Filters








13,653 Hits in 5.6 sec

A Neural Network Model for Semi-supervised Review Aspect Identification [chapter]

Ying Ding, Changlong Yu, Jing Jiang
2017 Lecture Notes in Computer Science  
In this work, we propose a neural network model to identify aspects from reviews by learning their distributional vectors.  ...  Furthermore, to leverage review sentences labeled with aspect words, a sequence labeler based on Recurrent Neural Networks (RNNs) is incorporated into our neural network.  ...  We would like to explore how these trained neural network models can be used to help the aspect identification task. In this work, we propose a neural network model for review aspect identification.  ... 
doi:10.1007/978-3-319-57529-2_52 fatcat:wt35r2nrsra4tm43yglcevkarq

Multi-modal Network Representation Learning

Chuxu Zhang, Meng Jiang, Xiangliang Zhang, Yanfang Ye, Nitesh V. Chawla
2020 Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining  
In this tutorial, we systematically review the area of multi-modal network representation learning, including a series of recent methods and applications.  ...  These methods will be categorized and introduced in the perspectives of unsupervised, semi-supervised and supervised learning, with corresponding real applications respectively.  ...  Therefore, semi-supervised representation learning for multi-model networks becomes a highly demanding, while barely explored technique.  ... 
doi:10.1145/3394486.3406475 fatcat:vbnikhs53ndczblj2nepa5nq2y

Deep semi-supervised learning with weight map for review helpfulness prediction

Hua Yin, Zhensheng Hu, Yahui Peng, Zhijian Wang, Guanglong Xu, Yanfang Xu
2021 Computer Science and Information Systems  
Based on this novel model, we develop an algorithm and conduct a series of experiments, on Amazon Review Dataset, from the aspects of the baseline neural network selection and the strategies comparisons  ...  Therefore, we propose an end-to-end deep semi-supervised learning model with weight map, which makes full use of the unlabeled reviews.  ...  Methodology In this paper, A deep semi-supervised learning method is proposed for review helpfulness prediction.  ... 
doi:10.2298/csis201228044y fatcat:k6uckcdfkvalxop2gk7bh24pdi

Systematic Review on Implicit and Explicit Aspect Extraction in Sentiment Analysis

Jaafar Zubairu Maitama, Norisma Idris, Asad Abdi, Liyana Shuib, Rosmadi Fauzi
2020 IEEE Access  
Example of the semi-supervised techniques is, Recurrent Neural Network (RNN) in [41] , [42] for explicit aspects, semanticbased in [43] for implicit aspects, and lexicon-based [44] , [45] for a  ...  Conditional Random Field (CRF) Supervised [113]; [114] 2. Recurrent Neural Network (RNN) Semi-supervised [115] 3. Hierarchy Supervised [115] 4.  ...  Apart from that, he also actively appeared in the mass media, a writer for local newspapers and an invited speaker on political, social, economic and current issues in the country.  ... 
doi:10.1109/access.2020.3031217 fatcat:vosmjncbe5h6lfaoucmjy2yxq4

Sentiment Analysis Tools and Techniques: A Comprehensive Survey

Maria Christina Barretto
2017 International Journal for Research in Applied Science and Engineering Technology  
The paper presents a comprehensive survey about various techniques and tools used for sentiment analysis with some newer approaches like sentiment analysis using LDA.  ...  Semantic analysis plays a very important role in decision making process. Due to increase in web technologies a large amount of data gets generated.  ...  each of the seed words 3) Semi Supervised learning: Semi supervised learning [3] is a class of supervised learning tasks that makes use of unlabelled data for training.  ... 
doi:10.22214/ijraset.2017.11419 fatcat:ab4ffzhdhvd3lb7sczabrmqrcm

Evaluation and Comparison of Deep Learning Methods for Pavement Crack Identification with Visual Images [article]

Kai-Liang Lu
2021 arXiv   pre-print
the evolution of convolutional neural network (CNN) backbone models and GAN models were summarized.  ...  Furthermore, a weakly supervised learning framework of combined TL-SSGAN and its performance enhancement measures are proposed, which can maintain comparable crack identification performance with that  ...  reviewed, then the evolution of CNN backbone models and GAN models were summarized.  ... 
arXiv:2112.10390v1 fatcat:qloaldo325gkdaglm65nmewz2q

Semi-supervised Feature Learning For Improving Writer Identification [article]

Shiming Chen, Yisong Wang, Chin-Teng Lin, Weiping Ding, Zehong Cao
2018 arXiv   pre-print
In this study, a semi-supervised feature learning pipeline was proposed to improve the performance of writer identification by training with extra unlabeled data and the original labeled data simultaneously  ...  Data augmentation is usually used by supervised learning approaches for offline writer identification, but such approaches require extra training data and potentially lead to overfitting errors.  ...  Our results show that the proposed semi-supervised learning model had a consistent improvement over the deep residual neural network baseline and achieved better performance than existing approaches on  ... 
arXiv:1807.05490v3 fatcat:dfxtdkumiffetbtpoye4jp35te

Systematic reviews in sentiment analysis: a tertiary study

Alexander Ligthart, Cagatay Catal, Bedir Tekinerdogan
2021 Artificial Intelligence Review  
The outcome of this tertiary study provides a comprehensive overview of the key topics and the different approaches for a variety of tasks in sentiment analysis.  ...  Different features, algorithms, and datasets used in sentiment analysis models are mapped.  ...  Xu and Tan (2019) proposed the target-oriented semi-supervised sequential generative model (TSSGM) for target-oriented aspect-based sentiment analysis and showed that this approach outperforms two semi-supervised  ... 
doi:10.1007/s10462-021-09973-3 fatcat:zo7igc4fnnh47kyafncbfmaf3u

Special Issue Editorial: Cognitively-Inspired Computing for Knowledge Discovery

Kaizhu Huang, Rui Zhang, Xiaobo Jin, Amir Hussain
2018 Cognitive Computation  
In particular, current neural networks strongly rely on a large amount of data for good performance and lack effective mechanisms to differentiate input samples from outliers.  ...  Neural networks, especially deep neural networks, have achieved great success in a range of fields including pattern recognition, computer vision, and natural language processing.  ...  Motivated by this phenomenon, Ding et al. design a novel manifold regularized model to solve semi-supervised learning in an incremental or online way.  ... 
doi:10.1007/s12559-017-9532-y fatcat:64jcrljij5d6xgqjemgijftp7m

Predicting Helpfulness of Online Reviews [article]

Abdalraheem Alsmadi, Shadi AlZu'bi, Mahmoud Al-Ayyoub, Yaser Jararweh
2020 arXiv   pre-print
Mainly, three approaches are used: a supervised learning approach (using ML as well as deep learning (DL) models), a semi-supervised approach (that combines DL models with word embeddings), and pre-trained  ...  Moreover, the semi-supervised has a remarkable performance compared with the other ones.  ...  Acknowledgement The authors would like to thank the Deanship of Research at the Jordan University of Science and Technology for supporting this work (Grant #20180193).  ... 
arXiv:2008.10129v1 fatcat:5fvw4ofoazbodo2kck4ia6pjru

Co-Training for Visual Object Recognition Based on Self-Supervised Models Using a Cross-Entropy Regularization

Gabriel Díaz, Billy Peralta, Luis Caro, Orietta Nicolis
2021 Entropy  
In this work, we propose a co-training model for visual object recognition using deep neural networks by adding layers of self-supervised neural networks as intermediate inputs to the views, where the  ...  An alternative is to use semi-supervised models, such as co-training, where multiple complementary views are combined using a small amount of labeled data.  ...  Therefore, a reasonable way to use the information from the unlabeled data is through semi-supervised learning. A detailed review of semi-supervised algorithms can be found in [9] .  ... 
doi:10.3390/e23040423 pmid:33916017 fatcat:ajfzk2s2b5hbpopngxh6igngsi

Deep Learning for Anomaly Detection: A Survey [article]

Raghavendra Chalapathy (University of Sydney and Capital Markets Cooperative Research Centre, Sanjay Chawla (Qatar Computing Research Institute
2019 arXiv   pre-print
Furthermore, we review the adoption of these methods for anomaly across various application domains and assess their effectiveness.  ...  The aim of this survey is two-fold, firstly we present a structured and comprehensive overview of research methods in deep learning-based anomaly detection.  ...  A review of deep learning based semi-supervised techniques for anomaly detection is presented by Kiran et al. [2018] and . DAD techniques learn a discriminative boundary around the normal instances.  ... 
arXiv:1901.03407v2 fatcat:x3tb4ccxfvdkfo7k2y2oxhr7ly

Sarcasm Detection: A Comparative Study [article]

Hamed Yaghoobian, Hamid R. Arabnia, Khaled Rasheed
2021 arXiv   pre-print
However, the figurative and creative nature of sarcasm poses a great challenge for affective computing systems performing sentiment analysis.  ...  Thus far, three main paradigm shifts have occurred in the way researchers have approached this task: 1) semi-supervised pattern extraction to identify implicit sentiment, 2) use of hashtag-based supervision  ...  Davidov et al. (2010) employ a semi-supervised learning approach for automatic sarcasm identification using two different forms of text, tweets from Twitter, and product reviews from Amazon.  ... 
arXiv:2107.02276v2 fatcat:2tgpyhchbngpnnhj3sezmj4hle

Deep Learning for Sentiment Analysis : A Survey [article]

Lei Zhang, Shuai Wang, Bing Liu
2018 arXiv   pre-print
This paper first gives an overview of deep learning and then provides a comprehensive survey of its current applications in sentiment analysis.  ...  Deep learning has emerged as a powerful machine learning technique that learns multiple layers of representations or features of the data and produces state-of-the-art prediction results.  ...  Ltd with a research gift.  ... 
arXiv:1801.07883v2 fatcat:nplicfgaozb6fbfx4eyts4zt7e

Machine Learning for Anomaly Detection: A Systematic Review

Ali Bou Nassif, Manar Abu Talib, Qassim Nasir, Fatima Mohamad Dakalbab
2021 IEEE Access  
We are also grateful to our research assistants who helped in collecting, summarizing, and analyzing the research articles for this SLR study.  ...  Ali Bou Nassif and co-authors would like to thank the University of Sharjah and OpenUAE Research and Development Group for funding this research study.  ...  It reviewed ML models from four perspectives: the application of anomaly detection type, the type of ML technique, the ML model accuracy estimation, and the type of anomaly detection (supervised, semi-supervised  ... 
doi:10.1109/access.2021.3083060 fatcat:vv7qthbvqjdz7ksm3yosulk22q
« Previous Showing results 1 — 15 out of 13,653 results