrid model can effectively improve the accuracy of text classification.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.4958-4970
• /
• 2019

As technology advances, the amount of fake news is increasing more and more by various reasons such as political issues and advertisement exaggeration. However, there have been very few research works on fake news detection, especially which uses grammatical transformation on deep neural network. In this paper, we shall present a new Fake News Detection Model, called FAGON(Fake news detection model using Grammatical transformation On deep Neural network) which determines efficiently if the proposition is true or not for the given article by learning grammatical transformation on neural network. Especially, our model focuses the Korean language. It consists of two modules: sentence generator and classification. The former generates multiple sentences which have the same meaning as the proposition, but with different grammar by training the grammatical transformation. The latter classifies the proposition as true or false by training with vectors generated from each sentence of the article and the multiple sentences obtained from the former model respectively. We shall show that our model is designed to detect fake news effectively by exploiting various grammatical transformation and proper classification structure.