• 제목/요약/키워드: AttentionBiLSTM

검색결과 24건 처리시간 0.018초

DG-based SPO tuple recognition using self-attention M-Bi-LSTM

  • Jung, Joon-young
    • ETRI Journal
    • /
    • 제44권3호
    • /
    • pp.438-449
    • /
    • 2022
  • This study proposes a dependency grammar-based self-attention multilayered bidirectional long short-term memory (DG-M-Bi-LSTM) model for subject-predicate-object (SPO) tuple recognition from natural language (NL) sentences. To add recent knowledge to the knowledge base autonomously, it is essential to extract knowledge from numerous NL data. Therefore, this study proposes a high-accuracy SPO tuple recognition model that requires a small amount of learning data to extract knowledge from NL sentences. The accuracy of SPO tuple recognition using DG-M-Bi-LSTM is compared with that using NL-based self-attention multilayered bidirectional LSTM, DG-based bidirectional encoder representations from transformers (BERT), and NL-based BERT to evaluate its effectiveness. The DG-M-Bi-LSTM model achieves the best results in terms of recognition accuracy for extracting SPO tuples from NL sentences even if it has fewer deep neural network (DNN) parameters than BERT. In particular, its accuracy is better than that of BERT when the learning data are limited. Additionally, its pretrained DNN parameters can be applied to other domains because it learns the structural relations in NL sentences.

Encoding Dictionary Feature for Deep Learning-based Named Entity Recognition

  • Ronran, Chirawan;Unankard, Sayan;Lee, Seungwoo
    • International Journal of Contents
    • /
    • 제17권4호
    • /
    • pp.1-15
    • /
    • 2021
  • Named entity recognition (NER) is a crucial task for NLP, which aims to extract information from texts. To build NER systems, deep learning (DL) models are learned with dictionary features by mapping each word in the dataset to dictionary features and generating a unique index. However, this technique might generate noisy labels, which pose significant challenges for the NER task. In this paper, we proposed DL-dictionary features, and evaluated them on two datasets, including the OntoNotes 5.0 dataset and our new infectious disease outbreak dataset named GFID. We used (1) a Bidirectional Long Short-Term Memory (BiLSTM) character and (2) pre-trained embedding to concatenate with (3) our proposed features, named the Convolutional Neural Network (CNN), BiLSTM, and self-attention dictionaries, respectively. The combined features (1-3) were fed through BiLSTM - Conditional Random Field (CRF) to predict named entity classes as outputs. We compared these outputs with other predictions of the BiLSTM character, pre-trained embedding, and dictionary features from previous research, which used the exact matching and partial matching dictionary technique. The findings showed that the model employing our dictionary features outperformed other models that used existing dictionary features. We also computed the F1 score with the GFID dataset to apply this technique to extract medical or healthcare information.

Comparative Analysis of RNN Architectures and Activation Functions with Attention Mechanisms for Mars Weather Prediction

  • Jaehyeok Jo;Yunho Sin;Bo-Young Kim;Jihoon Moon
    • 한국컴퓨터정보학회논문지
    • /
    • 제29권10호
    • /
    • pp.1-9
    • /
    • 2024
  • 본 연구는 화성 기상 데이터를 대상으로 활성화 함수와 어텐션 메커니즘이 시계열 모델의 성능에 미치는 영향을 평가하기 위해 비교 및 분석한다. 화성의 기상 데이터는 대기 밀도가 낮고, 급격한 온도 변동 및 복잡한 지형 등으로 인해 비선형적이고 불규칙적이다. 본 연구에서는 LSTM, BiLSTM, GRU, BiGRU 아키텍처를 사용하여 다양한 활성화 함수와 어텐션 메커니즘의 효과를 평가한다. 실험에 사용된 활성화 함수는 ReLU, Leaky ReLU, ELU, GELU, Swish, SELU이며, 모델 성능은 MAE와 RMSE 지표로 측정된다. 실험 결과, 어텐션 메커니즘을 통합함으로써 MAE와 RMSE가 모두 향상되었으며, Swish와 ReLU는 최저 온도 예측에서 가장 우수한 성능을 보였다. 반면, GELU와 ELU는 기압 예측에서 성능이 저하되었다. 이러한 결과는 복잡한 시계열 예측의 모델 정확도를 향상하기 위해 적절한 활성 함수와 어텐션 메커니즘을 선택하는 것이 중요함을 보여준다.

Bi-LSTM 모델을 이용한 음악 생성 시계열 예측 (Prediction of Music Generation on Time Series Using Bi-LSTM Model)

  • 김광진;이칠우
    • 스마트미디어저널
    • /
    • 제11권10호
    • /
    • pp.65-75
    • /
    • 2022
  • 딥러닝은 기존의 분석 모델이 갖는 한계를 극복하고 텍스트, 이미지, 음악 등 다양한 형태의 결과물을 생성할 수 있는 창의적인 도구로 활용되고 있다. 본 고에서는 Niko's MIDI Pack 음원 파일 1,609개를 데이터 셋으로 삼아 전처리 과정을 수행하고, 양방향 장단기 기억 순환 신경망(Bi-LSTM) 모델을 이용하여, 효율적으로 음악을 생성할 수 있는 전처리 방법과 예측 모델을 제시한다. 생성되는 으뜸음을 바탕으로 음악적 조성(調聲)에 적합한 새로운 시계열 데이터를 생성할 수 있도록 은닉층을 다층화하고, 디코더의 출력 게이트에서 인코더의 입력 데이터 중 영향을 주는 요소의 가중치를 적용하는 어텐션(Attention) 메커니즘을 적용한다. LSTM 모델의 인식률 향상을 위한 파라미터로서 손실함수, 최적화 방법 등 설정 변수들을 적용한다. 제안 모델은 MIDI 학습의 효율성 제고 및 예측 향상을 위해 높은음자리표(treble clef)와 낮은음자리표(bass clef)를 구분하여 추출된 음표, 음표의 길이, 쉼표, 쉼표의 길이와 코드(chord) 등을 적용한 다채널 어텐션 적용 양방향 기억 모델(Bi-LSTM with attention)이다. 학습의 결과는 노이즈와 구별되는 음악의 전개에 어울리는 음표와 코드를 생성하며, 화성학적으로 안정된 음악을 생성하는 모델을 지향한다.

Applying a Novel Neuroscience Mining (NSM) Method to fNIRS Dataset for Predicting the Business Problem Solving Creativity: Emphasis on Combining CNN, BiLSTM, and Attention Network

  • Kim, Kyu Sung;Kim, Min Gyeong;Lee, Kun Chang
    • 한국컴퓨터정보학회논문지
    • /
    • 제27권8호
    • /
    • pp.1-7
    • /
    • 2022
  • 인공지능 기술이 발달하면서 뉴로사이언스 마이닝(NSM: NeuroScience Mining)과 AI를 접목하려는 시도가 증가하고 있다. 나아가 NSM은 뉴로사이언스와 비즈니스 애널리틱스의 결합으로 인해 연구범위가 확장되고 있다. 본 연구에서는 fNIRS 실험을 통해 확보한 뉴로 데이터를 분석하여 비즈니스 문제 해결 창의성(BPSC: business problem-solving creativity)을 예측하고 이를 통해 NSM의 잠재력을 조사한다. BPSC는 비즈니스에서 차별성을 가지게 하는 중요한 요소이지만, 인지적 자원의 하나인 BPSC의 측정 및 예측에는 한계가 존재한다. 본 논문에서는 BPSC 예측 성능을 높이는 방안으로 CNN, BiLSTM 그리고 어텐션 네트워크를 결합한 새로운 NSM 기법을 제안한다. 제안된 NSM 기법을 15만 개 이상의 fNIRS 데이터를 활용하여 유효성을 입증하였다. 연구 결과, 본 논문에서 제안하는 NSM 방법이 벤치마킹한 알고리즘(CNN, BiLSTM)에 비하여 우수한 성능을 가지는 것으로 나타났다.

Predicting Stock Prices Based on Online News Content and Technical Indicators by Combinatorial Analysis Using CNN and LSTM with Self-attention

  • Sang Hyung Jung;Gyo Jung Gu;Dongsung Kim;Jong Woo Kim
    • Asia pacific journal of information systems
    • /
    • 제30권4호
    • /
    • pp.719-740
    • /
    • 2020
  • The stock market changes continuously as new information emerges, affecting the judgments of investors. Online news articles are valued as a traditional window to inform investors about various information that affects the stock market. This paper proposed new ways to utilize online news articles with technical indicators. The suggested hybrid model consists of three models. First, a self-attention-based convolutional neural network (CNN) model, considered to be better in interpreting the semantics of long texts, uses news content as inputs. Second, a self-attention-based, bi-long short-term memory (bi-LSTM) neural network model for short texts utilizes news titles as inputs. Third, a bi-LSTM model, considered to be better in analyzing context information and time-series models, uses 19 technical indicators as inputs. We used news articles from the previous day and technical indicators from the past seven days to predict the share price of the next day. An experiment was performed with Korean stock market data and news articles from 33 top companies over three years. Through this experiment, our proposed model showed better performance than previous approaches, which have mainly focused on news titles. This paper demonstrated that news titles and content should be treated in different ways for superior stock price prediction.

MalEXLNet:A semantic analysis and detection method of malware API sequence based on EXLNet model

  • Xuedong Mao;Yuntao Zhao;Yongxin Feng;Yutao Hu
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제18권10호
    • /
    • pp.3060-3083
    • /
    • 2024
  • With the continuous advancements in malicious code polymorphism and obfuscation techniques, the performance of traditional machine learning-based detection methods for malware variant detection has gradually declined. Additionally, conventional pre-trained models could adequately capture the contextual semantic information of malicious code and appropriately represent polysemous words. To enhance the efficiency of malware variant detection, this paper proposes the MalEXLNet intelligent semantic analysis and detection architecture for malware. This architecture leverages malware API call sequences and employs an improved pre-training model for semantic vector representation, effectively utilizing the semantic information of API call sequences. It constructs a hybrid deep learning model, CBAM+AttentionBiLSTM,CBAM+AttentionBiLSTM, for training and classification prediction. Furthermore, incorporating the KMeansSMOTE algorithm achieves balanced processing of small sample data, ensuring the model maintains robust performance in detecting malicious variants from rare malware families. Comparative experiments on generalized datasets, Ember and Catak, the results show that the proposed MalEXLNet architecture achieves excellent performance in malware classification and detection tasks, with accuracies of 98.85% and 94.46% in the two datasets, and macro-averaged and micro-averaged metrics exceeding 98% and 92%, respectively.

Self-Attention을 적용한 문장 임베딩으로부터 이미지 생성 연구 (A Study on Image Generation from Sentence Embedding Applying Self-Attention)

  • 유경호;노주현;홍택은;김형주;김판구
    • 스마트미디어저널
    • /
    • 제10권1호
    • /
    • pp.63-69
    • /
    • 2021
  • 사람이 어떤 문장을 보고 그 문장에 대해 이해하는 것은 문장 안에서 주요한 단어를 이미지로 연상시켜 그 문장에 대해 이해한다. 이러한 연상과정을 컴퓨터가 할 수 있도록 하는 것을 text-to-image라고 한다. 기존 딥 러닝 기반 text-to-image 모델은 Convolutional Neural Network(CNN)-Long Short Term Memory(LSTM), bi-directional LSTM을 사용하여 텍스트의 특징을 추출하고, GAN에 입력으로 하여 이미지를 생성한다. 기존 text-to-image 모델은 텍스트 특징 추출에서 기본적인 임베딩을 사용하였으며, 여러 모듈을 사용하여 이미지를 생성하므로 학습 시간이 오래 걸린다. 따라서 본 연구에서는 자연어 처리분야에서 성능 향상을 보인 어텐션 메커니즘(Attention Mechanism)을 문장 임베딩에 사용하여 특징을 추출하고, 추출된 특징을 GAN에 입력하여 이미지를 생성하는 방법을 제안한다. 실험 결과 기존 연구에서 사용되는 모델보다 inception score가 높았으며 육안으로 판단하였을 때 입력된 문장에서 특징을 잘 표현하는 이미지를 생성하였다. 또한, 긴 문장이 입력되었을 때에도 문장을 잘 표현하는 이미지를 생성하였다.

Video Saliency Detection Using Bi-directional LSTM

  • Chi, Yang;Li, Jinjiang
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제14권6호
    • /
    • pp.2444-2463
    • /
    • 2020
  • Significant detection of video can more rationally allocate computing resources and reduce the amount of computation to improve accuracy. Deep learning can extract the edge features of the image, providing technical support for video saliency. This paper proposes a new detection method. We combine the Convolutional Neural Network (CNN) and the Deep Bidirectional LSTM Network (DB-LSTM) to learn the spatio-temporal features by exploring the object motion information and object motion information to generate video. A continuous frame of significant images. We also analyzed the sample database and found that human attention and significant conversion are time-dependent, so we also considered the significance detection of video cross-frame. Finally, experiments show that our method is superior to other advanced methods.

Feature Selection with Ensemble Learning for Prostate Cancer Prediction from Gene Expression

  • Abass, Yusuf Aleshinloye;Adeshina, Steve A.
    • International Journal of Computer Science & Network Security
    • /
    • 제21권12spc호
    • /
    • pp.526-538
    • /
    • 2021
  • Machine and deep learning-based models are emerging techniques that are being used to address prediction problems in biomedical data analysis. DNA sequence prediction is a critical problem that has attracted a great deal of attention in the biomedical domain. Machine and deep learning-based models have been shown to provide more accurate results when compared to conventional regression-based models. The prediction of the gene sequence that leads to cancerous diseases, such as prostate cancer, is crucial. Identifying the most important features in a gene sequence is a challenging task. Extracting the components of the gene sequence that can provide an insight into the types of mutation in the gene is of great importance as it will lead to effective drug design and the promotion of the new concept of personalised medicine. In this work, we extracted the exons in the prostate gene sequences that were used in the experiment. We built a Deep Neural Network (DNN) and Bi-directional Long-Short Term Memory (Bi-LSTM) model using a k-mer encoding for the DNA sequence and one-hot encoding for the class label. The models were evaluated using different classification metrics. Our experimental results show that DNN model prediction offers a training accuracy of 99 percent and validation accuracy of 96 percent. The bi-LSTM model also has a training accuracy of 95 percent and validation accuracy of 91 percent.