scholarly journals Text Sentiment Analysis of German Multilevel Features Based on Self-Attention Mechanism

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Xiang Li
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Feature Representation ◽  
The Self ◽  
Word Level ◽  
Sentence Level ◽  
Improvement Effect ◽  
Representation Method ◽  
Text Sentiment Analysis ◽  
Deep Learning Model

In this paper, we propose a multilevel feature representation method that combines word-level features, such as German morphology and slang, and sentence-level features, such as special symbols and English-translated sentiment information, and build a deep learning model for German sentiment classification based on the self-attentive mechanism, in order to address the characteristics of German social media texts that are colloquial, irregular, and diverse. Compared with the existing studies, this model not only has the most obvious improvement effect but also has better feature extraction and classification ability for German emotion.

scholarly journals Deep-Learning-Based Detection of Infants with Autism Spectrum Disorder Using Auto-Encoder Feature Representation

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6762
Author(s):  
Jung Hyuk Lee ◽  
Geon Woo Lee ◽  
Guiyoung Bong ◽  
Hee Jeong Yoo ◽  
Hong Kook Kim
Keyword(s):  
Autism Spectrum Disorder ◽  
Feature Extraction ◽  
Deep Learning ◽  
Autism Spectrum ◽  
Feature Representation ◽  
Diagnostic Methods ◽  
Spectrum Disorder ◽  
Joint Optimization ◽  
Data Set ◽  
Children With Asd

Autism spectrum disorder (ASD) is a developmental disorder with a life-span disability. While diagnostic instruments have been developed and qualified based on the accuracy of the discrimination of children with ASD from typical development (TD) children, the stability of such procedures can be disrupted by limitations pertaining to time expenses and the subjectivity of clinicians. Consequently, automated diagnostic methods have been developed for acquiring objective measures of autism, and in various fields of research, vocal characteristics have not only been reported as distinctive characteristics by clinicians, but have also shown promising performance in several studies utilizing deep learning models based on the automated discrimination of children with ASD from children with TD. However, difficulties still exist in terms of the characteristics of the data, the complexity of the analysis, and the lack of arranged data caused by the low accessibility for diagnosis and the need to secure anonymity. In order to address these issues, we introduce a pre-trained feature extraction auto-encoder model and a joint optimization scheme, which can achieve robustness for widely distributed and unrefined data using a deep-learning-based method for the detection of autism that utilizes various models. By adopting this auto-encoder-based feature extraction and joint optimization in the extended version of the Geneva minimalistic acoustic parameter set (eGeMAPS) speech feature data set, we acquire improved performance in the detection of ASD in infants compared to the raw data set.

Deep Learning-Based Lane Marking Detection using A2-LMDet

2020 ◽  
Vol 2674 (11) ◽  
pp. 625-635
Author(s):  
Chunmian Lin ◽  
Lin Li ◽  
Zhixing Cai ◽  
Kelvin C. P. Wang ◽  
Danny Xiao ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Pavement Management ◽  
Feature Representation ◽  
Imaging Data ◽  
Lane Marking ◽  
Accurate Performance ◽  
And Performance ◽  
The One

Automated lane marking detection is essential for advanced driver assistance system (ADAS) and pavement management work. However, prior research has mostly detected lane marking segments from a front-view image, which easily suffers from occlusion or noise disturbance. In this paper, we aim at accurate and robust lane marking detection from a top-view perspective, and propose a deep learning-based detector with adaptive anchor scheme, referred to as A2-LMDet. On the one hand, it is an end-to-end framework that fuses feature extraction and object detection into a single deep convolutional neural network. On the other hand, the adaptive anchor scheme is designed by formulating a bilinear interpolation algorithm, and is used to guide specific-anchor box generation and informative feature extraction. To validate the proposed method, a newly built lane marking dataset contained 24,000 high-resolution laser imaging data is further developed for case study. Quantitative and qualitative results demonstrate that A2-LMDet achieves highly accurate performance with 0.9927 precision, 0.9612 recall, and a 0.9767 [Formula: see text] score, which outperforms other advanced methods by a considerable margin. Moreover, ablation analysis illustrates the effectiveness of the adaptive anchor scheme for enhancing feature representation and performance improvement. We expect our work will help the development of related research.

scholarly journals Deep learning model for metagenome fragment classification using spaced k-mers feature extraction

2020 ◽  
Vol 8 (3) ◽  
pp. 234-238
Author(s):  
Nur Choiriyati ◽  
Yandra Arkeman ◽  
Wisnu Ananta Kusuma
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Deep Learning ◽  
Language Processing ◽  
Computational Time ◽  
Genus Level ◽  
Computational Resources ◽  
Learning Architectures ◽  
Deep Learning Model

An open challenge in bioinformatics is the analysis of the sequenced metagenomes from the various environments. Several studies demonstrated bacteria classification at the genus level using k-mers as feature extraction where the highest value of k gives better accuracy but it is costly in terms of computational resources and computational time. Spaced k-mers method was used to extract the feature of the sequence using 111 1111 10001 where 1 was a match and 0 was the condition that could be a match or did not match. Currently, deep learning provides the best solutions to many problems in image recognition, speech recognition, and natural language processing. In this research, two different deep learning architectures, namely Deep Neural Network (DNN) and Convolutional Neural Network (CNN), trained to approach the taxonomic classification of metagenome data and spaced k-mers method for feature extraction. The result showed the DNN classifier reached 90.89 % and the CNN classifier reached 88.89 % accuracy at the genus level taxonomy.

scholarly journals A Geometry-Based Deep Learning Feature Extraction Scheme for Airfoils

2021 ◽  
Author(s):  
Yu Xiang ◽  
Liwei Hu ◽  
Jun Zhang ◽  
Wenyong Wang
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Feature Fusion ◽  
Feature Representation ◽  
Geometrical Meaning ◽  
Latent Features ◽  
Geometry Feature ◽  
Extraction Scheme ◽  
Geometry Parameter ◽  
Coordinate Data

Abstract The perception of geometry-features of airfoils is the basis in aerodynamic area for performance prediction, parameterization, aircraft inverse design, etc. There are three approaches to percept the geometric shape of an airfoil, namely manual design of airfoil geometry parameter, polynomial definition and deep learning. The first two methods can directly extract geometry-features of airfoils or polynomial equations of airfoil curves, but the number of features extracted is limited. While deep learning algorithms can extract a large number of potential features (called latent features), however, the features extracted by deep learning are lacking of explicit geometrical meaning. Motivated by the advantages of polynomial definition and deep learning, we propose a geometry-based deep learning feature extraction scheme (named Bézier-based feature extraction, BFE) for airfoils, which consists of two parts: manifold metric feature extraction and geometry-feature fusion encoder (GF encoder). Manifold metric feature extraction, with the help of the Bézier curve, captures features from tangent space of airfoil curves, and GF encoder combines airfoil coordinate data and manifold metrics together to form a novel feature representation. A public UIUC airfoil dataset is used to verify the proposed BFE. Compared with classic Auto-Encoder, the mean square error (MSE) of BFE is reduced by 17.97% ~29.14%.

scholarly journals Students’ Self Revision in Essay Writing

2017 ◽  
Vol 3 (2) ◽  
pp. 39-44
Author(s):  
Mohammad Febryanto
Keyword(s):  
The Self ◽  
Word Form ◽  
Essay Writing ◽  
Word Level ◽  
Sentence Level

This study investigates self-revision in essay writing conducted by 6 students. The analysis is based ondetermining common revised errors. The data have been reduced based on Language Related Episodes (LREs). The result shows that there are revision consisting of 1 change in punctuation both in first and second essay, 5 changes spelling in first essay, 19 changes vocabulary in the first essay and 6 changes in second essay, 25 changes in word form correction in the first essay and 27 changes in the second essay, and there are 19 changes in sentence level the first essay and 13 changes in the second one. This indicates that the self-revision is predominantly focused onthe word level changes particularly in morphology. Keywords: self-revision, common revised errors, Language Related Episodes (LREs)

scholarly journals Semantic-Preserving Adversarial Text Attacks

2021 ◽  
Author(s):  
Xinghao Yang ◽  
Yongshun Gong ◽  
Weifeng Liu ◽  
JAMES BAILEY ◽  
Tianqing Zhu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Potential Candidate ◽  
Success Rates ◽  
Learning Models ◽  
Text Documents ◽  
Word Level ◽  
Sentence Level ◽  
Adversarial Attack ◽  
Semantic Preservation ◽  
Adversarial Example

Deep learning models are known immensely brittle to adversarial image examples, yet their vulnerability in text classification is insufficiently explored. Existing text adversarial attack strategies can be roughly divided into three categories, i.e., character-level attack, word-level attack, and sentence-level attack. Despite the success brought by recent text attack methods, how to induce misclassification with the minimal text modifications while keeping the lexical correctness, syntactic soundness, and semantic consistency simultaneously is still a challenge. To examine the vulnerability of deep models, we devise a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) approach which attacks text documents not only at a unigram word level but also at a bigram level to avoid generating meaningless sentences. We also present a hybrid attack strategy that collects substitution words from both synonyms and sememe candidates, to enrich the potential candidate set. Besides, a Semantic Preservation Optimization (SPO) method is devised to determine the word substitution priority and reduce the perturbation cost. Furthermore, we constraint the SPO with a semantic Filter (dubbed SPOF) to improve the semantic similarity between the input text and the adversarial example. To estimate the effectiveness of our proposed methods, BU-SPO and BU-SPOF, we attack four victim deep learning models trained on three real-world text datasets. Experimental results demonstrate that our approaches accomplish the highest semantics consistency and attack success rates by making the minimal word modifications compared with competitive methods.

scholarly journals Semantic-Preserving Adversarial Text Attacks

2021 ◽  
Author(s):  
Xinghao Yang ◽  
Yongshun Gong ◽  
Weifeng Liu ◽  
JAMES BAILEY ◽  
Tianqing Zhu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Potential Candidate ◽  
Success Rates ◽  
Learning Models ◽  
Text Documents ◽  
Word Level ◽  
Sentence Level ◽  
Adversarial Attack ◽  
Semantic Preservation ◽  
Adversarial Example

Deep learning models are known immensely brittle to adversarial image examples, yet their vulnerability in text classification is insufficiently explored. Existing text adversarial attack strategies can be roughly divided into three categories, i.e., character-level attack, word-level attack, and sentence-level attack. Despite the success brought by recent text attack methods, how to induce misclassification with the minimal text modifications while keeping the lexical correctness, syntactic soundness, and semantic consistency simultaneously is still a challenge. To examine the vulnerability of deep models, we devise a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) approach which attacks text documents not only at a unigram word level but also at a bigram level to avoid generating meaningless sentences. We also present a hybrid attack strategy that collects substitution words from both synonyms and sememe candidates, to enrich the potential candidate set. Besides, a Semantic Preservation Optimization (SPO) method is devised to determine the word substitution priority and reduce the perturbation cost. Furthermore, we constraint the SPO with a semantic Filter (dubbed SPOF) to improve the semantic similarity between the input text and the adversarial example. To estimate the effectiveness of our proposed methods, BU-SPO and BU-SPOF, we attack four victim deep learning models trained on three real-world text datasets. Experimental results demonstrate that our approaches accomplish the highest semantics consistency and attack success rates by making the minimal word modifications compared with competitive methods.

Sign in / Sign up

Export Citation Format

Share Document